PLoS ONE plos plosone PLOS ONE 1932-6203 Public Library of Science San Francisco, CA USA 10.1371/journal.pone.0237337 PONE-D-20-05740 Research Article Engineering and technologyEquipmentCommunication equipmentCell phones People and placesPopulation groupingsProfessionsAgricultural workers Biology and life sciencesAgriculture Research and analysis methodsAnimal studiesExperimental organism systemsModel organismsMaize Research and analysis methodsModel organismsMaize Biology and life sciencesOrganismsEukaryotaPlantsGrassesMaize Research and analysis methodsAnimal studiesExperimental organism systemsPlant and algal modelsMaize Research and analysis methodsResearch designSurvey researchSurveys Biology and life sciencesAgricultureFarms People and placesGeographical locationsAfricaTanzania Biology and life sciencesAgricultureCrop scienceCropsCereal crops Mobile phone use is associated with higher smallholder agricultural productivity in Tanzania, East Africa Phone use associated with higher smallholder agricultural productivity http://orcid.org/0000-0001-7434-1500 Quandt Amy Formal analysis Investigation Methodology Project administration Resources Supervision Validation Writing – original draft Writing – review & editing 1 * Salerno Jonathan D. Conceptualization Data curation Formal analysis Funding acquisition Project administration Validation Visualization Writing – original draft Writing – review & editing 2 Neff Jason C. Conceptualization Methodology Supervision Writing – original draft Writing – review & editing 3 Baird Timothy D. Methodology Visualization Writing – review & editing 4 Herrick Jeffrey E. Methodology Writing – original draft Writing – review & editing 5 McCabe J. Terrence Investigation Methodology Writing – original draft Writing – review & editing 6 Xu Emilie Formal analysis Validation 7 Hartter Joel Conceptualization Funding acquisition Investigation Methodology Project administration Resources Supervision Writing – original draft Writing – review & editing 3 Department of Geography, San Diego State University, San Diego, California, United States of America Department of Human Dimensions of Natural Resources, Colorado State University, Fort Collins, Colorado, United States of America Environmental Studies Program, University of Colorado Boulder, Boulder, Colorado, United States of America Department of Geography, Virginia Polytechnic Institute and State University, Blacksburg, Virginia, United States of America Jornada Experimental Range, United States Department of Agriculture – Agricultural Research Service, Las Cruces, New Mexico, United States of America Department of Anthropology, University of Colorado Boulder, Boulder, Colorado, United States of America Fairview High School, Boulder, Colorado, United States of America Van Campenhout Bjorn Editor International Food Policy Research Institute, UNITED STATES

The authors have declared that no competing interests exist.

 * E-mail: aquandt@sdsu.edu 6 8 2020 2020 15 8 e0237337 27 2 2020 23 7 2020 This is an open access article, free of all copyright, and may be freely reproduced, distributed, transmitted, modified, built upon, or otherwise used by anyone for any lawful purpose. The work is made available under the Creative Commons CC0 public domain dedication.

Mobile phone use is increasing in Sub-Saharan Africa, spurring a growing focus on mobile phones as tools to increase agricultural yields and incomes on smallholder farms. However, the research to date on this topic is mixed, with studies finding both positive and neutral associations between phones and yields. In this paper we examine perceptions about the impacts of mobile phones on agricultural productivity, and the relationships between mobile phone use and agricultural yield. We do so by fitting multilevel statistical models to data from farmer-phone owners (n = 179) in 4 rural communities in Tanzania, controlling for site and demographic factors. Results show a positive association between mobile phone use for agricultural activities and reported maize yields. Further, many farmers report that mobile phone use increases agricultural profits (67% of respondents) and decreases the costs (50%) and time investments (47%) of farming. Our findings suggest that there are opportunities to target policy interventions at increasing phone use for agricultural activities in ways that facilitate access to timely, actionable information to support farmer decision making.

 University of Colorado's Research and Innovation Seed Grant Program Hartter Joel This work was supported by the University of Colorado’s Research & Innovation Seed Grant Program. Data Availability Data cannot be shared publicly due to IRB protocols and standards of privacy and confidentiality. Data are available by request from the University of Colorado Boulder Research and Innovation Office (rio@colorado.edu) in conjunction with the corresponding author (contact via aquandt@sdsu.edu) for researchers who meet the criteria for access to confidential data. Introduction

The rapid diffusion of mobile phones in the Global South has increased information flow, reduced telecommunication costs, and led to novel strategies for economic development [1, 2]. In a study of 120 developing countries, growth in mobile phone penetration coincided with economic growth [3]. Mobile phones have impacted the lives of hundreds of millions, particularly in areas with poor access to landline telephones due to a lack of infrastructure or electricity. In Sub-Saharan Africa, phones are increasingly used to provide a host of services and information across the financial, energy, and agronomic sectors. Furthermore, the ubiquity of mobile phones throughout sub-Saharan Africa offers new opportunities for rural households to realize a broader set of livelihood and development goals [4]. Information and communication technologies (ICTs), including mobile phones, have been shown to help reduce poverty in sub-Saharan Africa by strengthening and expanding social networks, cutting down on travel costs, maximizing the outcomes of necessary journeys, managing human-wildlife conflict, conducting business and financial transactions, and increasing the efficiency of livelihood activities [5–7]. For example, in Kenya, access to mobile money services was found to reduce extreme poverty in female-headed households by 22% [8] and more generally to have a positive impact on agricultural household income [9]. The benefits of ICTs have been well documented, but it is also important to note that these technologies can also exacerbate existing power imbalances and inequalities [10].

Sub-Saharan Africa is the fastest growing and second largest mobile market in the world [11]. By the end of 2017 the unique mobile subscriber penetration rate stood at 44% [12]. It is projected that the future growth of mobile phone use will be concentrated in rural areas and with a younger demographic, with approximately 300 million additional people becoming mobile phone subscribers by 2025 [12]. Smartphone connections particularly are expected to increase from 34% of connections in 2017 to 67% of connections by 2025 due to the growth of cheaper devices [12]. Electricity, particularly in rural areas, is a current barrier to mobile phone adoption [13]; however, increased access to electricity, cheaper phones, and lower costs of airtime and data continue to fuel growth [11].

The intersection of the agricultural economy and the expanding use of mobile phones has led to policy innovations related to phones for a range of agricultural services including the connection of farmers to buyers, the provisioning of inputs for farming, and the formal and informal exchange of agricultural information and recommendations [4]. Agriculture is the dominant income-generating activity in rural Sub-Saharan Africa where nearly 9 in 10 households generate income from crop production, and where non-agricultural income generation lags behind that of other developing regions [14]. Despite growing diversification of household incomes, agriculture remains the primary livelihood activity in rural areas and a focal point for economic development policies and interventions. ICTs for agricultural development initiatives are growing in number, with over 140 such initiatives reported globally in 2015 [4]. There is also a growing use of mobile phones for agricultural extension and outreach throughout sub-Saharan Africa, where agricultural extension agents must provide education, advice, and services to farmers across large geographic areas, and have little access to equipment and knowledge platforms [13, 15].

Over the past decade, the spread of these technologies has led to macro-scale improvements in agricultural market performance in developing economies [16] but with more mixed impacts locally with individual households and farmers [17]. Despite phones’ potential in the agricultural sector, there is mixed evidence on the relationship between the use of mobile phones and improved yields with evidence for positive [18–20] and neutral [21, 22] associations between ICTs and yields. Diverse, reported impacts may stem from variation in structural issues such as access to markets, transportation infrastructure, and ICTs across local contexts [23]. The diversity of conclusions may also be due in part to differences in methodologies, phone use measurements, and the many factors that must be considered in the analyses.

Many studies of mobile phone use and agricultural productivity are econometric [4], focused on outcomes and impact evaluations [24], concerned with specific agricultural services/projects [4], and based on large, national datasets [25]. However, fewer studies have examined farmers’ perceptions of ICTs and the value they hold for agriculture despite the critical role perceptions play in the adoption of innovations [26]. Often, the perception of the characteristics of an innovation, including its benefits, drives its rate of adoption [26]. This current study is unique because it focuses on the perceptions of mobile phones specifically for agricultural activities rather than simply phones themselves.

Our study addresses this gap with a survey-based approach to examine farmers’ perceptions of mobile phones and agricultural development in 4 rural villages in Iringa Region, Tanzania, where agriculture and fishing are the main sources of household income, 85% of the population had at least a primary education in 2017, nearly two-thirds lived in poverty, and 65% of individuals and 80% of households owned a mobile phone respectively [27]. Here, we use the term “perceptions” to refer to respondents’ own perceived behaviors, as opposed to researchers’ observations of research subjects’ behaviors. Our study provides a unique contribution to ICT4D scholarship by focusing on farmers’ perceptions of mobile phones and their specific uses for agricultural practices and effects associations with productivity.

This research addresses 3 main questions: (RQ1) What perceptions do farmers (male and female) have about the impact of mobile phones on agricultural productivity? (RQ2) What is the relationship between generalized mobile phone use and self-reported agricultural yield? and, (RQ3) What is the relationship between mobile phone use specifically for agricultural purposes and self-reported agricultural yield?

Lastly, this research seeks to inform food and agriculture-related policies that affect the use of technological innovations to improve food systems and agricultural productivity. Our study provides further evidence that mobile phone use can be linked to farm activities. This research is at the nexus of food, agriculture, and technology. Surprisingly, there are few existing formal international, national, or local policies addressing the use of mobile phones in the agricultural sector despite their dynamic and emerging nature. Thus, an overarching goal of this research is to inform government and NGOs policies and action plans aimed at improving agricultural productivity.

 Methods

Permission to conduct human subjects research was granted by the Tanzania Commission for Science and Technology (Research Permit No. 2017-250-NA-2017-166), and the University of Colorado Institutional Review Board (protocol # 17–0042).

Study area

Iringa Region provides an excellent setting to examine these issues. Mobile-phone use has grown steadily in this area and smallholder agriculture is widespread. Furthermore, Tanzania is one of the eight sub-Saharan African markets predicted to contribute more than a third of new mobile subscribers globally between 2016 and 2021 [28]. Additionally, the agricultural sector in Tanzania accounts for more than 45% of the country’s GDP, 65% of the export earnings, and engages 80% of the workforce [13]. The study was conducted in the villages of Kibena, Lyamgungwe, Malagosi, and Mgama, located in the Iringa Rural District of Iringa Region in southern Tanzania (Fig 1). Within this district, which had a population of approximately 270,000 in 2017, a government funded assessment reported 53% of residents engage in farming or fishing as their main economic activities, 83% had at least a primary education, and 64% of adults and 90% of households owned a mobile phone [27]. Our study villages, which are overwhelmingly agricultural, were selected because they are ethnically and economically similar, though they differ in population, area, level of development, and distance to a main road. Kibena is the most urban, as it is located on the major highway connecting Tanzania to Zambia. Mgama is located along a well-maintained murram road (hard-packed soil) a few kilometers off the main highway. Lyumgungwe and Malagosi are markedly more rural. They are located along poorly-maintained roads, and are not connected to the electrical grid. The major ethnic group represented in the study villages is Hehe with Bena as the prominent minority group, both of whom are mainly farmers, but also keep cattle and goats. Maize is the primary staple crop in all 4 villages. The majority of agriculture is rain fed. Annual precipitation averages 680mm, and the rains typically begin in late November or early December, and last through April. At least one of the 4 major mobile networks (Tigo, Vodacom, Airtel, and Halotel) is available in each of the 4 villages.

10.1371/journal.pone.0237337.g001 Study communities in Iringa Region, Tanzania. Data collection

We first conducted qualitative focus group discussions in 3 villages (Nyamihuu, Mapogoro, and Lupalama) to collect basic information about phone use and agriculture in the region. Male, female, and youth focus groups were conducted separately. Villages were selected due to their similarities with the villages that participated in the household survey, including approximate degrees of intra-household economic diversity, various levels of urbanization and/or development, and broad reliance on agriculture. The villages selected for focus groups were different than for the survey in order to avoid having survey respondents who also participated in the focus groups biasing their answers. The major goal of the focus groups was to inform the survey design, helping to create a contextually-specific survey instrument. Primary data from the focus groups are not presented in our analysis. Focus group discussion notes were qualitatively analyzed and discussed within the research team to find recurring and important themes and ideas about agriculture and mobile phone use that were then integrated into the survey instrument.

A total of 279 surveys were conducted in July 2017, which roughly corresponds to the timing of the maize harvest in the region. Informed consent was granted by respondents prior to surveys. The timing of the surveys is important, and, in the case of this research, conducting surveys during/after the maize harvest proved beneficial because yield and agricultural information was fresh in the minds of the respondents. We implemented a balanced, stratified random sample, with each of the 4 villages as strata; a goal sample of 40 household compounds per village was informed by previous research implementing similar inferential methods [29–31], and set at a level substantially higher than a recent government sponsored economic assessment in the region [27]. Households in each village were selected randomly from the village register, or roster (160 household compounds total across all 4 villages). At each household, our goal was to interview a male and female household member who engages in farming (which was determined before the survey took place), preferably the male and female household heads, or, if absent, another adult household member. On occasion, when an adult (18 or older) of 1 gender was not available, only 1 interview was conducted. Surveys were conducted by enumerators in Kiswahili, the official language of Tanzania, because all survey respondents were fluent in Kiswahili.

Enumerators first underwent a 3-day training before starting data collection, which was led by the lead author in Kiswahili. The enumerators assisted in the translation of the survey from English to Kiswahili, and conducted a practice survey before beginning survey work. Enumerators worked in teams of 2, 1 male and 1 female, with each enumerator only interviewing respondents of their same gender. Using same gender enumerators is a common practice in rural, developing areas where education is relatively low and gender roles can be hierarchical [32]. Groups of enumerators were assisted by local residents who helped to locate the randomly-selected households and provided an introduction to the household members of the research topics on behalf of the research team.

The survey included questions about demographics, phone ownership and use, social networks, and agricultural practices and productivity. Respondents were asked about their own individual behavior, perceptions, and agricultural activities. All respondents were asked the same questions because the goal of the survey was not necessarily to differentiate between groups of people, but instead to understand the overall generalized importance of mobile phone use on agricultural productivity in the study area. Furthermore, we focused the survey on maize, as it is the staple crop in the area, but also recorded other crops planted. Survey responses were based on the respondents’ perceptions and observations.

The level and type of phone ownership were determined based on 4 factors: (1) If there was a phone owned by any member of the household; (2) If the respondent personally owned any phone; (3) If they owned an internet capable phone; and (4) If they owned a smartphone. Smartphones and internet capable phones were differentiated for this research because the later are similar to non-smartphone cell phones but have the ability to access the internet (e.g., email, Facebook, etc.) through a simple interface and small screen, lacking the ability to download apps and the touch-based interface of smartphones. Other measures of phone use used in the analysis are described below.

 Data analysis

To examine farmers’ perceptions of the impacts of mobile phone technologies on agricultural productivity, we calculated simple descriptive statistics of the survey data (RQ1). To test for associations between general phone use and self-reported agricultural yield (RQ2), and also for associations between phone use specifically for agricultural purposes and self-reported agricultural yield (RQ3), we estimated separate regression models (see below). General maize yields were reported as number of 65-kg sacks per hectare of grain (not on the cob) in recent good years. These values were converted into tons per hectare for presentation and analysis. It is important to note that the weight of maize sacks can vary throughout Tanzania. Long-term residents of Iringa Region told us that they generally use 65 kg as the standard weight in Iringa Region. However, this should be considered an approximation.

RQ2 and RQ3 were operationalized into 2 separate multilevel linear statistical models predicting self-reported maize yield in a good year: a general phone use model (RQ2) and phone for agriculture model (RQ3). The decision to use multilevel models (i.e., varying effects, random effects, hierarchical models) was informed a priori by the nested structure of our data, with respondents in households in communities, and we expect variance to be correlated within these groups [33]. Our choice for multilevel models is supported in 3 ways. First, these models make more accurate estimates than ordinary linear models when data are clustered or share similarities by group, as is the case with multiple observations from the same individual, location, or time period. Second, multilevel models better account for potential imbalances in the sample. Third, multilevel models are also more appropriate when variation within and between groups in the data (i.e., group-level effects) are relevant to research questions [see [34], p. 356 for further discussion]. We do, however, test this assumption by estimating alternative specifications with fixed effect dummy variables for village for both the general phone use and phone for agriculture models. These are not as parsimonious as the reported models including varying effects for village, as determined by information criterion. (dAICc = 7 and 8, respectively) [35].

Our outcome variable, self-reported maize yield, was continuous and approximated a log-normal distribution, so we fitted Gaussian models. The 2 research questions were specified into 2 separate models conforming to the following structure: yi~Normal(μi,σ) μi=α+βxi,h,v+H+V, where the log of self-reported maize yield y by respondent i has a Gaussian distribution with mean μi and standard deviation σ. The linear predictor, μi, is specified as a function of the grand intercept α, a vector of β parameters and associated predictor variables x observed in individual i, household h, and village v. For the general phone use model (RQ2), this vector includes the focal variables total number of contacts, number of SMS messages sent and received in the past 24 hours, and number of calls made and received in the last 24 hours plus controls. For the phone for agriculture model (RQ3), this vector includes a single synthetic focal variable measuring phone use specifically for agricultural purposes derived from a set of survey questions, plus controls. These fixed effect variables are detailed just below. Varying intercept effects (i.e., random effects) H and V are understood as the household- and village-level adjustments, respectively, to the linear predictor.

The general phone use model includes 3 focal variables to evaluate the question of whether or not mobile phone use generally was associated with self-reported maize yield outcomes (RQ3). Because “phone use” can be described in multiple ways and be difficult to measure accurately across various seasons and over long periods of time, we selected 3 proxy variables that capture a range of use behaviors in our farmer population that represent longer-term and shorter-term phone use and can be measured reliably: total number of contacts saved (i.e., a measure of one’s phone-based social network accrued over a longer period of time), number of SMS messages sent and received in the past 24 hours (i.e., a measure of one’s phone-based written communication over a very short period of time), and number of calls made and received in the last 24 hours (i.e., a measure of one’s phone-based vocal communication over a short period). These measures have been used in other studies of mobile phones in rural East Africa [36, 37]. These 3 variables were square root-transformed in the model due to a high proportion of zero values along with a large number of outlier values. This transformation allowed for adequate scaling and preserved zero-values in the data, though represents a tradeoff as interpretation is less-intuitive than would be with a log-log model [33]. SMS and phone call measures for the last 24 hours served as proxies for previous phone use and were easier for respondents to recall than phone use over a longer period of time. The assumption made in selecting these variables is that phone use over the previous 24 hours is indicative of overall phone use over longer time scales, and that having a greater number of contacts is also indicative of higher levels of phone use.

The phone-for-agriculture model includes a single synthetic focal variable measuring phone use specifically for agricultural purposes to evaluate the question of whether or not the degree of mobile phone use for agricultural activities was associated with self-reported maize yield outcomes (RQ3). Since we were interested in phone use for agricultural purposes generally, and not, for example, using phones to help with fertilizer application specifically, we created a synthetic variable to represent a latent property of our nine individual-level, phone-for-agriculture variables (Table 1). These 9 variables represent different ways that respondents use phones for agriculture-related activities, which we identified through focus group discussions. Unlike the generalized phone use variables (RQ2), the phone-for-agriculture questions were not measured over the past 24 hours, but instead measured binary responses of whether or not respondents use phones for these activities. Collapsing the information in these 9 binary variables produced a single continuous variable, trading reduced dimensionality for information loss. Dimension reduction strategies commonly include ordinary principal components analysis or factor analysis [38]. Due to the binary structure of the component variables, we implemented the Gifi method of non-linear principal components analysis [i.e., homogeneity or multiple correspondence analysis; [39]]. This method does not assume normality as does ordinary principal components analysis, yet preserves relative dimensionality of the input matrix. We computed loadings based on the first principal component using the {homals} package in R, producing a single continuous predictor variable, which approximated normal and was not transformed [40].

10.1371/journal.pone.0237337.t001 Regression variable means (and standard errors) stratified by study village.

Binary variables are reported as proportions.

Lyamgungwe Malagosi Kibena Mgama Total
Dependent variable
 Self-reported maize yields in good year (tons/hectare)1 1.81 (0.17) 1.70 (0.20) 1.37 (0.11) 2.12 (0.26) 1.73 (0.10)
Independent variables
 Phone contacts 81.57 (15.46) 59.16 (9.91) 82.52 (14.49) 78.39 (10.76) 76.30 (6.62)
 Total calls in prev. 24hrs 8.64 (2.42) 8.03 (1.89) 10.26 (1.78) 10.89 (1.66) 9.56 (0.97)
 Total SMS in prev. 24hrs 8.90 (2.69) 11.11 (3.05) 15.01 (4.25) 19.24 (6.30) 13.81 (2.23)
 Phone-for-agriculture composite2 1.24 (0.14) 1.25 (0.11) 1.18 (0.11) 1.46 (0.08) 1.28 (0.06)
 Wealth score3 5.65 (0.17) 5.99 (0.22) 6.40 (0.16) 6.71 (0.20) 6.21 (0.10)
 Hectares farmed1 1.12 (0.09) 1.48 (0.18) 1.03 (0.12) 1.32 (0.14) 1.22 (0.07)
 Proportion male 0.60 (0.08) 0.63 (0.08) 0.52 (0.07) 0.58 (0.07) 0.58 (0.04)
 Age 41.62 (2.04) 42.45 (2.74) 39.35 (1.87) 41.09 (2.08) 40.98 (1.07)
 Proportion completed primary school 0.14 (0.05) 0.13 (0.06) 0.22 (0.06) 0.40 (0.07) 0.23 (0.03)
n 42 38 54 45 179

1 Areas and yields are approximate. Weights and harvested areas were estimated by the respondents.

2A synthetic variable representing degree of phone use for agricultural activities, created from HH survey responses by non-linear principal components analysis, and described in the main text.

3 Wealth score is described in the main text.

Both models included an identical set of 5 fixed effect control covariates: a wealth index, farm size, gender, age, and education level. These covariates were informed by literature review and the understood impacts anticipated on agricultural practices and phone use based on various contexts [4, 19, 41]. More generally, these variables describe important dimensions patterning variation in farm-household livelihoods [42]. Wealth is measured through a wealth-poverty index developed for monitoring and evaluation of rural development programs globally, and tailored specifically to Tanzania, derived from 10 survey questions measuring various non-monetary dimensions of wealth and poverty (e.g., female literacy, ownership of durable assets) [43]. The wealth score is scaled to a continuous measure from 0 to 10; raw values are used in the models. Farm size is reported as acres in surveys, or converted; log-transformed values for more appropriate scaling are used in the models. Respondent gender is a binary value for male. Raw values of respondent age are used in the models. Respondent education is a binary value for whether or not they completed primary school.

We implemented likelihood-based multilevel model estimation with the package {lme4} in the R statistical software environment [44]. Models were fitted to data from only those respondents owning their own phone, and for whom complete data existed with respect to variables included in models (n = 179). We evaluated model results by plotting data and coefficient estimates with 95% confidence intervals. Importantly, these not causal models but test only for significant associations. To apportion causality to mobile phones, a randomized controlled trial (RCT) would be ideal.

 Results

Table 2 provides a summary of phone ownership measures stratified by study village. Smartphone ownership and use among respondents was uncommon (6.3% of survey respondents). Thus, the use of communication tools like WhatsApp and Facebook, as well as agricultural information services, was infrequent. During focus group interviews, respondents were asked what types of agricultural activities they conduct with their phones. They reported using phones for everyday activities on the farm including hiring labor or hiring/borrowing equipment, sourcing and buying agricultural inputs, selling agricultural crops, accessing agricultural or weather information, and communication about agriculture. Table 3 presents the percentage of farmers in each of the 4 study villages who use phones in each of these ways. Importantly, 20% of respondents reported using their phones for all the agricultural purposes of interest, while 25% reported using their phone for none of these purposes.

10.1371/journal.pone.0237337.t002 Phone ownership means (and standard errors) stratified by study village.

Binary variables are reported as proportions.

Measures Lyamgungwe Malagosi Kibena Mgama Total
Phone within the household (%) 88.57 (3.83) 94.52 (2.68) 97.14 (2.01) 98.48 (1.52) 94.62 (1.35)
Own a phone (%) 77.14 (5.06) 57.53 (5.83) 88.57 (3.83) 78.79 (5.07) 75.27 (2.59)
Own an internet capable phone (%) 17.14 (4.54) 16.44 (4.37) 35.71 (5.77) 18.18 (4.78) 21.86 (2.48)
Own a smartphone (%) 2.86 (2.01) 1.37 (1.37) 8.57 (3.37) 7.58 (3.28) 5.02 (1.31)
n 70 73 70 66 279
10.1371/journal.pone.0237337.t003 Percentages of respondents using their own mobile phones for specific agricultural purposes.
Purposes % of respondents (N = 179)
Discussions with friends and relatives about agriculture 75
Selling crops 70
Talking to agricultural extension agent 65
Buying seeds or fertilizer 62
Gathering information about agricultural practices 65
Hiring or borrowing equipment 48
Using mobile money services 47
Accessing weather information 48
Hiring farm labor 50

Additionally, addressing RQ1, respondents were asked how mobile phones were affecting their own agricultural productivity. Respondents were free to respond based on their own experiences and interpretations of the questions. Approximately 47% of respondents stated that the use of a phone has reduced the amount of time they spent buying inputs or selling crops, and 50% of respondents reported that the use of a phone has reduced the amount of money they spent on farm activities. Further, 64% reported that the use of a phone has increased profits from farming compared to when the respondent did not have a phone. The percentage of respondents who answered yes to each of these questions indicates that for many, phones have increased the efficiency and cost-effectiveness of farming by reducing the time and money spent on farming activities, while simultaneously increasing profits.

Addressing RQ2, model results suggest general phone use has inconsistent associations with self-reported maize yield (Fig 2; Tables 1 and 4). The number of farmers’ phone contacts, the number of recent calls, and the number of recent SMS messages do not have credible associations with reported yield with a 95% CI. Farmers in Kibena Village have the lowest self-reported yields, and Lyamgungwe the highest, though these differences are relatively small, which is apparent in the varying effects estimates from the model-averaged predictions plots (Fig 2, colored lines).

10.1371/journal.pone.0237337.g002 General phone use model estimates for the predicted association between reported maize yield outcomes and 3 phone use predictors (RQ2).

Coefficient estimates of phone contacts (left), calls in the last 24 hours (center), and SMS sent in the last 24 hours (right) have mixed associations with the self-reported maize yield outcome, after controlling for individual-level wealth, gender, farm size, age, and education. The model is estimated with varying intercept effects at the household and village levels; village intercepts are plotted as colored lines in colors corresponding to village data points. Coefficients are plotted separately as predictions with 95% confidence intervals, with other fixed effect variables held at mean or modal values, and with averaging over uncertainty estimated across the model. See Table 4 for model estimates.

 10.1371/journal.pone.0237337.t004 Model estimates and [95% confidence intervals<xref ref-type="table-fn" rid="t004fn001"><sup>1</sup></xref>] for Figs <xref ref-type="fig" rid="pone.0237337.g002">2</xref> and <xref ref-type="fig" rid="pone.0237337.g003">3</xref>.
Maize yield (Fig 2; RQ2) Maize yield (Fig 3; RQ3)
Grand intercept -0.070 [-0.608, 0.467] -0.467 [-0.988, 0.055]
Fixed effects
 # of contacts 0.008 [-0.016, 0.031]
 # of calls2 0.052 [-0.008, 0.111]
 # of SMS2 -0.006 [-0.050, 0.038]
 Synthetic phone use variable 0.273 [0.162, 0.383]
 Wealth score 0.035 [-0.035, 0.106] 0.049 [-0.016, 0.114]
 Hectares farmed 0.339 [0.186, 0.492] 0.325 [0.182, 0.468]
 Gender (male) 0.096 [-0.093, 0.285] 0.141 [-0.018, 0.301]
 Age 0.000 [-0.007, 0.007] 0.002 [-0.004, 0.008]
 Education -0.074 [-0.288, 0.139] -0.016 [-0.218, 0.185]
Variance on varying intercept effects
 Household 0.085 0.035
 Village 0.009 0.005
Observations 179 179
Model marginal R2 0.195 0.284
Model conditional R2 0.425 0.382

1 Confidence intervals (CIs) here indicate 95% confidence that the mean of the variable for all respondents lies within the reported interval. Estimates that are significant at this level have CIs that do not cross 0.

2 Made/sent and received in the past 24 hours

Addressing RQ3, when we examine phone use specific to agricultural activities, the results suggest that phone use for agriculture is credibly associated with higher self-reported maize yield (Fig 3; Tables 1 and 4). This result is consistent across the sample after controlling for observed differences among individuals in wealth, farm size, gender, age, and education, and also after controlling for unobserved differences within households and within villages. Kibena is estimated to have the lowest yields, and Lyamgungwe the highest, as shown by the village-level varying intercept adjustments.

10.1371/journal.pone.0237337.g003 Phone for agriculture model estimates for the predicted association between reported maize yield outcomes and the degree to which farmers integrate phones into agricultural activities (RQ3).

A synthetic variable representing degree of phone use for agricultural activities was created from household survey responses by non-linear principal components analysis. Phone use for agriculture has a positive association with self-reported maize yield, after controlling for individual-level wealth, gender, farm size, age, and education. The model is estimated with varying intercept effects at the household and village levels; village intercepts are plotted as colored lines in colors corresponding to village data points. The phone use coefficient is plotted with 95% confidence intervals, with other fixed effect variables held at mean or modal values, and with averaging over uncertainty estimated across the model. See Table 4 for model estimates.

 Discussion

Our goal was to examine relationships between mobile phone use and agricultural productivity at the household and farmer levels. A key result is the positive association between phone use for agricultural activities and self-reported agricultural yields (RQ3). Further, our results find that many farmers had positive perceptions of mobile phone use increasing agricultural efficiency through increasing profits, decreasing costs, and decreasing time investments in farming (RQ1). However, our findings showed no consistent associations between general phone use and self-reported maize yield, when phone use is measured as number of contacts, number of SMS sent and received, and number of phone calls made and received within a narrow window of time (RQ2).

Our finding, that the association between yields and general phone, is not statistically significant is not necessarily surprising given that much of the other research on small-holder agricultural outcomes has focused on the use of phones to convey market and weather information [21, 22]. Alternatively, some confounding variable, such as social network, could drive both phone use and agricultural productivity, though in this context respondents did not highlight this issue during focus group interviews. Notably, qualitative analyses of phone use in East Africa have identified that daily phone-use is commonly, simply to connect with friends and family [32, 37]. A lesson here may be that given the breadth of ways that phones are used, general phone use is a poor predictor of specific economic outcomes. Also, this finding speaks to the difficulty of measuring general phone use over extended time-periods (as we discuss in the Limitations section).

Still, this result suggests that simply owning and using a mobile phone may not be enough to support agricultural productivity. Instead, how a farmer uses her phone may be critical. Other research has identified potential mechanisms behind positive relationships between using phone use and for agricultural productivity, which include: the use of mobile phones for connecting farmers to buyers [6], acquiring inputs for farming [45], reducing transaction costs and time associated with agricultural activities [46, 47], and exchanging agricultural information and recommendations [4, 48]. Our results are consistent with these findings, specifically our observations of respondents’ positive perceptions of mobile phones for decreasing time and money spent, and increasing profits from agricultural activities. Along these lines, a farmer can use his phone to communicate with a fertilizer seller in town, buy fertilizer, and then recruit a friend to help him transport the fertilizer to the farm, saving both time and money.

Our findings are also consistent with those of studies connecting mobile phone use and increased agricultural yield. A study in India [49] found that 35% of farmers who used their phones for connecting with markets, getting better prices, and getting agricultural information reported increased yields. A study of coffee farms in Uganda found positive associations between mobile phone use and increased coffee harvests, as well as higher off-farm incomes [19]. And a study in Ghana [20] concluded that a farmer with a mobile phone had, on average, an increased maize yield of 261 kg/ha per production season compared to farmers without a phone. However, these studies all employed different metrics in measuring phone use, which can have an important impact on the results, as our study shows. Ultimately, to better understand the causal mechanisms in our study area would require more involved methodological approaches, including in-depth ethnographic work, and/or an RCT.

Overall, our findings support the targeted and intentional use of ICTs as a strategy to improve agricultural productivity and economic development. Mobile phones can support development by increasing household management efficiency [1, 16, 50] and contributing to existing livelihood activities [37]. They can provide people and communities in rural parts of the developing world with access to digital information and resources, as well as new types of knowledge sharing platforms [51, 52]. Our results highlight the importance of mobile phones at individual- and household-scales, and complement research at larger scales, which highlights how mobile phone penetration and use can improve agricultural market performance in developing economies [16].

Policy implications

The results presented in this paper highlight 2 important areas for potential future policy interventions aimed at improving agricultural productivity for smallholder farmers while providing other social and economic benefits [53]. First, simply owning and using a mobile phone may have little impact on improving smallholders’ yields. Alternatively, our findings suggest that when farmers’ use phones specifically and intentionally for a range of agricultural tasks, yields can improve. Consequently, governmental and non-governmental interventions should encourage smallholders to use phones specifically for tasks throughout the agricultural enterprise to increase the likelihood that phone use has a positive impact on yield. This could include strategies that promote farmer education on the uses of ICTs for agriculture, as well as the development of extension services via mobile phones. For example, a national governmental agricultural extension agency could promote technology trainings to farmers, as well as extension services via mobile phone technologies, such as SMS and call-in services. These types of policies may also enable the extension agency to reach out to a greater number of farmers, and provide easy access to important agricultural information [13, 15].

Second, the results highlight the importance of perception in the adoption of new technologies that may be promoted by various policies. Often, regardless of what policy interventions are implemented, critical to the adoption of any innovation are the perceived benefits from stakeholders [26]. The results presented in this paper show that many respondents had positive perceptions of mobile phone use for agriculture, which suggests that they are ready to adopt greater mobile phone use within the agricultural sector. Thus, timely policy interventions would likely be well received within the study communities. This also highlights that in other contexts, studies of stakeholder perceptions of any intervention are important to understand the likely success of a given policy.

 Limitations and future directions

First, in controlling for demographic characteristics including farm size, wealth, and gender, our goal was to gain a basic understanding of the relationship between phone use expressly for agricultural purposes and self-reported yield, but not to examine other associations. Also, we did not control for the influence of other ICTs such as radio or television, largely due to the limited access to electricity for most respondents. Furthermore, we did not include more nuanced control variables such as ‘entrepreneurship’ and ‘innovativeness’, which are culturally relative and difficult to measure. However, the topic of differential impacts of ICTs is something we plan to explore in future work, especially given the growing body of research focused on the ‘digital divide’ in access and use of ICTs between men and women [4, 24].

Second, measuring both the character and volume of phone use over long periods is also challenging. Research respondents’ abilities to recall phone use over long periods is low and soliciting this information can lead to estimation errors. In this study, we avoided this by getting reliable measures over a narrow amount of time. Also, measuring phone use specifically for agricultural activities can be complicated by the seasonality of the agricultural cycle. Accordingly, future research on phone use should examine the temporal nature of agricultural practices in order to more effectively measure the impact of phone use on agricultural productivity throughout the agricultural cycle. For this study, data collection took place at the end of the harvest season.

Third, while many respondents reported greater profits from agriculture and less money spent on agricultural activities through the use of a mobile phone, this does not necessarily factor in the costs of mobile phone ownership and use itself. Owning and using a mobile phone does have financial costs which can include purchasing of the phone, buying phone credit, and paying for phone charging services. These costs were not accounted for in this study, and could possibly influence the costs and benefits of using mobile phones for agricultural activities if the cost of owning and using a mobile phone exceeds the financial benefits from using phones for agricultural activities.

Lastly, it is important to note that while phone use is mainly an individual activity, agricultural productivity is generally a household outcome. Therefore, there is a mismatch in scale between phone use and agricultural productivity. In this study we aimed to address this by interviewing both male and female household members. However, innovative methods for studying phenomena at these 2 different scales may help better address these issues in the future.

 Conclusions

Addressing the objectives of this paper, we conclude the following: (RQ1) many farmers had positive perceptions about the benefits of mobile phones for their agricultural productivity; (RQ2) there was not a significant relationship between general mobile phone use and self-reported maize yield; and (RQ3) there was a positive significant relationship between mobile phone use for agricultural activities and self-reported maize yield.

Our research indicates that there are significant policy opportunities to leverage the existing use of ICTs to increase efficiency, yields, and profits, by better directing the use of mobile phones towards agricultural activities. This potential will grow as phone use continues to expand and new agricultural strategies and technologies are developed. However, technology-based policy interventions are not panaceas and need to be part of comprehensive strategies for rural economic development including investments in physical infrastructure, education, health services, and access to electricity [54].

We are grateful to smallholder farmers who took time out of their days to contribute participate in this research. We are also grateful to our survey enumerators who spent 3 weeks in the field conducting surveys in the 4 communities.

 References Aker JC, Mbiti IM. Mobile phones and economic development in Africa. J Econ Perspect. 2010; 24(3): 207–232. Richard E, Mandari E. Factors influencing usage of mobile banking services: the case of Ilala District in Tanzania. ORSEA Journal. 2017; 7(1): 42–54. Qiang C. Telecommunications and economic growth. Washington, DC: The World Bank; 2009. Aker JC, Ghosh I, Burrell J. The promise (and pitfalls) of ICT for agriculture initiatives. Agr Econ. 2016; 47: 35–48. Donner J. Research approaches to mobile use in the developing world: a review of the literature. Inform Soc. 2008; 24(3): 140–159. doi: 10.1080/01972240802019970 Sife AA, Kiondo E, Lyiimo-Macha JG. Contribution of mobile phones to rural livelihoods and poverty reduction in Morogoro Region, Tanzania. The Journal on Information Systems in Developing Countries. 2010; 42(3): 1–15. Lewis AL, Baird TD, Sorice MG. Mobile phone use and human-wildlife conflict in northern Tanzania. Environ Manage. 2016; 58(1): 117–129. doi: 10.1007/s00267-016-0694-2 27017517 Suri T, Jack W. The long-run poverty and gender impacts of mobile money. Science. 2016; 354(6317): 1288–1292. doi: 10.1126/science.aah5309 27940873 Kikulwe EM, Fischer E, Qaim M. Mobile money, smallholder farmers, and household welfare in Kenya. PLoS ONE. 2014; 9(10): e109804. doi: 10.1371/journal.pone.0109804 25286032 Carmody P. The informationalization of poverty in Africa? Mobile phones and economic structure. Information Technologies and International Development. 2012; 8(3): 1–17. International Telecommunications Union. Retrieved from https://www.itu.int/en/ITU-D/Pages/default.aspx. Accessed October 23, 2018. GSMA (Global System for Mobile Communications Association). The Mobile Economy: Sub-Saharan Africa. 2018; UK, London. Martin R, Kahamba JS. Access and use of information communication technologies by agricultural extension agents in Tanzania. Huria Journal. 2017; 24(2): 82–96. Davis B, Di Guiseppe S, Zezza A. Are African households (not) leaving agriculture? Patterns of household’s income sources in rural Sub-Saharan Africa. Food Policy. 2017; 67: 153–174. doi: 10.1016/j.foodpol.2016.09.018 28413253 Msoffe G, Chengula A, Kipanyul MJ, Mlozi MRS, Sanga CA. Poultry farmers’ information needs and extension advices in Kilosa Tanzania: evidence from mobile-based extension, advisory and learning systems (MEALS). Library Philosophy and Practice (e-journal). 2018; 1710. Asongu S, Boateng A. Introduction to special issue: Mobile technologies and inclusive development in Africa. Journal of African Business. 2018; 19(3): 297–301. Nakasone E, Torero M, Minten B. The power of information: the ICT revolution in agricultural development. Annu Rev Resour Econ. 2014; 6: 533–50. Chavula HK. The role of ICTs in agricultural production in Africa. J Dev Agric Econ. 2014; 6: 279–289. doi: 10.5897/JDAE2013.0517 Sekabira H, Qaim M. Can mobile phones improve gender equality and nutrition? Panel data evidence form farm households in Uganda. Food Policy. 2017; 73: 95–103. Issahaku H, Abu BM, Nkegbe PK. Does the use of mobile phones by smallholder maize farmers affect productivity in Ghana? Journal of African Business. 2018; 19(3): 302–322. Fafchamps M, Minten B. Impact of SMS-Based Agricultural information on Indian Farmers. World Bank Econ Rev. 2012; 26(3). Camacho A, Conover E. The Impact of Receiving Price and Climate Information in the Agricultural Sector. IDB Working Paper 2011; number 220 Aker JC, Ksoll C. Can mobile phones improve agricultural outcomes? Evidence from a randomized experiment in Niger. Food Policy. 2016; 60: 44–51. doi: 10.1016/j.foodpol.2015.03.006 Baumüller H. The little we know: an exploratory literature review on the utility of mobile phone-enabled services for smallholder farmers. J Int Dev. 2018; 30: 134–154. doi: 10.1002/jid.3314 James J. A sequential analysis of the welfare effects of mobile phones in Africa. Soc Sci Comput Rev. 2018; 1–12. Rogers EM. Diffusion of Innovations, 5th Edition. New York, New York: Simon and Schuster; 2003. Chimilila C, Ibrahim A, Chengula F, Mushi E, Seifert J, Kewe S. Finscope Tanzania. Iringa Regional Report. Financial Sector Deepening Trust. 2017; 69 pages. GSMA (Global System for Mobile Communications Association). The Mobile Economy Africa 2016. London, UK, 1–60. Lawson DW, James S, Ngadaya E, Ngowi B, Mfinanga SGM, Borgerhoff Mulder M. No evidence that polygynous marriage is a harmful cultural practice in northern Tanzania. P Natl Acad Sci. 2015; 112:13827. Mosha DB, Vedeld P, Katani JZ, Kajembe GC, Tarimo AK. 2018. Contribution of Paddy Production to Household Income in Farmer-Managed Irrigation Scheme Communities in Iringa Rural and Kilombero Districts, Tanzania. J of Agr Studies. 2018; 6:100–122. Salerno J. 2016. Migrant decision-making in a frontier landscape. Environ Res Lett. 2016; 11: 044019. Summers KH, Baird TD, Woodhouse E, Christie ME, McCabe JT, Terta F, et al. Mobile phones and women’s empowerment in Maasai communities: How men shape women’s social relations and access to phones. J Rural Stud. 2020; 77: 126–137. Gelman A, Hill J. Data Analysis Using Regression and Multilevel/Hierarchical Models. New York: Cambridge University Press; 2007. McElreath R. Statistical Rethinking: A Bayesian Course with Examples in R and Stan. Chapman & Hall/CRC Press; 2015. Burnham KP, Anderson DR. Model Selection and Multimodel Inference: A Practical Information-Theoretic Approach, 2nd edition. New York: Springer-Verlag; 2002. Lewis AL, Baird TD, Sorice MG. Mobile phone use and human-wildlife conflict in Northern Tanzania. Environ Manage. 2016. doi: 10.1007/s00267-016-0694-2 27017517 Baird TD, Hartter J. Livelihood diversification, mobile phones and information diversity in Northern Tanzania. Land Use Policy. 2017: 460–471. Everitt BS. An introduction to latent variable models. London: Chapman & Hall; 1984. Gifi A. Nonlinear Multivariate Analysis. Chichester, England: Wiley; 1990. de Leeuw, Mair P. Gifi Methods for Optimal Scaling in R: The Package homals. J Stat Softw. 2009; 31: 1–20. Krone M, Schumacher KP, Dannenberg P. The impact of mobile phones on knowledge access and transfer of small-scale horticultural farmers in Tanzania. DIE ERDE-Journal of the Geographical Society of Berlin. 2014; 145(3): 158–161. Ellis F, Mdoe N. 2003. Livelihoods and Rural Poverty Reduction in Tanzania. World Dev. 2003; 31:1367–1384. Poverty probability index [internet]. New Haven, CT, USA: Poverty Index. Povertyindex.org/country/tanzania R Core Team. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. 2017; URL https://www.R-project.org/. Martin LM, Abbott E. Mobile phones and rural livelihoods: diffusion, uses, and perceived impacts among farmers in rural Uganda. USC Annenberg School for Communication and Journalism. 2011; 7(4): 17–34. Asif AS, Uddin MN, Dev DS, Miah MAM. Factors affecting mobile phone usage by the farmers in receiving information on vegetable cultivation in Bangladesh. Journal of Agricultural Informatics. 2017; 8(2): 33–43. Mwantimwa K. Use of mobile phones among agro-pastoralist communities in Tanzania. Inform Dev. 2017; 1–15. doi: 10.1177/0266666917739952 Dannenberg P, Lake T. The use of mobile phones by Kenya export-oriented small-scale farmers: insights from fruit and vegetable farming in the Mt. Kenya Region. Economia Agro-Alimentare. 2013; 3: 55–76. Mittal S, Mehar M. How mobile phones contribute to growth of small farmers? Evidence from India? Quarterly Journal of International Agriculture. 2012; 51(3): 227–244. Ogbeide OA, Ele I. Smallholder farmers and mobile phone technology in sub-Sahara agricultural. Mayfair Journal of Information and Technology Management in Africa. 2015; 1(1): 1–19. Mtega WP, Ngoepe M. Chapter 11: Strengthening the Flow of Agricultural Knowledge Among Agricultural Stakeholders: The Case of Morogoro Region in Tanzania. In: Thomas C, editor. Ontology in Information Science. London, United Kingdom: Intech Open; 2018. p. 255–278. doi: 10.5772/intechopen.72731 Weld G, Perrier T, Aker J, Blumenstock JE, Dillon B, Kamanzi A, et al. eKichabi: information access through basic mobile phones in rural Tanzania. CHI 2018, April 21–28, Montreal, QC, Canada. 2018. Herrick JE, Abrahamse T, Abhilash PC, Ali SH, Alvarez-Torres P, Barau AS, et al. Land Restoration for Achieving the Sustainable Development Goals: An International Resource Panel Think Piece. Nairobi, Kenya: United Nations Environment Programme, International Resource Panel; 2019. World Bank. World Bank Development Report: Digital Dividends. Washington, D.C.: World Bank Group; 2016. 10.1371/journal.pone.0237337.r001 Decision Letter 0 Van Campenhout Bjorn Academic Editor 2020 Bjorn Van Campenhout This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Submission Version 0

28 Apr 2020

PONE-D-20-05740

Mobile phone use associated with higher smallholder agricultural productivity in Tanzania, East Africa

PLOS ONE

Dear Dr. Quandt,

I hope you are well in these challenging times. I have now received review reports from two experts in the field. Based on these and my own reading, I have decided to request some revisions to be made. You will see that one of the reviewer starts out pretty critical, noting that still a lot of work will be needed to make the manuscript suitable for publication. However, you will also see that many of this reviewers comments are not all that substantial, mostly related to the presentation. I would therefore suggest to focus more on the comments of the other reviewer, that is more positive but points out a few issues that needs to be address.

For my own reading, I like the random effects model, but also wonder if a simple linear (pooled) regression, or a regression with fixed effects for the villages would yield conclusions that differ much. If the latter is the case, reasons should be explored.

I agree with the reviewer that variables should not be excluded just because they are not significant; you should be guided by theory.

While you are mostly careful not to attribute a causal interpretation to the relationships you find, I think it would not hurt to have an extra paragraph making explicit that, ideally, these sort of questions should be investigated using an RCT or other method that can isolate exogenous variation in phone use. Related, I agree with the reviewer that you can not control for (un)observables (something you later also admit) by including wealth in your regression: wealth is endogenous.

Finally, you combine different dimensions of phone use into one indicator. But number of contacts in phone may measure a very different attribute than eg calls placed. The first one may be a proxy for social network, which has also been found to yield increments for many reasons (access to finance,...). Thus, finding a correlation may not be because of phone use but due to social network effects. This will have implications for policy.

I am thus more optimistic than reviewer 2 and think it should not take too much effort to respond to these issues. I do want to stress though, that I will expect to see some additional regressions in the response to reviewers such that we get a sense of the robustness of the findings, that is, that results are not driven by the small sample.

When you are ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter.

To enhance the reproducibility of your results, we recommend that if applicable you deposit your laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols

Please include the following items when submitting your revised manuscript:

A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). This letter should be uploaded as separate file and labeled 'Response to Reviewers'.

A marked-up copy of your manuscript that highlights changes made to the original version. This file should be uploaded as separate file and labeled 'Revised Manuscript with Track Changes'.

An unmarked version of your revised paper without tracked changes. This file should be uploaded as separate file and labeled 'Manuscript'.

Please note while forming your response, if your article is accepted, you may have the opportunity to make the peer review history publicly available. The record will include editor decision letters (with reviews) and your responses to reviewer comments. If eligible, we will contact you to opt in or out.

We look forward to receiving your revised manuscript.

Kind regards,

Bjorn Van Campenhout, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. We note that you have indicated that data from this study are available upon request. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly. For more information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions.

In your revised cover letter, please address the following prompts:

a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent.

b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings as either Supporting Information files or to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories.

We will update your Data Availability statement on your behalf to reflect the information you provide.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Partly

Reviewer #2: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: No

Reviewer #2: No

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: No

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: No

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Review comments

Manuscript ID – PONE – D – 20 – 05740: Title: Mobile Phone use Associated with Higher Smallholder Agricultural Productivity in Tanzania – East Africa. Due date: 3rd April 2020

General Comments:

Good focus of the paper and with a clear new novelty (Perceptions on MP use versus agricultural productivity. Well written and referenced but a few technical comments highlighted below if addressed would make the paper better. Some robustness checks would be so nice to include (a different method of analysis to back up similar results as these results here)

Specific Comments:

TITLE:

1. I think there should be a “,” and “is” between “use” and “associated”

ABSTRACT

2. Generally comprehensive and easy to understand

3. there should be some highlights on the data sample size used,

4. and methods used to analyze the data should also be concisely highlighted in the abstract

INTRODUCTION

1. Generally, well written, referenced and easy to understand.

2. However – villages of interest in Tanzania are not mentioned at all, or

3. Perhaps some specific statistics of this Iringa province, since all statistics mentioned here are only at regional or government level. Provincial or village specific stats, would make the write up stronger.

4. Novelty is clear that, the paper focuses on farmers’ perceptions on agricultural productivity, which has rarely been researched

5. A good mix of qualitative and quantitative approach

METHODS

1. Some specific statistics about the four villages – would be interesting to look at here briefly

2. Line 178 – what is meant by “household diversity?” Technically this is largely used with regards to household production diversity or household dietary diversity, so it may be confusing here – and you may need another term to avert the potential confusion to readers

3. Line 187 – what informed the sample size of 279? Some background could be helpful

4. Line 204 – how was it likely to influence the responses by having same gender enumerator/respondents? This needs to be explained as it is not usual, and would be a potential source of biases

5. Lines 288 – 290 – variables age and education based on several literatures can influence mobile phone use, as well as agricultural yield. Moreover, they also make logical sense to be controlled for other than being merely excluded because they were not significant. This would deny us potentially logical and economic sense/significance based modelling which is another excellent component for validity of results on top of statistical significance. I would wish to see how the model results come out with these logical, and economically valid variables included

6. Also, a wealth index and use of mobile phones, could be endogenous; how was this potential endogeneity handled?

7. Line 295 – use either 1 to 100 or one to a hundred – to avert potential confusion

8. Line 296 – was farm-size transformed because it was not normal? If yes, this has to be stated, but not only stated for a few variables

9. Lines 309 – 311 – the assumption of number of calls or SMSs reflecting long time use of the phone; did you control for the seasonality aspect? I would assume that during the planting or harvesting seasons, phone calls would be more. Perhaps, you may need to clarify on the seasonality aspect with regards to this assumption

RESULTS

1. Table 1; were these statistics different across the 4 villages? It would be nice to show these. Also, in discussions of these results, it would be good to briefly show how these compare with national statistics or regional or provincial ones.

2. In Table 2, presenting results in percentages would make it easier for comparison and understanding

3. Table 3 – for ease of understanding results in line with usual literature – could you show the significance levels of each of the control variables by asterisk? Also reduce the grid lines in the table for more neatness.

4. Age and Education should also be controlled for in the results of this table 3 for their potentially significant logical and economic importance.

DISCUSSIONS

1. Line 404 – could you be specific with these confounding factors that contrary to general literature – led the results of general MP use not to be associated significantly with yield? This would make the paper more “self-contained” and independent

2. In Policy Implications – perhaps you must strongly make it clear that this advise is intended to “smallholder farmers” who are investigated in this paper. Otherwise – blindly advising policy to generally support MP use on specific agricultural activities may not have similar results for cattle herdsmen who are also common in rural Tanzania.

CONCLUSIONS

1. There was only about 4% of the sample using smart phones – and why make this a priority concluding remark in line 528 – in the first real paragraph that should be aimed at the central results of the study.

Reviewer #2: The attachment provides a detailed analysis of my my thinking about this manuscript. The reviewer thinks that with a very major revision, the paper can improve and substantially be at the point where it can be acceptable for publication. Authors would have to do a lot work, though in in this period, in order to get the manuscript to an acceptable level.

I encourage them to follow the points raised in my reviewer comments very carefully. and I will be willing and hopefully, available to to do another round of review of this paper if needed.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: Yes: Dr. Haruna Sekabira

Reviewer #2: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files to be viewed.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email us at figures@plos.org. Please note that Supporting Information files do not need this step.

Submitted filename: Review comments _05740.docx

Submitted filename: Review of PONE-D-20-05740.pdf

 10.1371/journal.pone.0237337.r002 Author response to Decision Letter 0 Submission Version 1

9 Jul 2020

RESPONSE TO REVIEWERS

Editor comments

I hope you are well in these challenging times. I have now received review reports from two experts in the field. Based on these and my own reading, I have decided to request some revisions to be made. You will see that one of the reviewer starts out pretty critical, noting that still a lot of work will be needed to make the manuscript suitable for publication. However, you will also see that many of this reviewers comments are not all that substantial, mostly related to the presentation. I would therefore suggest to focus more on the comments of the other reviewer, that is more positive but points out a few issues that needs to be address.

RESPONSE: Thank you for your effort to review our paper. We appreciate the thoughtful comments and have worked hard to incorporate them into our revised paper. Along these lines, we have made substantive revisions to every section of the paper to improve the quality of the writing and the clarity of our communication. We have made revisions to the modeling and presentation of data and findings, including overhauls of each of the tables and figures. We believe these revisions, which are described in greater detail throughout our response to reviewers’ comments, greatly improve the quality of the paper.

EDITOR: For my own reading, I like the random effects model, but also wonder if a simple linear (pooled) regression, or a regression with fixed effects for the villages would yield conclusions that differ much. If the latter is the case, reasons should be explored.

RESPONSE: We estimated 2 alternatives to each of the models presented in the revision, the first a simple linear model without the random effects for village (leaving out village effects entirely), and the second a regression with fixed effects for village. Estimates for focal variables and controls were relatively the same across revised presented models and these alternatives (i.e., coefficient estimates and standard errors differed slightly, but credibility or significance of estimates were the same). That is, for our general phone use model only farmed area was credibly associated with reported maize yield; and, for our phone use for agriculture model, phone-for-agriculture and farmed area were credibly associated with reported maize yield. Therefore, we do not report these additional models and rely on our a priori justification for using a multilevel model with random effects for village. We do, however, note in the Methods that our reported model specification ranks higher by AICc information criterion than the alternative, and include dAICc scores. However, if the editor feels strongly that the alternative models should be included in the revised text, then we are happy to comply.

EDITOR: I agree with the reviewer that variables should not be excluded just because they are not significant; you should be guided by theory.

RESPONSE: We agree that age and education level serve as good additional controls, and we have included them in the revised models. Notably, they were not excluded from the original submission based on the estimates, rather we opted for a more parsimonious model. The original text was not clear on this point. However, we agree that these additional variables are wise to include in both revised models. Estimates of our focal variables remain relatively unchanged.

EDITOR: While you are mostly careful not to attribute a causal interpretation to the relationships you find, I think it would not hurt to have an extra paragraph making explicit that, ideally, these sort of questions should be investigated using an RCT or other method that can isolate exogenous variation in phone use. Related, I agree with the reviewer that you can not control for (un)observables (something you later also admit) by including wealth in your regression: wealth is endogenous.

RESPONSE: While economists are often concerned about exogeneity, other fields have different perspectives. Our group, which is composed primarily of human geographers and anthropologists, derives some confidence in our study from our qualitative focus groups conducted in the field to understand mechanisms and ultimately shape the design of our survey. Still, as noted, we avoid “causal” language opting instead for language of “relationships” or “associations.” Also, we now include a clear statement at the end of the methods section that describes how the models are not causal, and that an RCT would be ideal.

EDITOR: Finally, you combine different dimensions of phone use into one indicator. But number of contacts in phone may measure a very different attribute than eg calls placed. The first one may be a proxy for social network, which has also been found to yield increments for many reasons (access to finance,...). Thus, finding a correlation may not be because of phone use but due to social network effects. This will have implications for policy.

RESPONSE: The original text was not entirely clear. We have revised the model description in the Methods section, and restructured the Results for better clarity. Contacts, calls, and texts are estimated separately in the general phone use model (see Fig. 3). Also, we’ve discussed these in greater detail in the methods. And we’ve discussed the potential for social networks to serve as an omitted causal variable in the discussion section. In the phone for agriculture model, we do combine multiple measures of agricultural phone use into an index measure as the focal variable, including using phones for accessing information on fertilizer or hiring farm labor. Lastly, we’ve revised the policy implications section to be more specific and conservative.

EDITOR: I am thus more optimistic than reviewer 2 and think it should not take too much effort to respond to these issues. I do want to stress though, that I will expect to see some additional regressions in the response to reviewers such that we get a sense of the robustness of the findings, that is, that results are not driven by the small sample.

RESPONSE: We note the additional models estimated and revisions made in our response just above. Here we include fixed effect coef estimates from each reported models and the two alternatives to each.

General phone use model, as reported in revision, with village random/varying effects:

# Estimate Std. Error t value

#(Intercept) -0.0703427 0.2741156 -0.257

#sqrtPhContacts 0.0075574 0.0118448 0.638

#sqrtCallTotal 0.0515576 0.0304081 1.696

#sqrtSmsTotal -0.0063911 0.0224546 -0.285

#scaledPovertyScore 0.0351852 0.0358823 0.981

#logFarmHectPlant 0.3388541 0.0781271 4.337*

#male 0.0963103 0.0963723 0.999

#as.numeric(age) 0.0001625 0.0034560 0.047

#edLevSec -0.0741210 0.1089327 -0.680

General phone use model, with no village effects

# Estimate Std. Error t value

#(Intercept) -0.0449657 0.2669384 -0.168

#sqrtPhContacts 0.0081260 0.0118962 0.683

#sqrtCallTotal 0.0498101 0.0305475 1.631

#sqrtSmsTotal -0.0073511 0.0226110 -0.325

#scaledPovertyScore 0.0292653 0.0355737 0.823

#logFarmHectPlant 0.3553133 0.0768808 4.622*

#male 0.0992511 0.0965557 1.028

#age 0.0002841 0.0034790 0.082

#edLevSec -0.0603360 0.1087211 -0.555

General phone use model, with village fixed effects:

# Estimate Std. Error t value

#(Intercept) -0.2462413 0.2977124 -0.827

#sqrtPhContacts 0.0070669 0.0118938 0.594

#sqrtCallTotal 0.0527244 0.0305543 1.726

#sqrtSmsTotal -0.0051489 0.0225070 -0.229

#scaledPovertyScore 0.0398582 0.0366041 1.089

#logFarmHectPlant 0.3260410 0.0800655 4.072*

#male 0.0930076 0.0969894 0.959

#age 0.0001362 0.0034648 0.039

#edLevSec -0.0844512 0.1100695 -0.767

#as.factor(village)LYAMGUNGWE 0.2711080 0.1308731 2.072*

#as.factor(village)MALAGOSI 0.0986482 0.1363669 0.723

#as.factor(village)MGAMA 0.2440906 0.1261938 1.934*

Phone for agriculture model, as reported in revision, with village random/varying effects:

# Estimate Std. Error t value

#(Intercept) -0.466821 0.266043 -1.755

#phAgLoad 0.272561 0.056312 4.840*

#scaledPovertyScore 0.048771 0.033043 1.476

#logFarmHectPlant 0.325143 0.073103 4.448*

#male1 0.141193 0.081337 1.736

#as.numeric(age) 0.002237 0.003139 0.712

#edLevSec -0.016479 0.102698 -0.160

Phone for agriculture model, with no village effects

# Estimate Std. Error t value

#(Intercept) -0.456685 0.261457 -1.747

#phAgLoad 0.276297 0.056434 4.896*

#scaledPovertyScore 0.044510 0.032651 1.363

#logFarmHectPlant 0.334173 0.072170 4.630*

#male1 0.141747 0.081587 1.737

#as.numeric(age) 0.002407 0.003152 0.764

#edLevSec -0.008811 0.102058 -0.086

Phone for agriculture model, with village fixed effects:

# Estimate Std. Error t value

#(Intercept) -0.593713 0.285615 -2.079

#phAgLoad 0.265868 0.056733 4.686*

#scaledPovertyScore 0.054234 0.034055 1.593

#logFarmHectPlant 0.314582 0.075212 4.183*

#male1 0.140365 0.081525 1.722

#as.numeric(age) 0.002033 0.003149 0.646

#edLevSec -0.025678 0.104654 -0.245

#as.factor(village)LYAMGUNGWE 0.225751 0.118982 1.897(*)

#as.factor(village)MALAGOSI 0.058243 0.123694 0.471

#as.factor(village)MGAMA 0.179576 0.116765 1.538

Regarding additional changes not noted below, we recalculated and reformatted tables. Due to a missing value, recalculated means and standard errors for certain variables are slightly different from those reported in the original submission. Missing values are dropped by default when estimating regression models with lme4 in R, and so regression estimates were unaffected.

Reviewer 1 comments

General Comments:

Good focus of the paper and with a clear new novelty (Perceptions on MP use versus agricultural productivity. Well written and referenced but a few technical comments highlighted below if addressed would make the paper better.

Specific Comments:

Title

1. I think there should be a “,” and “is” between “use” and “associated”

RESPONSE: We have added “is” but don’t see how the “,” makes sense grammatically.

Abstract

2. Generally comprehensive and easy to understand

3. there should be some highlights on the data sample size used,

4. and methods used to analyze the data should also be concisely highlighted in the abstract

RESPONSE: We agree, and implement these changes in the revised abstract.

Introduction

1. Generally well written, referenced and easy to understand.

2. However – villages of interest in Tanzania are not mentioned at all, or

3. Perhaps some specific statistics of this Iringa province, since all statistics mentioned here are only at regional or government level. Provincial or village specific stats, would make the write up stronger.

4. Novelty is clear that, the paper focuses on farmers’ perceptions on agricultural productivity, which has rarely been researched

5. A good mix of qualitative and quantitative approach

RESPONSE: We’ve provided Iringa specific statistics in the Introduction.

Methods

1. Some specific statistics about the four villages – would be interesting to look at here briefly

RESPONSE: We’ve included district-level statistics (agriculture, education, phone ownership) in the study-site section of the methods.

2. Line 178 – what is meant by “household diversity?” Technically this is largely used with regards to household production diversity or household dietary diversity, so it may be confusing here – and you may need another term to avert the potential confusion to readers

RESPONSE: Indeed, we refer here to intra-household, economic diversity. This language, along with some surrounding language, has been changed to be clearer.

3. Line 187 – what informed the sample size of 279? Some background could be helpful

RESPONSE: Revised text details a goal sample of 40 household compounds per village, which was informed by previous research implementing similar analytical methods; multiple individuals were surveys in each household.

4. Line 204 – how was it likely to influence the responses by having same gender enumerator/respondents? This needs to be explained as it is not usual, and would be a potential source of biases

RESPONSE: Conversely, our experience working in this area has taught us that having male enumerators for female respondents can be problematic due to cultural norms. We now include the following language in the text: “Using same gender enumerators is a common practice in rural, developing areas where education is relatively low and gender roles can be hierarchical.”

5. Lines 288 – 290 – variables age and education based on several literatures can influence mobile phone use, as well as agricultural yield. Moreover, they also make logical sense to be controlled for other than being merely excluded because they were not significant. This would deny us potentially logical and economic sense/significance based modelling which is another excellent component for validity of results on top of statistical significance. I would wish to see how the model results come out with these logical, and economically valid variables included

RESPONSE: We agree that age and education level would serve as good additional controls, and we have included them in the revised models. Notably, they were not excluded from the original submission based on the estimates, rather we opted for a more parsimonious model. The original text was incorrectly stated. However, we agree that these additional variables are wise to include in both revised models. Estimates of our focal variables remain relatively unchanged.

6. Also, a wealth index and use of mobile phones, could be endogenous; how was this potential endogeneity handled?

RESPONSE: Through our qualitative focus group interviews, we learned that wealth/poverty are important drivers of yield, as they affect smallholders’ ability to acquire farm inputs. We also learned that phones help farmers to be in touch with extension agents who can provide useful information. These responses give us confidence that the wealth and phone-use represent distinct mechanisms that are directly related to yield. Also, we are clear throughout the paper that we are not presenting causal models. Still, our models include covariates that meaningfully describe maize yields in these small-holder farming systems (i.e., wealth, acres, location, etc.). With our analyses, we’re looking to explain additional variance in yield that can be apportioned to variance in phone use. Finally, the wealth index used is a multi-dimensional measure of wealth and poverty, which we now articulate in the revised text rather than only supplying the reference.

7. Line 295 – use either 1 to 100 or one to a hundred – to avert potential confusion

RESPONSE: We’ve changed this to “1 to 100”

8. Line 296 – was farm-size transformed because it was not normal? If yes, this has to be stated, but not only stated for a few variables

RESPONSE: Substantial revisions to the Methods make each variable transformation clear.

9. Lines 309 – 311 – the assumption of number of calls or SMSs reflecting long time use of the phone; did you control for the seasonality aspect? I would assume that during the planting or harvesting seasons, phone calls would be more. Perhaps, you may need to clarify on the seasonality aspect with regards to this assumption

RESPONSE: We don’t assume that SMS reflect phone use over a long period of time. Instead, it serves as a proxy of phone use during a short period of time, as we now indicate in text. Similarly, phone calls also serve as a proxy for use (vocal rather than written communication) over a short period. We use phone-contact list as a proxy of use over a comparatively longer period. We are now clear about this in the text. We also now acknowledge the issue of seasonality. And notably, our measurements are taken during an agricultural active season - harvest season.

Results

1. Table 1; were these statistics different across the 4 villages? It would be nice to show these. Also, in discussions of these results, it would be good to briefly show how these compare with national statistics or regional or provincial ones.

RESPONSE: We understand this comment to mean that the reviewer is looking for significance tests on means across villages. This information is not central to our research questions and reporting these statistics would overly complicate the table, and burden the reader. We do however report village-level means with standard errors to give interested readers a sense of how data are patterned across villages.

2. In Table 2, presenting results in percentages would make it easier for comparison and understanding

RESPONSE: Table 2 does report whole number percentages. We’ve made a small adjustment to the column heading so that it’s easier to read.

3. Table 3 – for ease of understanding results in line with usual literature – could you show the significance levels of each of the control variables by asterisk? Also reduce the grid lines in the table for more neatness.

RESPONSE: We avoid categorizing coefficient estimates as “significant” in order to avoid confusion with null hypothesis significance testing and frequentist approaches. Rather, models make estimates with associated standard errors and confidence intervals, which we report at the 95% level. We opt for this approach following shifting norms of practice away from statistical significance in line with the American Statistical Association and numerous publishing groups . To help with understanding and readability, we bold coefficients estimated as credible at 95% confidence in the Table. Likewise, we reformatted tables for easier reading in review.

4. Age and Education should also be controlled for in the results of this table 3 for their potentially significant logical and economic importance.

RESPONSE: As stated in the response above, age and education are included as additional controls in the revised models.

Discussions

1. Line 404 – could you be specific with these confounding factors that contrary to general literature – led the results of general MP use not to be associated significantly with yield? This would make the paper more “self-contained” and independent

RESPONSE: We’ve changed this section, replacing 3-4 sentences with new language that better addresses how our findings fit with existing research. We explain how the non-significance of our general phone-use variable is not surprising when compared with other studies, which have focused on market and weather information. And we cite other research that suggests that most phone use is not about specific economic activities. We feel that this is a much improved interpretation of this non-significance.

2. In Policy Implications – perhaps you must strongly make it clear that this advise is intended to “smallholder farmers” who are investigated in this paper. Otherwise – blindly advising policy to generally support MP use on specific agricultural activities may not have similar results for cattle herdsmen who are also common in rural Tanzania.

RESPONSE: We have taken this advice and included specific language about small-holder farmers throughout the section. Also, we are more specific in our advice, noting that intentional phone use across a range of agricultural tasks is most likely to positively impact yields.

Conclusions

1. There was only about 4% of the sample using smart phones – and why make this a priority concluding remark in line 528 – in the first real paragraph that should be aimed at the central results of the study.

RESPONSE: We agree, and have shifted this concluding paragraph back to a focus on mobile phones broadly.

Reviewer 2 comments

This article seeks to “examine relationships between mobile phone use and agricultural productivity at the household and farmer levels” in Tanzania. Authors utilize multi-level modeling and principal component analysis to examine the nature and type of relationships between farmers’ perception and mobile phone use in agriculture, and the level of agricultural productivity, measured by maize yields per hectare. There are three findings: First, a positive relationship between mobile utilization and agricultural yields. Second, a positive relationship between farmer-perception of mobile phones and “agricultural efficiency” in terms of lower costs, higher profits, and lower “time investments in farming”. The third finding is that there is “no-consistent association between general phone use and self-reported maize yield” (in terms of the number of contacts, SMS sent and received, and calls made and received in short intervals).

Based on these findings, authors proposed policy recommendations including support for intentional use of mobile phones for agricultural production and the relevance of farmers’ perception about mobile phone usage in agriculture. Their main conclusion is that there are important policy prospects that can help leverage current ICT usage to upsurge the extent of agricultural gains associated with mobile use in developing countries.

General observation: The topic is nice and can be relevant in advancing an understanding of the constraints to adoption of agricultural technologies like ICTs and other critical technologies that contribute to the sustainable development goals (SDGs) especially hunger and climate change. However, the current version of the paper needs substantial improvement or a complete overhaul if it is to be acceptable for publication. Furthermore, authors should let a non-author read the paper for consistency checks before making any resubmission.

RESPONSE: As noted above, we have made substantive revisions to every section of the paper to improve the quality of the writing and the clarity of our communication. We have made revisions to the modeling and presentation of data and findings, including overhauls of each of the tables and figures. We believe these revisions, which are described in greater detail throughout our response to reviewers’ comments, greatly improve the quality of the paper.

Major comments

A. Writing, narrative, and structure

1. The paper is not well written. It lacks a coherent structure, which makes it hard for me to see what the authors are really trying to achieve.

RESPONSE: Substantive revisions to the quality of the writing have been made in each section of the manuscript.

2. I do not see a compelling contribution to literature. The potential contribution mentioned on pg. 5 (lines 111-120) has some problems including the endogeneity of perception due to its subjectivity, which the authors do not seem to address.

- Authors do not clearly articulate the study’s relevance beyond the setting.

- The proposed policy contributions on pg. 6 (lines 135-143) appear more like study objectives than actual policy contributions. Better writing can be helpful here.

RESPONSE: not addressed

3. Insufficient motivation for use perception as the key policy variable in this study. Why should we care about the perception of farmers in the use of mobile phones for agriculture when the technology is not new?

- What is novel about mobile phone utilization in agriculture in the region, elsewhere in

Africa, and beyond? I would like to see a more convincing justification on this subject and the use of perception as a policy var. Perception, in fact, is a major determinant of technology adoption and/or program participation in many contexts.

- I don’t see what is new about farmers’ perception of mobile phone use for agriculture in this context.

RESPONSE: We see that the use of the word perception is confusing. In the paragraph of the introduction where we describe our specific study, we now define our use of the term “perceptions.”

4. Another critical problem is how agricultural productivity is measured – crop yields are not the only measure of productivity.

- Self-reported yield estimates are weak due to several associated errors.

- What actions did you take to account for this risk? See relevant example papers on this critical topic (Amadu et al., 2020; Desiere and Jolliffe, 2018; Godlonton et al., 2017; Judge and Schechter, 2009; Wossen et al., 2019).

RESPONSE: not addressed

5. Insufficient description of the study area and data. Figure 1, the google earth map, is blurry. Please use an actual GIS map with coordinates to show your study sites (e.g., Coulibaly et al., 2017; Rana, and Miller, 2019; Van Campenhout, 2017). In general, all the Figures are blurry and unacceptable.

RESPONSE: We apologize for the low resolution figures in the original submission. Regarding the map, it was not Google Earth imagery but an SRTM DEM surface to display elevation, overlaid with road networks and household locations. However following the reviewers advice, we include a revised, simplified study region map.

B. Data, conceptual framework and variables

1. There is no conceptual framework for the paper. Authors can do a better job by presenting a conceptual framework that guides the statistical operations in the paper. This is critical for any quantitative analysis.

RESPONSE: not addressed

2. Therefore, the “Data analysis” section (pg. 10+) does not make much sense to me. For instance, how are the key variables measured like perception, various uses of mobile in relation to agriculture? See for example (Amadu et al., 2020; Rana, and Miller, 2019).

RESPONSE: Substantial revisions have been made throughout the methods section.

3. Therefore, the two models presented on pg. 11 (lines 254 & 255) and not clear.

RESPONSE: Substantial revisions have been made throughout the methods section.

4. Paper lacks a convincing presentation of data. I kept revising the paper to see:

- how can I understand and interpret the data and results (albeit not really a result, but descriptive stats – more on this below).

- For example, on pg. 9 (lines 193 – 196), I am confused as to whether some household members did not undertake farming? Is this articulated in the narrative? If yes, where? If no, why not?

RESPONSE: We have made substantial improvements to our methods section and each of our tables.

5. Moreover, I suggest you provide a “theoretical expectations” section to guide the interpretation of the key variables based on sound literature review. This is lacking and need attention.

- For example, you may want to caption part of pg. 12 to 13 as either literature review, or theoretical expectation, instead of making statements like “these covariates were informed by literature...” (pg. 13, L. 286).

- We expect literature to inform your work. Therefore, just present a section to discuss the main vars and covariates in terms of what obtains elsewhere and expectations in this setting.

RESPONSE: While we avoid creating a new section, we have added justifications for our choice of variables in appropriate sections.

6. Following the above points, there should been a summary stats’ table upfront to show the mean of all variables in the analysis.

RESPONSE: Table 2 now does this for the regression models.

7. On pg. 9, writing on lines 198 to 206 is wordy. Consider using concise language for

clarity. For e.g., use pretesting of questionnaires, instead of “conducted a practice survey ...” (lines 202-203). On the same pg., (lines 209-212), delete sentence starting with “All respondents ... study area”. It is wordy and adds little.

RESPONSE: This language has been revised.

C. Results, discussion, policy, limitation, and conclusion

1. The presentation of your results seems clumsy. For instance, your “results” (pg. 14) look

more like descriptive statistics. Thus, I think Table 1 should be labelled ‘summary statistics’ rather than “results based on ...”. These are not rigorous analytical results.

RESPONSE: We’ve made revisions to each table and split table 1 into 2 tables. Each table has a revised title. And summary statistics for model variables are not reported in table 2.

2. Some variables in Table 1 had not been discussed in the narrative of the paper – the more reason you need to have a theoretical expectations section above. For example, “good year” is mentioned on pg. 11 (line 241) but not defined. “Bad year” is not mentioned earlier at all. Likewise, “synthetic phone” had not been defined earlier in the narrative, except for the mention of “synthetic variables” on pg. 12 (line 271).

RESPONSE: Greater care has been taken with our descriptions/representations of all variables in the text and in the tables.

3. Table 1 and all Tables should have notes immediately below, not above in the Table title.

RESPONSE: We have moved the notes below the table.

4. Table 2 does not have a good title. Consider presenting the title of a Table as a statement

like ‘proportion of respondents using phones.” Moreover, there should be a note under the Table to provide clarity. The table is not clear. Is there a column for the interaction of these variables such as using phones to discuss with friends and for selling crops? The Table does not present a complete picture.

RESPONSE: All the tables have new titles.

5. Table 3 is not clear. Same points as above such as proper labelling and notes.

RESPONSE: We have also adjusted this table in accordance with these notes.

6. The “discussion” section (pg. 20 – 22) reads more like a results section.

RESPONSE: Substantial revisions have been made to the discussion section so that it better compares our findings to the findings from other studies.

7. On pg. 24, “intensity and frequency” appear for the first time in the paper. Why?

- These are loaded terms, which should have been described in introduction or study area description before using them anywhere else.

- Or they should have been conceptualized/operationalized in this study and then included in the analysis before using them here in the “limitations...” section. \\

RESPONSE: We recognize that these words are loaded in some disciplines and have thus changed them to more appropriate words for this context.

8. I like your discussion of potential mechanisms (pg. 21) through which mobile phones

may lead to yield enhancement. However, you do not provide statistical analyses for any of these mechanisms in the paper to bolster your findings (see. For example, Van Campenhout, 2017).

RESPONSE: Throughout the manuscript now, we avoid the word “mechanism/s” except when discussing alternative approaches to examining the effect of mobile phones on agricultural productivity.

9. Following the above point, there should be a robustness check for your findings.

RESPONSE: not addressed

10. The conclusion is too terse and makes no sense. Should be succinct but convey enough

information to appear as ‘stand-alone’ for an impatient reader. For example, the starting sentence (pg. 26 line 518) is awkward. In short, I would not consider this section as a conclusion for the paper because it presents little or nothing about the rest of the paper.

RESPONSE: We’ve revised the conclusion so that it is summative and forward looking without replicating the abstract.

Other/Minor comments

1. Be consistent about the use of sub-Saharan Africa versus Africa. To maintain the flow,

choose one and stick to it, or you can indicate your intentional inter-use at the beginning of the paper and move on.

RESPONSE: We’ve changed everything to sub-Saharan Africa.

2. Introduction is too long being 4 pages. Reduce to 2 or 2.5 pages.

RESPONSE: The introduction is slightly shorter now.

3. On pg. 5 (line 108) remove many before fewer studies.

RESPONSE: Done.

4. On pg. 6 (line 140-143), delete sentence starting with “Thus... and ending with

productivity”. That whole sentence is not only poorly written but does not really add much to the argument of the paper.

RESPONSE: This sentence has been shortened and rewritten.

5. On pg. 7 (L. 156) insert ‘distance from’ after “in relation to” ...

RESPONSE: Done.

6. Also, on pg. 7, delete from lines 167 – 168. It adds nothing.

RESPONSE: Done.

7. On pg. 8 (L. 171), write Data (delete collection). On line 173, write ‘Data for this study

come from before “Focus group...”

RESPONSE: The beginning of this paragraph has been adjusted.

8. Pg. 9: On L. 193, delete “both a”. On L. 194, write members.

RESPONSE: Done.

9. On pg. 12, line 266 is missing something. Following line 255, I expected the two models.

RESPONSE: This whole section has been revised.

10. The entire paper can be significantly enhanced if the authors can clean up typos.

RESPONSE: Substantial revisions have been made in each section. And we’ve done our best to root out all typos and grammatical errors.

References

Amadu, F. O., Miller, D. C., McNamara, P. E., 2020. Yield effects of climate-smart agriculture aid investments in southern Malawi. Food Policy. 92, 101869. https://authors.elsevier.com/a/1ay3A15oGp6Skf.

Coulibaly, J.Y., Chiputwa, B., Nakelse, T. and Kundhlande, G., 2017. Adoption of agroforestry and its impact on household food security among farmers in Malawi. Agricultural Systems, 155, 52-69.

Desiere, S., Jolliffe, D., 2018. Land productivity and plot size: Is measurement error driving the inverse relationship? Journal of Development Economics. 130, 84–98. https://doi.org/10.1016/j.jdeveco.2017.10.002.

Godlonton, S., Hernandez, M. A., Murphy, M., 2017. Anchoring Bias in recall data: Evidence from Central America. Amer. J. Agr. Econ. 0(0), 1–23; doi: 10.1093/ajae/aax080.

Judge, G., Schechter, L., 2009. Detecting Problems in Survey Data Using Benford's Law. Journal of Human Resources 44 (1) 1-24.

Rana, P., Miller, D. C., 2019. Explaining longterm outcome trajectories in social–ecological systems. PLoS ONE 14(4): e0215230. https://doi.org/10.1371/journal.pone.0215230.

Van Campenhout, Bjorn., 2017. There is an app for that? The impact of community knowledge workers in Uganda, Information, Communication & Society, 20:4, 530-550, DOI: 10.1080/1369118X.2016.1200644

Wossen, T., Alene, A., Abdoulaye, T., Feleke, S., Manyong, V., 2019. Agricultural technology adoption and household welfare: Measurement and evidence. Food Policy 87, 101742. https://doi.org/10.1016/j.foodpol.2019.101742.

Submitted filename: PLOS One RESPONSE TO REVIEWERS.docx

 10.1371/journal.pone.0237337.r003 Decision Letter 1 Van Campenhout Bjorn Academic Editor 2020 Bjorn Van Campenhout This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Submission Version 1

24 Jul 2020

Mobile phone use is associated with higher smallholder agricultural productivity in Tanzania, East Africa

PONE-D-20-05740R1

Dear Dr. Quandt,

After reading your responses to earlier comments, I have decided that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Bjorn Van Campenhout, Ph.D.

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

 10.1371/journal.pone.0237337.r004 Acceptance letter Van Campenhout Bjorn Academic Editor 2020 Bjorn Van Campenhout This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

29 Jul 2020

PONE-D-20-05740R1

Mobile phone use is associated with higher smallholder agricultural productivity in Tanzania, East Africa

Dear Dr. Quandt:

I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department.

If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org.

If we can help with anything else, please email us at plosone@plos.org.

Thank you for submitting your work to PLOS ONE and supporting open access.

Kind regards,

PLOS ONE Editorial Office Staff

on behalf of

Dr. Bjorn Van Campenhout

Academic Editor

PLOS ONE