The research protocol was approved by the ethical review committees of the Asociación Benéfica PRISMA and the Johns Hopkins Bloomberg School of Public Health. All participants provided written informed consent prior to data collection, including consent for audio-recording.

Arequipa is the second largest city in Peru, located in an arid zone 2,300 m above sea level [15]. The outskirts of the city contain hundreds of peri-urban pueblos jóvenes (young towns or shantytowns) and pueblos tradicionales (traditional towns). Pueblos jóvenes are low-income hillside squatter settlements founded over the past 60 years [17],[18]. Pueblos tradicionales tend to be in lower-lying flat areas, are inhabited by higher-income landowners, and date back to the late 19^th or early 20^th century. (See Figure 1 for photos of the two types of communities.) Because preliminary data from our research group indicated that T. infestans prevalence differed between these two types of towns [12], we compared migration and settlement patterns in 3 pueblos jóvenes and 2 pueblos tradicionales.

The research team worked with 2–3 community leader “gatekeepers” in each community to ensure acceptance and to recruit people who could provide detailed information about their personal history of migration and settlement (for interviews) or community history (for focus groups). A total of 94 female and male participants were enrolled in the study.

This was a qualitative study that employed focus group discussions and in-depth interviews. Focus group sessions were carried out with 8–10 participants in each community at central, well-known locations (health establishments, community centers) selected by the gatekeepers. We used participatory methodologies to explore the community's demographic characteristics and mobility patterns, and historical and current presence of triatomine vectors. Participants created community maps [19] which formed the basis for discussions of the history and characteristics of communities. Participants then created a timeline [19] of important community events dating back approximately 40 years, first exploring general events and then focusing on events related to Chagas disease and vector infestation. All sessions were audio-recorded; participatory activities were recorded on large sheets of paper that were hung on the wall and visible to all participants.

In-depth interviews utilized an event history calendar (EHC), a highly structured but flexible interview style that facilitates recall by using the individual's own experiences as cues [20]. Interviews were carried out with 10 participants per community, and explored migration history, experience with Chagas disease, the presence of its vectors, and customs of raising animals in each place of residence, starting from birth. Each interview, held at a location selected by the participant (their home, the focus group location), was audio-recorded and lasted 45 to 60 minutes. All interviews and focus groups were conducted by two of the authors (AB and GH).

Presence of vectors was examined by asking participants when they had seen triatomine bugs. Because T. infestans is the sole insect vector for Chagas disease in southern Peru, we only asked participants to recall the presence of this species. All of the study communities had been involved in insecticide application programs run by the Ministry of Health (MOH) and as a result were broadly familiar with T. infestans, which they refer to as a “chirimacha.” In this context, there is no other bug that goes by the same name. We also showed images of T. infestans to participants to aid their recall. During interviews, participants were asked if they recalled seeing triatomine bugs in their house or in their community for the specific years they lived in each place of residence. During focus groups, participants were asked to reach a consensus regarding the year that triatomine bugs first appeared and the areas most infested.

Data on the number of households, estimated population, and year of insecticide application were collected by our research group in collaboration with the Arequipa Regional Office of the Ministry of Health (MOH). The domiciliary infestation index (DII) is a community level variable equivalent to the number of infested houses divided by the total number of houses surveyed. We used ArcView 9.1 (ESRI) and existing maps to estimate the distance of each community from Arequipa and its surface area (to calculate population density).

Detailed notes were taken from focus group audio-recordings and the large sheets of paper, and synthesized into matrices in Excel by theme and by community to carry out further analysis. Audio-recordings of interviews were transcribed verbatim from digital audio recorders to word processing programs and analyzed using the grounded-theory approach. Grounded theory refers to theory that is developed inductively from a body of data, in contrast to theory that is derived deductively from grand theory and not necessarily based on data. The grounded theory approach is applied by reading textual data, in this case transcripts and field notes, in order to discover the main concepts or themes that were mentioned during data collection, allowing the data to reveal its message (or theory) instead of looking for confirmation of a previously-developed hypothesis [21],[22],[23],[24]. Further information about grounded theory can be accessed via the web links listed in the references [25],[26]. Two authors (AB and GH) created a code set based on the main themes that emerged in the interviews after an initial reading of the transcripts. The Atlas-ti software (Scientific Software Development GmbH, 2005) was used to apply the codes to each interview transcript. The event history calendars themselves were also analyzed by entering the information into a single timeline in Excel, such that each decade from 1900 to the present year detailed the places of residence of participants and the presence of triatomine vectors in those places. The superimposition of the EHCs on a timeline allowed us to visualize patterns in migration and vector presence over time. Each coded interview was analyzed together with the interviewee's EHC and all focus group and interview data were analyzed by community and then across communities.

During the EHC interviews, all moves were recorded, including a change of abode within the same community. For the purposes of this analysis, only a change of resident community for one month or more, whether temporary or permanent, was considered as a movement.

Fifty people provided in-depth interviews and 44 participated in focus groups. Interview participants had a median age of 52 and 47 years for males and females, respectively, with a range of 20 to 80 years. Focus group participants had a median age of 67 for males and 49 for females, with a range of 20 to 79 years (Table 2). Older community members were purposely recruited for focus groups, to ensure knowledge of historical events.

Males moved more frequently than females, with a median of 3.0 (Interquartile range (IQR) 1.0–4.0) lifetime moves for females and 4.0 (IQR 2.5–5.5) for males. There was also more migration among residents of pueblos jóvenes: 80% of participants from pueblos jóvenes were in-migrants, while 60% of participants from pueblos tradicionales were non-migrants (Table 3). Typical patterns of migration are shown in Table 4. Residents of pueblos jóvenes typically moved from a rural birth community to the Arequipa area early in life due to economic stress. Later moves took them to a pueblo jóven near Arequipa in search of cheap housing and then multiple, short-term moves continued throughout life in search of work. Some residents of pueblos tradicionales also moved from a rural area to Arequipa during childhood or adolescence, usually for schooling. Later moves were few since these residents tended to settle in the pueblo tradicional to focus on building agricultural enterprise and raising a family. The majority of participants who migrated from rural areas recalled raising farm animals in their birth places, and many continued to raise animals, especially guinea pigs, rabbits and poultry, in peri-urban Arequipa.

Study participants indicated that the pueblos jóvenes of Arequipa's urban periphery were mostly settled by people from greater Arequipa and the northern Andean regions of Cusco and Puno, and in lesser numbers by people from the southern coastal/Andean region of Moquegua (see map insert in Figure 2). The formal founding dates of the pueblos jóvenes in this study ranged from 1970 to 1981, although some residents had lived in these settlements since the 1960s. Migration from rural birthplaces to urban Arequipa was motivated by acute economic stress, with a few families sending their children away to work as early as age six. This early move was followed by migration later in life to a pueblo joven to acquire land and housing. Each quote presented in the Results section is followed by the participant's sex, age, type of current community, and the years corresponding to the movement. Two examples of interviewees who moved alone as children follow:

Other participants moved with their entire family for work:

Migration to pueblos jóvenes enabled early settlers to acquire land at little cost as squatters invading land. The pueblo tradicional of Tío Chico is located just below several hillside pueblos jóvenes, including Guadalupe:

By contrast, residents who arrived after the original invasion bought an existing house or land parcel, rented a house or room, or lived with family members. Pueblos jóvenes are still expanding in geographic area and population, and currently are composed of multiple generations, including the original migrants, their children and grandchildren, and newly-arrived migrants.

Pueblos tradicionales are made up primarily of people who have lived in the community since birth and whose families have lived there for several generations. As in pueblos jóvenes, the founding migrants arrived in search of land and housing. However they usually purchased this higher-cost land:

Later migrants tended to move to pueblos tradicionales motivated by a return to family roots or the search for a calmer environment:

Current migration dynamics are causing important changes to the population of pueblos tradicionales. Many people, especially young people, are moving out of pueblos tradicionales due to a lack of opportunities. In the two pueblos tradicionales in this study, out-migration has resulted in diminished populations and a shortage of agricultural workers. To compensate, land owners hire temporary workers who are often migrants to the peri-urban areas of Arequipa. In Tío Chico, these workers do not live in the town itself since there are few available houses and they can live more affordably in the surrounding pueblos jóvenes. In contrast, Quequeña, being further from the city, lacks housing options other than the town itself. Rental is therefore common since the property owners have moved and need people to watch over their properties and work their land. As a result, Quequeña is experiencing relatively recent in-migration, while Tío Chico is not.

A constant across most participants' adult lives was migration to live with a partner or spouse and children:

Across communities, the search for work was a constant that often spanned generations, with migration in early life by parents and in later life by participants. These participants described the almost constant movement of their fathers in search of work:

Male participants described their own search for work opportunities and female participants discussed similar searches by their partners:

Forty-six (92%) of 50 interviewees had seen triatomine vectors (locally known as chirimachas) during their lifetimes in some place of residence; the four who did not report seeing chirimachas lived in the pueblo tradicional of Tío Chico (Figure 3). Participants reported seeing no triatomines in the highland Andes regions of Cusco and Puno, where many migrants were born. In addition, the urban center of Arequipa (often the first place of residence for low-income migrants to Arequipa) was described as vector-free.

The earliest sighting of triatomines occurred in Moquegua in 1942, a sending area for some migrants to urban Arequipa that is located south of the study communities (Figure 2). Other early memories came from the rural areas of Valle de Vitor and La Joya, both valleys west of Arequipa. The study community of Villa La Joya is a pueblo joven founded near the more rural and longer established community of La Joya. Villa La Joya had its first residents in the early 1960s, but chirimachas were not memorable until the town was much more populated in the late 1970s and 1980s.

Closer to the urban center, reported vector presence showed a similar pattern of infestation following settlement, but much more recently. The first memories of urban vector presence from study participants were from the pueblo joven of Jacobo D. Hunter in 1968, a peri-urban district settled in early squatter invasions. Years later, in 2002, Hunter was the setting of a highly publicized child death due to acute Chagas disease [27]. Peri-urban pueblos jóvenes increased in number and size during the 1960s and 1970s, and vector presence was reported in the urban pueblos jóvenes of our study roughly 20 years following original settlement. Participants from Guadalupe (founded in 1970) and Nueva Alborada (founded in 1981) noted the first widespread appearance of triatomines in 1988 and 2002, respectively.

In pueblos tradicionales, vector reports followed a different pattern than in the pueblos jóvenes. Although their settlement dates back to the mid-1800s, focus group participants recalled first seeing vectors in Quequeña around 1978. They noted that chirimachas were especially concentrated in the area of town around a communal stable and zones of relatively newer settlement by migrants. Tío Chico, in contrast, had very few reports of infestation, and much later (from 2000). The following quotes contrast the degree of infestation between Tío Chico and Guadalupe, the hillside pueblo joven located above Tío Chico. Participants specifically associated infestation with the presence of domestic animals.

Residents reported continuous presence of chirimachas in all study communities except Tío Chico until insecticide spraying occurred (Figure 3).

According to MOH vector control data, the pueblos tradicionales in our study had considerably lower infestation rates than pueblos jóvenes (Table 1). The high infestation rates in pueblos jóvenes parallel higher population densities of 10,300–15,000 inhabitants/km², compared to 1,700–3,300 inhabitants/km² in pueblos tradicionales (Table 1).