Globally, urban transport is an important determinant of population health, with 1.35 million road traffic deaths being reported in 2016, and road traffic collisions costing most countries around 3% of their Gross Domestic Product [1]. The Global Burden of Disease study recorded in 2019 that transport injuries were one of the top 15 causes of death and disability among working age adults in countries with a High or High-Middle Sociodemographic Index [2]. In addition to the direct public health impacts, urban transport also indirectly contributes to air and noise pollution, reduced road safety, physical inactivity and sedentary behaviour [3]. Consequently, researchers, governments, transport planners, and other stakeholders (e.g., road safety and active travel charities) are seeking ways to reduce the detrimental impact of urban transport on public health, as well as other agendas such as climate change.

A common traffic management method is to try and reduce speeds [4]. Speed reduction interventions have been implemented in two main ways: ‘speed limits’ (signage without physical infrastructure); and ‘speed zones’ (signage with physical infrastructure (e.g., chicanes, humps)) [5, 6]. In 2014 an umbrella review investigating the health implications of 20mph zones and limits concluded that residential and area-level schemes (traffic calming 20mph zones) can reduce road traffic collisions, injuries, traffic speed and volume, improve perceptions of safety, and be cost-effective [7]. More recently, a meta-narrative evidence synthesis published in 2019 suggested that whilst the evidence for 20mph zones was established, the effects of 20mph limits was less clear [8]. Additionally, the effects on different socio-economic groups and communities are not well understood [7, 8].

Without the need to install physical infrastructure like speed humps or chicanes, 20mph speed limit interventions are cheaper to implement, making them an attractive option to local governments. However, the absence of these features means the intervention is less coercive, being more akin to guiding rather than restricting driver choice. Hence the uncertainty around whether 20mph speed limit interventions can effectively reduce speeds through changing behavioural norms. Consequently, awareness raising, enforcement and educational activities are important components of 20mph speed limit interventions.

Between 2016 and 2018, City of Edinburgh Council (United Kingdom) increased the proportion of roads in the city with 20mph limits from 50% to 80% [9,10]. The aim of the current study was to describe any changes in traffic speed and traffic volume that followed the implementation of the 20mph speed limit intervention in Edinburgh. Our research objectives were to:

The city-wide 20mph (32km/h) speed limit intervention in Edinburgh, Scotland, was implemented between July 2016-March 2018 [9]. This was a city council policy, with a range of anticipated outcomes including reductions in speed, improved public perceptions of safety, reductions in risk and severity of collisions, and improved liveability [10]. The intervention was implemented in four phases across seven ‘implementation zones’ over the 2-year period (see Table 1) [10, 11]. A network of ‘key arterial routes’ remained at higher speeds (30, 40, 50 and 60mph) in order to facilitate necessary travel while minimising risks [11]. The budget for the intervention was £2.22 million, incorporating signage, a Traffic Limit Order, enforcement, and extensive awareness raising and educational campaigns [12].

The ‘Is Twenty Plenty for Health?’ study was a National Institute for Health Research (NIHR) funded project to evaluate the 20mph speed limit intervention in Edinburgh (and also a similar scheme in Belfast, Northern Ireland) [13]. The project had four key work-packages (i) evaluate policy processes and political conditions that led to 20mph implementation, (ii) develop a qualitative understanding of implementation and effects, (iii) assess quantitative outcomes of the implementation, and (iv) conduct cost-effectiveness analysis. The current study was designed to contribute to work-package (iii) by quantifying changes in traffic speed and volume.

To address the research questions, this study describes analyses of repeated (pre-post) measures of traffic speed and volume on the same streets with a 12-month interval. As such, we have described it as an observational, longitudinal evaluation of a natural experiment.

Twelve months after a 20mph speed limit intervention across the city of Edinburgh, Scotland, mean speeds were observed to have reduced by 1.34mph (95% CI, 0.95 to 1.72) representing a 5.7% change. Importantly the distribution of overall speeds also shifted. The proportion of vehicles driving at speeds greater than 25 mph at 12 months post-intervention was 14% points lower. Taken together this is consistent with a significant public health impact [16]. The changes in volume of traffic (86 fewer vehicles per week (95% CI: -112 to 286)) were relatively smaller (2.4% change) and there is uncertainty on the direction of effect. This evidence does not indicate an effect on traffic volume of public health significance at 12 months post-intervention.

Reductions in speed were observed throughout the day and across the week. Importantly, larger reductions in speed were observed in the upper tail of the distribution of speeds, especially vehicles travelling over 30mph where the risk of injury or death from a collision is markedly increased [8]. There were differences by implementation zone, with zones that received 20mph earlier generally showing larger reductions in speed; of the three later zones there were non-significant reductions (Zone 4) and increases (Zone 6) in speed. This may be indicative of a change in the driving norms across the city. In the last two implementation zones to become 20mph, the pre-implementation average speed was already close to 20mph (Zone 5, 20.14mph, Zone 6, 20.25mph). The largest reduction (2.41mph) was observed in Zone 1b which was the most rural of the implementation zones. The finding that speeds were higher at night is consistent with speed limit interventions being less coercive than 20mph zones.

The small non-significant change in volume could indicate that the Edinburgh 20mph limit intervention did not have a meaningful impact on modal choice. Anticipated outcomes of 20mph limit interventions include an increase in active travel and liveability, through people finding the roads safer to cycle on and/or walk near, potentially choosing to leave their car at home.

The small change in volume is an indication that the significant change in speed is due to a shift in driver behaviour, rather than the reduction in the number of journeys. This is also supported by the fact that the correlation between traffic speed and volume remained the same before and after the intervention.

Repeat cross-sectional surveys of public attitudes to the Edinburgh 20mph scheme identified higher levels of support for the policy and in rule following after it had been implemented, but no change in perceptions of safety [17]. This might offer an explanation for the reduction in speed, but the lack of marked change in vehicle volume. While people altered their driving behaviour (to drive slower), they did not on the whole switch mode as they did not feel that cycling or walking had become safer. It may be that safety is not the driving force for mode choice in Edinburgh, or perhaps it takes longer than 12 months for safety perceptions and subsequent mode choice to change.

A number of previous studies have sought to quantify or report the impact of 20mph interventions on traffic speed. In our 2019 review, grey literature was identified that reported uncontrolled before and after evaluations of four UK based 20mph speed limits [8]. All four evaluations reported reductions in average speed due to 20mph limits implementation. Reductions varied between Manchester (0.7mph reduction) [18], Bristol (2.7mph reduction) [19], Edinburgh (pilot scheme) (1.9mph reduction) [12], and Portsmouth (1.3mph reduction), with the Edinburgh pilot scheme and Portsmouth reporting greater reductions on roads with higher baseline speeds [20]. In a recent evaluation of twelve case study schemes in England, Atkins and Maher (2018) reported that median speeds had fallen by 0.7mph in residential areas and 0.9mph in city centre areas [21]. They also reported that faster drivers had shown greater reductions in speed.

Cairns et al.’s 2014 umbrella review of 20mph intervention effects reported a 9 mph reduction across 3 areas in UK [22] and that 85% of vehicles were travelling under 30km/h (20mph) post-intervention in The Netherlands [23]. However, as these interventions were traffic calming measures and infrastructure (20mph zones) the larger magnitude of effect is not directly comparable.

The size of the reduction in speed observed in Edinburgh is consistent with previous studies and reviews of 20mph limits, although it is not as large as the reduction observed in some places. Some variation in the size of reduction is to be expected due to differences in context and study design. For example, the greater magnitude of reduction in Bristol (2.7mph) might be explained by higher baseline speeds (27.1mph compared to 23.6mph in Edinburgh), the longer implementation/study period (2–3 years compared to 12 months), and differences in data collection and analysis (quasi-stepped wedge design and reported an adjusted reduction compared to unadjusted pre-post analysis) [19, 24]. In addition, the Edinburgh intervention increased coverage from 50% to 80% of streets [10, 11] and intervention effects may have been larger if initial coverage had been lower. There may also have been differences in implementation, enforcement, and ultimately compliance between studies that have not been recorded or reported. There is little literature for comparison in terms of effects on traffic volume, or factors associated with the odds of reduction in average volume.

There are several strengths and limitations to consider when appraising these findings. In terms of limitations, it was not possible to include data from comparison or control streets in the analysis, as the data utilised were collected by the local council rather than within a research project where control site data collection may have been funded. If this were possible it could have helped to identify the independent effects of the intervention. The analysis here cannot rule out that the changes in speeds observed could have happened anyway (secular trends), or how much of the observed changes can be attributed to the intervention (rather than other events or interventions within the timeframe under analysis).

The assessment of the feasibility of a control or comparison site for research of 20mph limits can be potentially complicated. Should controls be identified within the same city, or would contamination be inevitable? If selected in another city, the impact of extraneous variables present in one site but not the other would need to be accounted for. It is worth reflecting that in a dynamic and complex system such as a city, so many variables change over a 12-month period (e.g., road works, safety campaigns, police enforcement, parking availability, etc.) that even a controlled design and analysis would be subject to many uncontrolled (and often unknown) variables.

The use of council collected data was both a strength and limitation. It meant that research costs were substantially lower, and that baseline data for implementation Zones 1, 2 and 3 were available, as these adopted 20mph limits before the study was funded. However, it meant there was no influence over volume, location, or timing of data collection, which are all potential sources of bias. The council selected 66 streets, but a larger sample could have given better representation of the city, and at a zone level. The automatic counter data are themselves objective (even if placement was a subjective choice) and provide a high number of observations which is a strength. It is also important to recognise that the implementation zones are represented by different numbers of streets, proportions of main to residential street categories, geographical areas, traffic volumes, density of road networks, and population size. For example, Zone 6 was represented by only 5 streets.

The identification of effective interventions to reduce traffic speeds and related harms is a policy priority. This study used a pre-post evaluation design to assess the impact of the 20mph speed limit intervention in Edinburgh, Scotland. We showed a reduction in speeds across a range of metrics and variables. These reductions are of a magnitude that means they are likely to have public health relevance especially since the observed reduction in traffic speed was accompanied by reductions in road traffic collisions and casualties. Future research is required to understand mechanisms and inform more effective implementation, in addition to assessment of health economic value.