Natural experiments for the evaluation of place-based public health interventions: a methodology scoping review

Abstract

Introduction: Place-based public health evaluations are increasingly making use of natural experiments. This scoping review aimed to provide an overview of the design and use of natural experiment evaluations (NEEs), and an assessment of the plausibility of the as-if randomization assumption.

Methods: A systematic search of three bibliographic databases (Pubmed, Web of Science and Ovid-Medline) was conducted in January 2020 to capture publications that reported a natural experiment of a place-based public health intervention or outcome. For each, study design elements were extracted. An additional evaluation of as-if randomization was conducted by 12 of this paper's authors who evaluated the same set of 20 randomly selected studies and assessed 'as-if ' randomization for each.

Results: 366 NEE studies of place-based public health interventions were identified. The most commonly used NEE approach was a Difference-in-Differences study design (25%), followed by before-after studies (23%) and regression analysis studies. 42% of NEEs had likely or probable as-if randomization of exposure (the intervention), while for 25% this was implausible. An inter-rater agreement exercise indicated poor reliability of as-if randomization assignment. Only about half of NEEs reported some form of sensitivity or falsification analysis to support inferences.

Conclusion: NEEs are conducted using many different designs and statistical methods and encompass various definitions of a natural experiment, while it is questionable whether all evaluations reported as natural experiments should be considered as such. The likelihood of as-if randomization should be specifically reported, and primary analyses should be supported by sensitivity analyses and/or falsification tests. Transparent reporting of NEE designs and evaluation methods will contribute to the optimum use of place-based NEEs.

Keywords: evaluations; natural experiments; place-based; public health; public health policy; quasi experiments.

Figure 1

PRISMA Flow Diagram. Note that the total number of excluded studies per categories does not equal the total number of those excluded because studies may have been assigned more than one label.

Figure 2

Number of studies identified as “natural experiment evaluations” by their authors up to December 2019 (six studies from early 2020 included in this study, but not shown in this Figure to avoid erroneous inferences on trends). Dottedline indicates publication MRC guidance were published (16).