Difference-in-Difference in the Time of Cholera: a Gentle Introduction for Epidemiologists
- PDF / 516,899 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 96 Downloads / 229 Views
EPIDEMIOLOGIC METHODS (P HOWARDS, SECTION EDITOR)
Difference-in-Difference in the Time of Cholera: a Gentle Introduction for Epidemiologists Ellen C. Caniglia 1 & Eleanor J. Murray 2 Accepted: 11 September 2020 # Springer Nature Switzerland AG 2020
Abstract Purpose of Review The goal of this article is to provide an introduction to the intuition behind the difference-in-difference method for epidemiologists. We focus on the theoretical aspects of this tool, including the types of questions for which difference-indifference is appropriate, and what assumptions must hold for the results to be causally interpretable. Recent Findings While currently under-utilized in epidemiologic research, the difference-in-difference method is a useful tool to examine effects of population level exposures, but relies on strong assumptions. Summary We use the famous example of John Snow’s investigation of the cause of cholera mortality in London to illustrate the difference-in-difference approach and corresponding assumptions. We conclude by arguing that this method deserves a second look from epidemiologists interested in asking causal questions about the impact of a population level exposure change on a population level outcome for the group that experienced the change. Keywords Difference in difference . Change scores . Causal inference . John Snow
Introduction The difference-in-difference method is one of the oldest tools in the epidemiology toolkit, first used in 1855 by John Snow in his analysis of the cause of cholera [1•, 2•, 3•]. Despite this, difference-in-difference is used relatively infrequently by epidemiologists today. In this review, we describe what the difference-in-difference method is, how and why the estimation procedure works for estimating causal effects, and what types of causal questions it is appropriate for. We propose a causal diagram (DAG) for difference-in-difference analyses and use Snow’s investigation of London’s cholera outbreak as a motivating example to outline the method.
This article is part of the Topical Collection on Epidemiologic Methods * Eleanor J. Murray [email protected] 1
Department of Population Health, New York University Langone Medical Center, New York City, NY, USA
2
Department of Epidemiology, Boston University School of Public Health, Boston, MA, USA
What Is the Difference-in-Difference Method and How Does It Work? In its simplest form, the difference-in-difference method is a comparison of the change over time in a continuous outcome variable (such as the probability or rate of an outcome) in an exposed group versus the change over time in an unexposed or control group [3•, 4•]. This approach was pioneered by John Snow in 1855 to understand the causes of cholera mortality. Table 1 reproduces his data on cholera mortality rates by household water source. In 1855 London, cholera was a common occurrence, but the cause of cholera was unknown. John Snow suspected that the infection was waterborne and designed a difference-indifference study to test his hypothesis. In his investig
Data Loading...
