Difference between revisions of "Quasi-Experimental Methods"

Jump to: navigation, search
(Created page with "== Introduction == Like Experimental Methods, quasi-experimental research methods are intended to satisfy the conditions where a researcher can construct a model where ex...")
 
(23 intermediate revisions by 5 users not shown)
Line 1: Line 1:
== Introduction ==
Quasi-experimental methods are research designs that that aim to identify the impact of a particular intervention, program or event (a "treatment") by comparing treated units (households, groups, villages, schools, firms, etc.) to control units. While quasi-experimental methods use a control group, they differ from [[Experimental Methods | experimental methods]] in that they do not use [[Randomization in Stata | randomization]] to select the control group. Quasi-experimental methods are useful for estimating the impact of a program or event for which it is not [[Research Ethics | ethically]] or logistically feasible to randomize. This page outlines common types of quasi-experimental methods.


Like [[Experimental Methods]], quasi-experimental research methods are intended to satisfy the conditions where a researcher can construct a model where exposure to a treatment effect is uncorrelated with other characteristics. Unlike in experimental research methods, the investigator does not have direct control over the exposure, and instead uses "natural experiments" such as [[Regression Discontinuity]] designs to identify existing circumstances where random assignment of some treatment took place.
==Read First==
*Common examples of quasi-experimental methods include [[Difference-in-Differences | difference-in-differences]], [[Regression Discontinuity | regression discontinuity design]], [[Instrumental Variables | instrumental variables]] and [[Matching | matching]]. For more details on each type, please visit their respective pages.
*In general, quasi-experimental methods require larger sample sizes and more assumptions than experimental methods in order to provide valid and unbiased estimates of program impacts.
 
== Overview ==
Like experimental methods, quasi-experimental methods aim to estimate program effects free of confoundedness, reverse causality or simultaneous causality. While quasi-experimental methods use a counterfactual, they differ from [[Experimental Methods | experimental methods]] in that they do not [[Randomization in Stata | randomize]] treatment assignment. Instead, quasi-experimental methods exploit existing circumstances in which treatment assignment has a sufficient element of randomness, as in [[Regression Discontinuity | regression discontinuity design]] or event studies; or simulate an experimental counterfactual by constructing a control group as similar as possible to the treatment group, as in [[Propensity Score Matching|propensity score matching]]. Other examples of quasi-experimental methods include [[Instrumental Variables | instrumental variables]] and [[Difference-in-Differences | difference-in-differences]].
 
==Assumptions and Limitations==
In general, quasi-experimental methods require larger samples than experimental methods. Further, for quasi-experimental methods to provide valid and unbiased estimates of program impacts, researchers must make more assumptions about the control group than in experimental methods. For example, difference-in-differences relies on the equal trends assumption (see [[Difference-in-Differences]] for more details), while matching assumes identical unobserved characteristics between the treatment and control groups.
 
== Additional Resources ==
* Robert Michael's slides on [http://www.indiana.edu/~educy520/sec6342/week_05/quasi_designs_2up.pdf Quasi-Experimental Designs]
*Gertler et al.’s [https://siteresources.worldbank.org/EXTHDOFFICE/Resources/5485726-1295455628620/Impact_Evaluation_in_Practice.pdf Impact Evaluation in Practice]
 
[[Category: Quasi-Experimental Methods ]]

Revision as of 07:03, 12 February 2020

Quasi-experimental methods are research designs that that aim to identify the impact of a particular intervention, program or event (a "treatment") by comparing treated units (households, groups, villages, schools, firms, etc.) to control units. While quasi-experimental methods use a control group, they differ from experimental methods in that they do not use randomization to select the control group. Quasi-experimental methods are useful for estimating the impact of a program or event for which it is not ethically or logistically feasible to randomize. This page outlines common types of quasi-experimental methods.

Read First

Overview

Like experimental methods, quasi-experimental methods aim to estimate program effects free of confoundedness, reverse causality or simultaneous causality. While quasi-experimental methods use a counterfactual, they differ from experimental methods in that they do not randomize treatment assignment. Instead, quasi-experimental methods exploit existing circumstances in which treatment assignment has a sufficient element of randomness, as in regression discontinuity design or event studies; or simulate an experimental counterfactual by constructing a control group as similar as possible to the treatment group, as in propensity score matching. Other examples of quasi-experimental methods include instrumental variables and difference-in-differences.

Assumptions and Limitations

In general, quasi-experimental methods require larger samples than experimental methods. Further, for quasi-experimental methods to provide valid and unbiased estimates of program impacts, researchers must make more assumptions about the control group than in experimental methods. For example, difference-in-differences relies on the equal trends assumption (see Difference-in-Differences for more details), while matching assumes identical unobserved characteristics between the treatment and control groups.

Additional Resources