Difference-in-differences — setup and assumption.

hard

Answer

$Compare change in outcome for treated group vs change for control group before and after intervention.$
$(Y_{\mathrm{treated}}, \mathrm{post}\; - \;Y_{\mathrm{treated}}, \mathrm{pre})\; - \;(Y_{\mathrm{control}}, \mathrm{post}\; - \;Y_{\mathrm{control}}, \mathrm{pre})$
$Runs as OLS with unit + time fixed effects and an interaction Treated \times Post.$
$Key assumption: parallel trends — without treatment, both groups would have evolved similarly.$
$Verify with pre-trend tests, event studies, robustness checks.$
$Foundational in policy analysis and observational A/B.$

Check yourself — multiple choice

Random
$(\mathrm{post}\; - \;\mathrm{pre})\mathrm{treated}\; - \;(\mathrm{post}\; - \;\mathrm{pre})\mathrm{control}$ via OLS with FE + Treated×Post interaction; assumes parallel trends — verify with pre-trends / event studies
Same as ANOVA
Not real

DID: FE + Treated×Post; assumes parallel pre-trends; verify with event study.

#causal-inference#quasi-experimental

215 interview questions in this topic.