Topic: Time-Varying Treatments and Confounder Feedback

Direct And Total Effects In A Two-Period Linear Model

Cumulative Exposure And Treatment Timing In Regression

Current-Treatment Regression Versus Treatment-History Regression

Deriving Omitted-Confounder Bias In A Later Treatment Model

Confounding By Indication Across Repeated Treatment Decisions

Common Mistake: Reading Conditional Coefficients As Marginal Effects

Common Mistake: Treating A Time-Varying Confounder As Baseline

Coding Current, Lagged, And Historical Treatment

Common Mistake: Adjusting For Every Measured Covariate

A Counterexample To Sequential Covariate Adjustment