Standardization and Control for Confounding in Observational Studies: A Historical Perspective

TL;DR

This paper reviews the historical evolution of methods for controlling confounders in observational studies, highlighting the shift from stratification and standardization to regression and weighting techniques over time.

Contribution

It provides a comprehensive historical perspective on the development and refinement of confounder control methods in observational research.

Findings

Regression models became the preferred method for confounder control with the advent of computers.

Weighting methods have regained importance since the mid 1990s.

Standardization and stratification were primary before the rise of regression techniques.

Abstract

Control for confounders in observational studies was generally handled through stratification and standardization until the 1960s. Standardization typically reweights the stratum-specific rates so that exposure categories become comparable. With the development first of loglinear models, soon also of nonlinear regression techniques (logistic regression, failure time regression) that the emerging computers could handle, regression modelling became the preferred approach, just as was already the case with multiple regression analysis for continuous outcomes. Since the mid 1990s it has become increasingly obvious that weighting methods are still often useful, sometimes even necessary. On this background we aim at describing the emergence of the modelling approach and the refinement of the weighting approach for confounder control.