Standardization and control for confounding in observational studies: a historical perspective

DOI10.1214/13-STS453zbMATH Open1331.62287arXiv1503.02853MaRDI QIDQ252802FDOQ252802

David Clayton, Niels Keiding

Publication date: 4 March 2016

Published in: Statistical Science (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1503.02853

zbMATH Keywords

marginal structural modelcausalitylog-linear modelepidemiologyodds ratio\(2\times2\times K\) tabledecomposition of ratesexpected number of deathsG. U. YuleH. WestergaardNational Halothane Studyrate ratiotransportability

Mathematics Subject Classification ID

Contingency tables (62H17) History of mathematics in the 20th century (01A60) History of statistics (62-03)

Cites Work

• The prognostic analogue of the propensity score
• Population Marginal Means in the Linear Model: An Alternative to Least Squares Means
• Title not available (Why is that?)
• Statistical models based on counting processes
• Title not available (Why is that?)
• The central role of the propensity score in observational studies for causal effects
• Title not available (Why is that?)
• A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect
• Title not available (Why is that?)
• Joint modelling of longitudinal measurements and event time data
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Nonparametric inference for a family of counting processes
• Title not available (Why is that?)
• The Analysis of Rates and of Survivorship Using Log-Linear Models
• Some Methods for Strengthening the Common χ 2 Tests
• Age-period-cohort analysis in the 1870s: Diagrams, stereograms, and the basic differential equation
• Components of a Difference Between Two Rates
• Title not available (Why is that?)
• Title not available (Why is that?)
• Use of Many Covariates in Clinical Trials
• Statistical Analysis of a Multiplicative Model and Its Application to the Standardization of Vital Rates: A Review
• Summary Rates
• Multiplicative Models and Cohort Analysis
• The Design and Analysis of the Observational Study--A Review
• The Method of Expected Number of Deaths, 1786-1886-1986, Correspondent Paper
• Title not available (Why is that?)
• Title not available (Why is that?)
• Estimation of the probability of an event as a function of several independent variables
• Title not available (Why is that?)

Cited In (5)

• Doubly robust estimator for indirectly standardized mortality ratios
• A general formulation for standardization of rates as a method to control confounding by measured and unmeasured disease risk factors
• The role of exchangeability in causal inference
• Identification and Efficiency Bounds for the Average Match Function Under Conditionally Exogenous Matching
• Confounding in Epidemiologic Studies: The Adequacy of the Control Group as a Measure of Confounding

   Recommendations

• The use of historical controls in estimating simultaneous confidence intervals for comparisons against a concurrent control 👍 👎
• A two-stage strategy to accommodate general patterns of confounding in the design of observational studies 👍 👎
• Confounding in Epidemiologic Studies: The Adequacy of the Control Group as a Measure of Confounding 👍 👎
• A general formulation for standardization of rates as a method to control confounding by measured and unmeasured disease risk factors 👍 👎
• The foundations of confounding in epidemiology 👍 👎
• Title not available (Why is that?) 👍 👎
• Control for confounding in the presence of measurement error in hierarchical models 👍 👎
• Control-variate methods for comparison with a standard 👍 👎

This page was built for publication: Standardization and control for confounding in observational studies: a historical perspective

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q252802)