Difficulties with Regression Analysis of Age-Adjusted Rates.
Abstract
A common type of observational study compares population rates in several regions having differing policies in an effort to assess the effects of those policies. In many studies, particularly in public health and epidemiology, age-adjusted rates are regressed on predictor variables to obtain a covariance adjusted estimate of effect; we show that this estimate is generally biased for the appropriate regression coefficient. The analysis of crude rates with age as a covariate can, under familiar models, leads to unbiased estimates, and therefore can be preferrable. Several other regression methods are also considered. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1982
- Accession Number
- ADA124381
Entities
People
- Donald B. Rubin
- Paul R. Rosenbaum
Organizations
- University of Wisconsin–Madison