Greenland, Sander, Daniel, Rhian ORCID: https://orcid.org/0000-0001-5649-9320 and Pearce, Neil 2016. Outcome modelling strategies in epidemiology: traditional methods and basic alternatives. International Journal of Epidemiology 45 (2) , pp. 565-575. 10.1093/ije/dyw040 |
Preview |
PDF
- Published Version
Available under License Creative Commons Attribution. Download (303kB) | Preview |
Abstract
Controlling for too many potential confounders can lead to or aggravate problems of data sparsity or multicollinearity, particularly when the number of covariates is large in relation to the study size. As a result, methods to reduce the number of modelled covariates are often deployed. We review several traditional modelling strategies, including stepwise regression and the ‘change-in-estimate’ (CIE) approach to deciding which potential confounders to include in an outcome-regression model for estimating effects of a targeted exposure. We discuss their shortcomings, and then provide some basic alternatives and refinements that do not require special macros or programming. Throughout, we assume the main goal is to derive the most accurate effect estimates obtainable from the data and commercial software. Allowing that most users must stay within standard software packages, this goal can be roughly approximated using basic methods to assess, and thereby minimize, mean squared error (MSE).
Item Type: | Article |
---|---|
Date Type: | Publication |
Status: | Published |
Schools: | Medicine |
Subjects: | R Medicine > R Medicine (General) |
Publisher: | Oxford University Press |
ISSN: | 0300-5771 |
Date of First Compliant Deposit: | 13 November 2017 |
Date of Acceptance: | 5 February 2016 |
Last Modified: | 02 May 2023 12:13 |
URI: | https://orca.cardiff.ac.uk/id/eprint/106059 |
Citation Data
Cited 151 times in Scopus. View in Scopus. Powered By Scopus® Data
Actions (repository staff only)
Edit Item |