Premium
Analysis of continuous covariables in epidemiological studies: Dose‐response modelling and confounder adjustment
Author(s) -
Becher Heiko
Publication year - 2002
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/1521-4036(200209)44:6<683::aid-bimj683>3.0.co;2-2
Subject(s) - confounding , epidemiology , computer science , econometrics , medicine , regression analysis , epidemiological method , statistics , mathematics
The analysis of continuous covariables with regression models commonly used in epidemiology are reviewed and compared. While some methods have been in use for decades, other more recent methods are not yet common or have not yet been formally described. It is shown that recently developed methods such as fractional polynomials and others are very useful to obtain dose‐response curves or for confounder adjustment. Different methods have their specific merits making it difficult to give general recommendations. The application of some of the methods is demonstrated with real data examples from epidemiological studies. Some suggestions for practical strategies in analysing continuous covariables are given.