Premium
On case‐crossover methods for environmental time series data
Author(s) -
Whitaker Heather J.,
Hocine Mounia N.,
Farrington C. Paddy
Publication year - 2007
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/env.809
Subject(s) - crossover , series (stratigraphy) , residual , statistics , econometrics , computer science , regression , time series , mathematics , algorithm , artificial intelligence , paleontology , biology
Case‐crossover methods are widely used for analysing data on the association between health events and environmental exposures. In recent years, several approaches to choosing referent periods have been suggested, with much discussion of two types of bias: bias due to temporal trends, and overlap bias. In the present paper, we revisit the case‐crossover method, focusing on its origin in the case‐control paradigm, in order to throw new light on these biases. We emphasise the distinction between methods based on case‐control logic (such as the symmetric bi‐directional (SBI) method), for which overlap bias is a consequence of non‐exchangeability of the exposure series, and methods based on cohort logic (such as the time‐stratified (TS) method), for which overlap bias does not arise. We show by example that the TS method may suffer severe bias from residual seasonality. This method can be extended to control for seasonality. However, time series regression is more flexible than case‐crossover methods for the analysis of data on shared environmental exposures. We conclude that time series regression ought to be adopted as the method of choice in such applications. Copyright © 2006 John Wiley & Sons, Ltd.