Ra. Wolfe et Rl. Strawderman, LOGICAL AND STATISTICAL FALLACIES IN THE USE OF COX REGRESSION-MODELS, American journal of kidney diseases, 27(1), 1996, pp. 124-129
Time-dependent covariates are an essential data analysis tool for mode
ling the effect of a study factor whose value changes during follow-up
. However, survival analysis models can yield conclusions that are con
trary to the truth if such time-dependent factors are not defined and
used carefully. We outline some of the biases that can occur when time
-dependent covariates are used improperly in a Cox regression model. F
or example, we discuss why one should almost never use a covariate tha
t has been averaged over a patient's entire follow-up time as a baseli
ne covariate, Instead, the baseline value should be used as a covariat
e, or the cumulative average up to each point in time should be used a
s a time-dependent covariate. We also document why one should use time
-dependent covariates with great caution in analyses when the evaluati
on of a baseline factor is the primary objective. Several simulated ex
amples are given to illustrate the direction and magnitude of the bias
es that can result from not adhering to some basic assumptions that un
derlie all survival analysis methodologies. (C) 1996 by the National K
idney Foundation, Inc.