This is interested in surival time to an event and deals with time series data inherently, including the use of lagging indicators in some cases. Many of the independent variables can change with time.
Discussions I have seen do not address concerns with autocorrelated data or bias tied to lagging predictors discussed in the time series literature. For instance test of autocorrelation common in time series are not raised [or have not in the literature I have seen anyhow}.
Are these not issues, not concerns, with Cox regression? I know the approach uses partial likelihood, perhaps this elminates the issues of autocorrelation and lagged variables.
Discussions I have seen do not address concerns with autocorrelated data or bias tied to lagging predictors discussed in the time series literature. For instance test of autocorrelation common in time series are not raised [or have not in the literature I have seen anyhow}.
Are these not issues, not concerns, with Cox regression? I know the approach uses partial likelihood, perhaps this elminates the issues of autocorrelation and lagged variables.
If a hazard ratio interval contains 0 it means you can not be sure that a variable influenced the time to event right? I ask because SAS apparently does not generate test of statistical signficance for simple effects when interaction occurs, but does generate say the 95 CI for those effects.