are we going to learn about time-varying covariates?
they reference them in the article for this week and I don't have a conceptual framework to think about them
thank you
You won’t be learning about time-varying covariates in this class, but you will in Epi 3 and biostat 5. It will be a lot easier to think about them after the upcoming DAG session.Intuitively, you need to take time into account: a time-varying covariates is simply a variable (like age, blood pressure, etc…) that can vary over time. It could be important if they vary significantly over your study period and affect the likelihood of your outcome and/or your exposure.A time varying covariate could be a potential confounding factor that you wish to adjust for. If you are doing a survival analysis which allows updating of exposure, you can also try to include data on updated confounding factors, if such data are available. Such confounding factors would be an example of a time-varying covariates.
Just to add further clarification in case it helps - in last week's paper on aspirin and prostate cancer death - in the Cox proportional hazard model, I think they treated aspirin as a time-varying exposure, with simple updating (until the last cycle, when it was lagged). this means if they say they are not using at baseline, then for the next follow-up cycle they are a "non-user"; then at the next survey, they say they started aspirin, so their exposure for the next follow-up cycle is updated to "user".
All those person-time diagrams we were putting on the board last week were examples of time varying exposure.
A time-varying covariate is applying these sample principles to update information about other variables in the model that could change over time. For example, maybe BMI or age could be updated, if one was very concerned about adjusting for confounding by those factors.
best,
JMC