8. Why did they adjust for calendar year at entry, i.e. the year at which subjects became 65 years old?
Calendar year may be a predictor of risk of dying at any given age, because death rates tend to decline over time. We do not know whether it is associated with age at retirement, but we do know that it makes it plausible that the assumption that risk of death is unrelated to when the subject entered the study is violated. Adjusting for calendar year should make the data fit the assumptions of Cox regression better.
We cannot say what the effects would be, because we do not know whether age at retirement was related to calendar year, i.e. whether the rate of early retirement had changed over the period of the study.
Back to question.
Back to Biostatistics in Research Practice index.
This page maintained by Martin Bland.
Last updated: 15 February, 2007.