03-10-2017 01:18 PM
I work in the medical field and I’m looking into using survival analysis calculate time to utilization of medical services, that is, once we have a member enrolled in our medical insurance product, how long does it take until this member sees a doctor for the first time. One detail about this is that these members can join the insurance at any time in the year.
I've never done this before, so I’m not sure which approach to use, I’m thinking about two, and would love your assistance on how to proceed (and if there is a better approach than these two, I’d love to hear it).
Have a fixed block of time, for example, look at member patters in the year 2015 (January through December), and follow members during this window
Have the same time window of full year 2015 to start observing when members enroll, and then follow these members for 1 year based on their enrollment date. So if a member joined in 01/05/2015 the window to follow this member would go until 01/05/2016. If another member joined in 08/20/2015 then follow him until 08/20/2016, and so on, so that each time frame for a member is 1 year. Those enrolled after end of 2015 would not be included in the study.
What’s the best approach to do this? Are any of these approached appropriate at all? Is one better than the other or does it matter? And which of the survival analysis procedures would be the most appropriate to use for this case? Would it be PHREG? Also consider that I’d like to use covariates such as age, race, marital status and the like.
Your help would be greatly appreciated. Please let me know what you think.
Thank you very much!