topic Re: Longitudinal weighting in Statistical Procedures

Longitudinal weighting

Miracle — Tue, 23 Sep 2014 05:39:58 GMT

Dear all,

Wish you all well. My apology that this is not SAS-related.

I have to do weighting for an alcohol longitudinal study(2011-2013).

How do I go about getting the final weights?

Some people stopped responding as the survey progressed leaving only the drinkers responded in the end(2013).

Does it sound statistically correct by multiplying the sampling weights by postratification weights(weighted on census by gender, age and ethnicity) then by attrition weights to get the final weights?

Any input will be greatly appreciated

Re: Longitudinal weighting

Ksharp — Tue, 23 Sep 2014 12:04:51 GMT

Survival Analysis ?

K-M estimator ?

Better Post it at SAS Statistical Procedures

Message was edited by: xia keshan

Re: Longitudinal weighting

SteveDenham — Fri, 03 Oct 2014 17:56:20 GMT

What are you trying to estimate here? 's suggestion of some sort of survival analysis may be in order. Look at some of the examples in the PHREG documentation to see if they look like they fit what you want. If so, then sit down with an experienced proportional hazards modeler to work through the assumptions and whether they are met for an analysis.

Steve Denham

Re: Longitudinal weighting

Miracle — Sat, 04 Oct 2014 12:16:08 GMT

Dear Keshan and Steve,

Thanks for your reply.

I wish to analyse only the 2013 data and to create weighting for the 2013 only participants so it will be a nationally representative of the population.

However, I'm not sure how do I go about doing the weighting given that there are only drinkers in the 2013 data.

Thank you.