I am using data from different waves to see how job status changes over time (will be mostly working with variable jbstat) in different areas, mostly trying to compare cities with the rest of the country (we got access to place information through the special license).
It's just going to be a very simple model, in which it's very likely we will drop Northern Ireland. I assumed the only weight we would be interested in is something related about the assumption that people living in cities are the same of those who don't, but not sure how to do that.
Do I need to do any weighting? And if so, which one do I need to use?
#2 Updated by Olena Kaminska over 2 years ago
Thank you for your question. Sample design of UKHLS is not simple random sample, and nonresponse at wave 1 and subsequent attrition causes further distortion in sample representation - so unweighted analysis (or analysis without an appropriate account for sample and nonresponse) will not represent population. For further information please read our User Guide.
If you are using long format of dataset you will need to use the longitudinal weight from the last wave of your analysis.
Hope this helps,
#5 Updated by Elena Cora Magrini over 2 years ago
Again, thanks for your help. One last clarification.
I am using longitudinal data from wave a to f. The variable I am interested in is the jbstat one, which is part of the adult interview. Am i correct in using the f_indinus_lw weight? And this weight is good to analysis data for all previous waves, right? (I mean, in the context of comparing results from one wave to another).
Just trying to get things right from the beginning so that I don't have to go back and start from scratch again.