Any advice on how best to get standard errors for the UNION variable? I know I need to use the EARNWT weight. Given that replication weights are not provided for outgoing rotation group questions (as far as I can tell) is there a way I can calculate my own replication weights to make these calculations? If its helpful I’m working on this in python, but also can work in R.
Thanks so much!
There are not replicate weights for outgoing rotation group data. There is no way to create your own replicate weights as these rely on the full set of design variables that are not included in the public use microdata (these design variables would be the next best option for estimating standard errors as well). However, you may be interested in research (Davern et al. 2006 and 2007) describing how to improve variance estimation using variables available in the public use microdata.