Understanding Society User Support

Sue,

Thank you for your question. Do you mean you want to study the group who has not moved their house in the last 12 years (for example)? If so, this is a substantive group within a population and is well represented with the existing weights (same as any other subgroup of the population).

Hope this helps,
Olena

Hi Olena,

Well sub-population 1) is the residents who have not moved at all.

However, is it possible to also include subset 2) residents/respondents who have moved up to the point they moved e.g. those respondents who were in from wave 1, but moved house in to 2007, using the same longitudinal weights at wave k? (i.e. the ones who will have right-censored data because they moved location before 2020/21).

For this sub-population who moved, I will only be including their data up to the point of moving, so are their weights at wave k still appropriate?

Thanks.

Sue E.

Sue,

Yes, such analysis with a longitudinal weight from wave k will be fine. Having said that some models that allow right censoring (e.g. survival analysis), also correct for attrition within the model. In such case you could use wave 1 weight relying on the model for attrition correction.

Best wishes,
Olena