Understanding Society User Support

Margherita,

Thank you for your question. Unfortunately, this isn't an option. The results will be wrong if our weights applied from different waves in the described way. This is because each set of weights represents a population, but taking different values from different waves and putting them together looses this representation.

If you are concerned about numbers you could create a tailored weight for your analysis. Our online course describes it (unfortunately the link seems to be broken today): https://www.understandingsociety.ac.uk/help/online-training/creating-tailored-weights .

Hope this helps,
Olena

Thank you very much, Olena, for your help, I understand the point.

If I wanted to use Understanding Society weights, is it correct to use the longitudinal weight from the last wave (i_indinus_lw or, if I also use variables from the self-completion questionnaire, i_indscus_lw) even if my variables of interest are only present in the even waves?
In both cases, I find significantly fewer observations for males than for females; I wonder what the reason might be.

Thanks for your availability.

Margherita,

Thank you for your question. Yes, you should use the longitudinal weight from the last wave in your analysis even if you don't use all waves.

There are a few subgroups that tend to have higher nonresponse and attrition in all surveys, including UKHLS, males being one of such groups. Weights correct for this nonresponse, so you should always use them.

Hope this helps,
Olena