Understanding Society User Support

Hi there,

I just had a quick question regarding the new UKHLS calendar year datasets that are available. In the user guides to the data, it states that: "These calendar year datasets should be used for cross-sectional analysis only. For those interested in
longitudinal analyses using Understanding Society please access the main survey datasets from the
UKDS: End User Licence version or Special Licence version." I was just wondering if you could shed some light on to why this is the case?

I also had two quick follow-ups related to this. Firstly, my understanding is that these datasets are based on actual calendar years. However, in a previous query, it was suggested I could calculate 'sample year' datasets, using the 'sample month' (w_month) variable (please see here: https://iserredex.essex.ac.uk/support/issues/2075#change-8640). These are closely related to actual calendar years, but there is also a small amount of spill over between years as well, if I understand things correctly. However, I just wanted to check if it was still possible to do longitudinal analysis using the data as 'survey' years. The fact it's not possible with the calendar year datasets has just got me concerned.

Secondly, I was also hoping to confirm whether (a) the new calendar year datasets, and (b) any 'sample year' datasets I create, can be used to analyse the child samples? I understand they provide representative samples of the adult population, but is there anything I need to be aware of if I use these datasets to look at the child data?

Thanks so much in advance for your help,

James