Support #2284
open
Chosen longitudinal weight check
10%
Description
Dear Understanding Society User Support Team,
I am using waves 13 and 14 to conduct an analysis at the individual level. My interest is whether food insecurity in wave 13 associates with future changes in mental health. Following the guidance, I have chosen the indinui_lw weight from wave 14. I wished to check that this decision is suitable for the analysis, as it is significantly reducing the sample size. In particular, it is removing ~ 50% of individuals who previously reported food insecurity. While this is okay, I wished to check that I was using the correct weight (and hadn't misread the guidance) before checking additional model diagnostics. I would also be interested if there is any advice for working with these weights given the reduction in cell counts it causes (if the choice is correct).
Any help would be greatly appreciated.
Many thanks,
Dan Pinhay
Updated by Understanding Society User Support Team 2 days ago
- Status changed from New to In Progress
- Assignee changed from Understanding Society User Support Team to Olena Kaminska
- % Done changed from 0 to 10
- Private changed from Yes to No
Many thanks for your enquiry. The Understanding Society team is looking into it and we will get back to you as soon as we can. We aim to respond to simple queries within 48 hours and more complex issues within 7 working days.
Best wishes,
Understanding Society User Support Team
Updated by Olena Kaminska 1 day ago
Daniel,
Yes, the choice of the weight is correct. An alternative would be to create your own tailored weight following our online course: https://www.understandingsociety.ac.uk/help/training/creating-tailored-weights/ . I suggest you watch the first video on the course to decide whether you want to create a tailored weight or whether you want to use the weight that we provide.
Hope this helps,
Olena
Updated by Daniel Pinhay 1 day ago
Hi Olena,
Thank you for your response! I'm now having a look at whether to use a tailored weight or whether to just use the one provided. Could I ask, what factors might contribute to individuals having a weight of 0 when they have fully responded to the individual-level questionnaires (say for both waves I am looking at)?
Apologies for the follow up question, I am just trying to ensure I understand fully before making a weight decision.
Many thanks,
Dan
Updated by Olena Kaminska 1 day ago
Dan,
The weight you are using 'ui' starts at wave 6, and therefore is for an analysis where a response is present in all waves since waves 6, without exception. You don't need all the waves in your analysis, and therefore could create a tailored weight, which would increase the sample size, but is likely not to change the findings as explained in the first video of the course. There is more information on the course and there are also examples that may help you understand the issue better.
Hope this helps,
Olena