Support #689
closed
Weighting on youth self-completion datasets
Added by Jane Lakey almost 8 years ago.
Updated almost 8 years ago.
Description
Hi, we are trying to derive a longitudinal weight for linked youth datasets, following guidance given by Peter Lynn previously. Please could you explain why the youth self-completion weight is 0 for more than 1/5 of the youth s-c respondents at wave 2?
thanks
- Status changed from New to In Progress
- Assignee changed from Olena Kaminska to Jane Lakey
- % Done changed from 0 to 10
- Private changed from Yes to No
Dear Jane - many thanks for your query and for bearing with us over the Christmas holiday period. I have passed on your query to our weighting team.
Best wishes, Victoria.
Jane,
It looks to me that the weight is present for 95% of respondents. Specifically, b_ythscus_xw is missing for only 0.7% of GPS+EMB cases, and b_ythscbh_xw is zero for 18.9% of BHPS cases:
| samp
wght | us bhps | Total
-------------+----------------------+----------
b_ythscus_xw | 3,876 0 | 3,876
| 99.31 0.00 | 77.21
-------------+----------------------+----------
b_ythscbh_xw | 0 906 | 906
| 0.00 81.11 | 18.05
-------------+----------------------+----------
both zero | 27 211 | 238
| 0.69 18.89 | 4.74
-------------+----------------------+----------
Total | 3,903 1,117 | 5,020
| 100.00 100.00 | 100.00
The higher rate of zero weights for the BHPS sample is because the weight relies on having a valid longitudinal weight for at least one adult in the household, and BHPS has had a lot of waves by that point!
Peter
- Status changed from In Progress to Feedback
- % Done changed from 10 to 80
- Status changed from Feedback to Closed
- % Done changed from 80 to 100
Also available in: Atom
PDF
Updated by Victoria Nolan 
Updated by