Support #621
closed
Weights - biomarker data
100%
Description
Hi,
I am hoping to use the biomarker data (and associated nurse data) from the GPS and BHPS samples and their longitudinal data from Wave 1 and Wave 2, and Wave 2 and Wave 3, respectively. Could you please clarify which weights to use for this analysis please?
Many thanks,
Claire
Updated by Olena Kaminska over 8 years ago
Hi Claire,
If you are using only nurse information with mainstage (but not information from blood) use indnsub_xw weight from xindresp_ns.dta .
If you are also using information from blood use indbdub_xw from xlabblood_ns.dta.
Best,
Olena
Updated by Claire Niedzwiedz over 8 years ago
Hi Olena,
Thanks for your reply. I will be using the blood data too. Will using the indbdub_xw weight also take into account attrition between the two waves (waves 1 and 2, as well as waves 2 and 3)?
Best wishes,
Claire
Olena Kaminska wrote:
Hi Claire,
If you are using only nurse information with mainstage (but not information from blood) use indnsub_xw weight from xindresp_ns.dta .
If you are also using information from blood use indbdub_xw from xlabblood_ns.dta.Best,
Olena
Updated by Olena Kaminska over 8 years ago
Yes, that's right.
The indbdub_xw weight is designed for the analysis of blood information together with wave 2 and wave 3 mainstage responses. The response of wave 2 is conditional on the response in wave 1 for GPS - so this is also taken into account by design.
This is a unique situation when cross-sectional weight can be used for the analysis you specify. Once you move to future waves (e.g. waves 4 and 5) you will have to use longitudinal weights.
Best,
Olena
Updated by Victoria Nolan over 8 years ago
- Status changed from New to Feedback
- Assignee changed from Olena Kaminska to Claire Niedzwiedz
- % Done changed from 0 to 90
- Private changed from Yes to No
Updated by Claire Niedzwiedz over 8 years ago
Hi Olena,
Many thanks for answering.
Best wishes,
Claire
Updated by Victoria Nolan over 8 years ago
- Status changed from Feedback to Closed
- % Done changed from 90 to 100