Project

General

Profile

Actions

Support #440

closed

Longitudinal Regression Analysis Weights

Added by Esther Afolalu almost 9 years ago. Updated almost 9 years ago.

Status:
Closed
Priority:
Urgent
Category:
Weights
Start date:
11/01/2015
% Done:

100%


Description

Hello. I am working on the understanding society database looking specifically at the self-completion questionnaire data for the sleep and health questions. I am carrying out a longitudinal regression analysis to explore the association between change in individual sleep status on the health outcomes from wave 1 – wave 4 controlling for a number of other variables. I just wanted to double-check which longitudinal weight I should apply to the regression analysis – I am thinking ‘d_indscus_lw’? And for descriptive statistics to describe the initial sample at wave one, would I just use the ‘a_indscus_xw’ weighting?

Also, if I wanted to incorporate nurse assessment CRP biomarker data at Wave 2 as a mediator or examine the association from Wave 1 sleep status to Wave 2 biomarker status, which weighting would I apply in this case 'b_indnsus_lw'? And lastly, is there a weighting that’s applicable perhaps to look at the association from Wave 2 biomarker status to Wave 4 sleep?

Thank you,
Esther.

Actions #1

Updated by Olena Kaminska almost 9 years ago

Here are the answers to your questions in the order asked. Yes, d_indscus_lw is correct, and a_indscus_xw is correct as well for the analysis you describe.

We do not have the weight for combining biomarker data from wave 2 and self-completion questionnaire, but b_indnsus_lw is a good suboptimal weight. This weight takes into account all nonresponse stages except for nonresponse to self-completion questionnaire conditional on response to full questionnaire.

Yes, there is a weight for longitudinal analysis of full questionnaire data with combined biomarker data from wave 2 and wave 3 in each mainstage wave. It is called 'd_indnsus_lw' and you will find it on d_indresp.dta file released with the mainstage w4 release. There are two points you need to keep in mind here. First, the same as above - the nonresponse to self-completion conditional on full questionnaire response is not taken into account, but this is a good suboptimal weight. And second, the weight is created for the combined w2 and w3 nurse data - so you need to keep in mind that some respondents were asked nurse questions at different time points.

Hope this helps,
Olena

Actions #2

Updated by Esther Afolalu almost 9 years ago

That's great thank you!

Actions #3

Updated by Redmine Admin almost 9 years ago

  • Status changed from New to Closed
  • % Done changed from 0 to 100
Actions #4

Updated by Gundi Knies almost 9 years ago

  • Target version set to X M
Actions

Also available in: Atom PDF