Support #658
closedWeights, BHPS and USoc pooled
100%
Description
Dear Support team,
I have two questions with weights. Our data is based on a sub-population (respondents whose parents had non-missing interview records on their parents, that is, respondents' grandparents), while BHPS and USoc are pooled together. We are using BHPS wave 1-18, USoc wave 1-5. We have read through both BHPS and USoc user guides and weights-related posts on this forum but could not find the best solution.
Our research is on social class and education.
1. Class:
I use non-missing social class variables at the last, or most recent, waves that respondents attended. For example, in the case in which the last wave that a respondent was interviewed was BHPS wave 12, the non-missing social class recode at BHPS wave 12 would be taken as the measure of social class. Say, if the record at BHPS wave 12 is missing but the one at BHPS wave 11 is non-missing, the social class variable at wave 11 would be taken as the measure of social class.
This means that our data is drawn from different waves of BHPS and USoc. Can you please suggest which weights serve the best for our purpose.
2. Education
We use the highest educational qualifications that respondents have ever achieved. Which weights should we use in this case?
We incorporated gender, birth cohort, age, race (a roughly binary white vs non-white variable though), regions and data sources (a binary BHPS vs USoc variable) as the control variables in our analyses. We also take into clustered errors using household ID. We wonder whether it is statistically acceptable if there are no perfect weights used in our analyses.
We highly appreciate your supports.
Best wishes.
Updated by Victoria Nolan over 8 years ago
- Category set to Weights
- Status changed from New to In Progress
- Assignee set to Victoria Nolan
- % Done changed from 0 to 10
- Private changed from Yes to No
Updated by Victoria Nolan over 8 years ago
- Status changed from In Progress to Feedback
- Assignee changed from Victoria Nolan to Min Zhang
- % Done changed from 10 to 80
Updated by Victoria Nolan over 8 years ago
- Status changed from Feedback to Closed
- % Done changed from 80 to 100