Pooling data for analysis by calendar year
I am trying to get to the mean of certain variables for each calendar year and I am uncertain about rescaling weights. I have read the note on this (https://iserswww.essex.ac.uk/support/attachments/download/3/Pooling%20data%20from%20different%20waves.pdf). In the note, the example code is for a year where only two waves are contributing data, with the weights for data in the second wave being multiplied by (sum of w1 weights/sum of w2 weights).
For years 2013-2016, data from three waves are available. Would the appropriate modification to the weights then be:
w1 weight= w1 weight *(sum of w2 & w3 weights/sum of w1 weights)
w2 weight= w2 weight *(sum of w1 & w3 weights/sum of w2 weights)
w3 weight= w3 weight
Thanks for any guidance!
Updated by Alita Nandi over 4 years ago
- Status changed from New to In Progress
- Assignee set 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.
Understanding Society User Support Team
Updated by Olena Kaminska over 4 years ago
Thank you for your question. No, your suggestion will not work. You should base your calendar year on the month of issue, rather than a month of interview. What happens is that December month of issue has mostly response in December, but some people are followed for some time and respond later (up until March or April the following year). These numbers are small, but these people are important to keep with the previous year.
Hope this helps,