Weighting factors for cross-sectional analysis - 2022

Hi,

Our purpose is to analyze the access and expenditure of essential energy services in German households during 2022. For that reason, I have taken the bases that are inside the “Raw Data” file and with initials bm (correspond to 2022).
I have identified the variables I need in „bmh“ and „bmp“ file, but I cannot find the weighting factors to work the basis only in that year.
There are examples in the web page where they indicate to look for the database “phrf” and “hhrf”, but in the raw data I do not find them.
In the file where the data panel is, I found some bases called “hpathl” and “hhpathl” and there are the weighting factors from 1984 to 2022. My question is if I can take the weights from those “hpathl” and “hhpathl” databases only for 2022 and put them together with the 2022 household and person databases to do the respective analysis.

Based on an example from the following web page:
https://companion.soep.de/Working%20with%20SOEP%20Data/Generating%20a%20Cross-Sectional%20Dataset.html
I was wondering if for the year 2022 I should have a variable called “bmhhrf” to give the weights for that year? I did not find this variable in my bases “bmh” or “bmp”.

I thank you for your attention and any answer or document that can guide me because I have already read the web page and it is not clear to me the use of these weighting factors.

We recommend every user to start with the hpathl and ppathl data sets. You are doing cross-sectional analysis of 2022 so you would filter the data set to be only 2022. The weights we provide are cross-sectional weights for that respective year. (They are equivalent to what you are looking for in bmphrf.)

You can then merge the bmh or bmp data sets to the path data with the weights. It would be equivalent to merge the hl or pl data.

1 Like