Understanding Society User Support

Hi Alita,

I'm running Nested OLS regressions to examine the social class pay gap for each wave of data (I am using waves 1-9). Firstly, I proxy for respondents' social class, then control for their demographics, education, labour market features etc. in subsequent models. I am conditioning all models on respondents' being in employment. The sample size decreases each time I add in an additional control. This happens when I am running the models on an unbalanced and a balanced panel. Therefore, my question is why is the sample size not consistent across all models?

Thanks,
Michael