Hello! I am trying to do a diff in diff with fixed effects on unbalanced panel data. My dependent variable is individual contributions to state-level campaigns w my time fixed effect being whether or not the year is during a resource boom and entity fixed effect equaling state. Attached is the tabulation of year/election with election=1 and special election=2. A handful of states have off-year elections and it seems to be affecting my data. For the regression attached I used reg contr_rate top10 i.year if(elect==1), r
Am I approaching this correctly? What is the best way to deal with the off-year election? Thank you