Hi,
I am estimating the effect of what Airbnb has on apartment prices. I have calculated the amount of Airbnb listings per every postal code area for years 2015 to 2022. Additionally I have all the city's apartment transactions for these years on all postal code areas.
I have also downloaded a set of control variables such as unemployment rate for every postal code area and median income for every postal code area for every year.
I know that I have to form a panel dataset from where I can do the regression, but I don't understand how I do it as I have list of 100 000 apartment transactions, but then e.g. Airbnb listing are now calculated into matrix, where there is years on row 1 and postal codes in column 1.
If I want to add apartment characteristics in control variables (I don't know if that's necessary), how should it be done.
I want to do somewhat similar regression as in the following paper:
