I have a large dataset with info on mutual funds (20,761 rows) and wish to run a regression on a sub-sample of it. In the screenshot below, in column P, I have input an "IF" function which displays a "1" when the fund in question is a Large Growth fund - I have 8 other columns with different fund types, each with their own "IF" function to display a "1" when the fund is that specific type. These 1's are used in my regression as dummy variables.
My question is, how do I run a regression on the rows that display a "1" for Large Growth funds, excluding the rows that contain a "0"? I have tried filtering the data and then running the regression - however my input range is still the whole dataset rather than just the data that is visible after filtering. The large growth funds are not close to each other (e.g. one could be in row 21, one could be in row 450, one in row 1211, etc) so I cannot go through the whole data manually to click on each row for the input range.
Is there a way I can run a regression using only the filtered results?
Screen Shot 2018-02-16 at 23.19.05.png
Bookmarks