forvalues i = 1/139 {

reg fawtd fdistockgdp if seqnum != `i', robust

outreg2 using table, append excel
}

I'm running the above loop (to create a jackknife test) on 139 observations. I'm doing this because I have a list of 139 countries and want to know how my regression coefficient changes when each country is dropped individually.
There is data for all observations, no data is missing. I used seqnum to generate a numbered list of countries. I'm also using outreg2 to export the data.

My problem is that the results I get list 138 observations for some observations and 139 observations for others (seemingly randomly). It seems to me that it should be 138 for all, since I'm dropping one country each time. I've attached a screenshot that shows the first 22 results below. You can see how the number of observations varies.Array


I would really appreciate it if anyone has thoughts on what the problem might be. Thank you!