I am attempting to match two datasets, one of which is about 70 000 observations and the other maybe twice that. The "0% 20% 40%" etc goes by fast and tha match finished, but then STATA is running "Computing results, Percent completed ... (search space saved by index so far)" for hours without end. Is it taking so long because of the large data set, or is something wrong? I've tried running it twice, but it always gets stuck for hours.