Refer to the attached files, and let me know if you have any questions (I was able to run a bootstrap to obtain the # of observations with p<0.05 for the four different scenarios).
Best,
Stephen
Nice job Stephen. Note the distinction between
bootstrap, reps(100) size(500): regress Ysel Xsel
which draws 100 samples of size n=500 from a population (in this case of 50,000) and repeatedly generating new data sets of size n=500. The former case will lead to more similarity between iterations than the latter.
Also, what you did looks terrific but some of this is already packaged in stata and would make your life easier if you need to do it in the future - there is a "simulate" command in stata that is very useful and alternatively you can ask the bootstrap to return any particular parameter from each iteration - ie the p-values.
maria