set seed problem

[Francisco Carballo]

Hello Statalist,

I recently came up with a replicability problem when using someone else's Do-File.

It seems my Stata is assigning different random numbers after "gen random = runiform()" even when the seed on both computers is the same.

set seed 875511
gen random=runiform()

br if random<0.001

I get only two observations popping up, while my collegue gets 5.

Can anyone give me an explanation for this? I am using Stata 14, while she uses Stata 13.

Thank you in advance

[daniel klein]

From

help whatsnew13to14

15. New random-number generators (RNGs)

Existing function runiform() now uses the 64-bit Mersenne Twister. runiform() produces uniformly
distributed random numbers, and the functions providing random numbers for other distributions use
runiform() in producing their results. Thus, all of Stata's RNGs are now based on the Mersenne Twister,
too. Stata previously used KISS32 and still does under version control.

Best
Daniel

[Francisco Carballo]

Hello Daniel,

Thanks for the information.

Any other way to create random numbers and make it replicable even among different Stata versions? This is for future purposes.
As for the present problem, any way to set my Stata 14 to use Stata 13 RGNs? So I can get same numbers from a runiform() function as my collegue?

Thanks in advance
Best regards.

[Clyde Schechter]

Daniel has already shown you the answer to that. Pay attention to:

Stata previously used KISS32 and still does under version control.

See -help version-.

[Francisco Carballo]

Thank you both for your comments.

version 13

at the beginning of the code should work.

Best regards.