Hi Lars,
You can easily generate random draws from a variety of distributions using STATA's built in commands. For example, to generate 100 obs from the standard normal (mean 0 variance 1) you would type
1.clear
2.set obs 100
3.gen x=rnormal(0,1)
The following is from the STATA help
runiform(r, c) returns an r x c real matrix containing uniformly
distributed random variates on [0,1). runiform() is the same function
as Stata's runiform() function.
rbeta(r, c, a, b) returns an ir x jc real matrix containing beta random
variates. The real-valued matrices a and b contain the beta shape
parameters. The matrices a and b must be r-conformable, where i =
max(rows(a),rows(b)) and j = max(cols(a),cols(b)).
rbinomial(r, c, n, p) returns an ir x jc real matrix containing binomial
random variates. The real-valued matrices n and p contain the number of
trials and the probability parameters. The matrices n and p must be
r-conformable, where i = max(rows(n),rows(p)) and j =
max(cols(n),cols(p)).
rchi2(r, c, df) returns an ir x jc real matrix containing chi-squared
rnormal(r, c, m, s) returns an ir x jc real matrix containing normal
(Gaussian) random variates. The real-valued matrices m and s contain
the mean and standard deviation parameters, respectively. The matrices
m and s must be r-conformable, where i = max(rows(m),rows(s)) and j =
max(cols(m),cols(s)).
rpoisson(r, c, m) returns an ri x ci real matrix containing Poisson
random variates. The real-valued matrix m contains the Poisson mean
parameters, where i = rows(m) and j = cols(m).
I hope this helps.
Best,
David Vincent
Econometrician
Advanced Analytics Practice
Hewlett-Packard Limited
Mobile: +44 (0)7939 200 747
Internet: mailto:[email protected]
Hewlett-Packard Limited Registered Office: Cain Road, Bracknell, Berks RG12 1HN
Registered No: 690597 England
The contents of this message and any attachments to it are confidential and may be legally privileged. If you have received this message in error, you should delete it from your system immediately and advise the sender.
To any recipient of this message within HP, unless otherwise stated you should consider this message and attachments as "HP CONFIDENTIAL".
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Lars Holstenkamp
Sent: 05 June 2009 14:02
To: [email protected]
Subject: st: Random number generation
Dear all,
is there somewhere a list of how to generate random numbers with various
distributions (esp. triangular, beta, pert; for use in Monte Carlo
simulations)?
Regards,
Lars
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
