# Re: st: Drawing multiple samples from a normal distribution

 From Marcello Pagano <[email protected]> To [email protected] Subject Re: st: Drawing multiple samples from a normal distribution Date Tue, 21 Dec 2004 11:18:13 -0500

No. If you check the help file you will find,
seed(#) specifies the initial value of the random-number seed used by the uniform()
function. The default is the current random-number seed. Specifying seed(#) is the
same as typing set seed # before issuing the drawnorm command.

So, it does not need a new seed each time, but if you want the same "random" numbers
generated again, then set the same seed--here, a positive integer.

m.p.

Joseph Cordes wrote:

Actually, because we don't want them to actually know the "true" means and SDs we are going to generate the samples ourselves. Do I understand you correctly to say that each time we make a draw we need to provide a different seed? And if the answer is yes, am I correct in assuming that the seed can be any number chosen?

----- Original Message -----
From: Marcello Pagano <[email protected]>
Date: Tuesday, December 21, 2004 11:07 am
Subject: Re: st: Drawing multiple samples from a normal distribution

If you want to retain the ability to check your students' work, make sure they
tell you the seed they used. To ensure they all use different seeds, you can
Just a thought.

m.p.

Joseph Cordes wrote:

I want to give my class a simple exercise in which each student
is given a different sample that is drawn from the same normal distribution with a known mean and standard deviation, and then is asked to (a) calculate the sample mean, (b) do the standard inferences about the population mean from their estimate, (c) graph the different estimates of the sample mean produced in the class, and (d) reproduce the exercise with increasing sample size to demonstrate the notion of a consistent estimator.

My question is not about (a)-(d), but about how to create the
samples. Am I correct that I could do this by using the following commands?>

Set obs #

drawnorm sample1, mean(M) sds(sd)

and then simply repeating this command substituting sample2,
sample3, etc. in for sample 1 to generate (in my case) 25 different samples?

Thanks.

```*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```