On Thu, 17 Aug 2000, Chris Chiu wrote:
> Does anyone happen to know of a way to generate integers that have a
> normal distribution or a distribution close to a normal distribution?
Well, integers cannot have a _normal_ distribution, they can only have a
distribution that is more or less well approximated by a normal
distribution. (One might be curious as to your reasons and intent.)
> I am trying to generate some whole-numbers with a given range, mean,
> and standard deviation. For example, I was wondering if one could
> simulate, say, 1000 random numbers with a mean 3.5, standard deviation
> 1, and a range going from 1 to 6?
Then the frequencies you want are, approximately,
23, 136, 341, 341, 136, 23. Generate the corresponding numbers of 1s,
2s, ..., 6s in a vector (a column in Minitab's worksheet, say), and
invoke the standard uniform random number generator to put them in a
random order. (If your purpose requires summary statistics only, you
can skip the random ordering part.) If so close and constant an
approximation to normality is not to your liking, apply some random
jitter to those frequencies before producing the numbers of integers
(and if you find the frequencies do not sum to exactly 1000, you have
to decide whether having exactly 1000 is necessary, important, or
desirable enough to figure out a way of fudging them so that they do
produce exactly 1000).
Other contributors may have other suggestions...
-- DFB.
------------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED]
MSC #29, Plymouth, NH 03264 603-535-2597
184 Nashua Road, Bedford, NH 03110 603-471-7128
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
