Re: [R] random number generation

[Pascal A. Niklaus]

You need to know the exact distribution of the random numbers you want 
to generate. For rnorm, in fact, you do not just specify the mean and 
the variance, but implicitely also that the data is normally 
distributed. Likewise, it is not sufficient to give min, max, skewness 
etc, you also need to know the distribution and then maybe you can use 
runif() as base for your code.

Pascal

nmi13 wrote:

Hi every one,

I am trying to generate a normally distributed random variable with the 
following descriptive statistics,

min=1, max=99, variance=125, mean=38.32, 1st quartile=38, median=40, 3rd 
quartile=40, skewness=-0.274.

I know the "rnorm" will allow me to simulate random numbers with mean 38.32 
and Sd=11.18(sqrt(125)). But I need to have the above mentioned descriptive 
statistics for the data that I generate.

I would be thankful to anyone who can help me with this problem.

Regards
Murthy
 

______________________________________________
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help