Re: generating correlated random variables


oercim wrote:
I want to generate random variables such as

y(it)= n(i)+ e(it),
where i denotes the cross section unit and t denotes the time. Here
n(i) is independently distributed with the identical distribution over
cross section units. And
e(it) is independently distributed with the identical distribution over
cross sections and time.
Let say we have the values of n(i) and let say we know the
distributional properties of n(i) (like: variance, mean). So for a
given correlation coefficient value, how can i generate y(it)?

Search the sci.stat.math archives in Google Groups

generate correlated random (62 hits)

Hope this helps.

Greg

.

Relevant Pages

  • generating correlated random variables
    ... where i denotes the cross section unit and t denotes the time. ... eis independently distributed with the identical distribution over ...
    (sci.stat.math)
  • Re: What is the conjugate prior for Beta distribution
    ... I re-parameter Betaas Betap), where m denotes the mean ... of the distribution while p denotes the "precision" of the ... u and V an independent Gamma process with rate v, ... are those of the Statistics Department or of Purdue University. ...
    (sci.stat.math)
Quantcast