1. Posts in the subject areas are now being moderated. Please do not post any details about your exam for at least 3 working days. You may not see your post appear for a day or two. See the 'Forum help' thread entitled 'Using forums during exam period' for further information. Wishing you the best of luck with your exams.
    Dismiss Notice

ASET - October 2010 7 (i)

Discussion in 'SP9' started by Edwin, Sep 19, 2014.

  1. Edwin

    Edwin Member

    Hi all,

    Can someone please explain to me a little more how this can be done, I had thought to myself that there is no relatonship between Monte Carlo and correlation, unless you are speaking Cholesky and therefore assuming that the Multivariate frequency distributions are Multivariate normal, and if you do this then the marginals HAVE to be normal as well...

    ...then the preceeding point about simulating the frequency distribution from a poisson is wrongly placed.

    My thinking is that the only correlation that could be being referred to here is paerson and hence the elliptical property surfaces. I really feel the examiners' could have been clearer and maybe ASET even more clearer. :(
     
    Edwin, Sep 19, 2014
    #1
  2. Simon James

    Simon James ActEd Tutor Staff Member

    Hi Edwin

    you lost me at "Multivariate frequency distributions are Multivariate normal". Why do they have to be normal?
     
    Simon James, Sep 23, 2014
    #2
  3. Edwin

    Edwin Member

    If you are going to simulate with cholesky, or am i wrong Sir?
     
    Edwin, Sep 23, 2014
    #3

Share This Page