Author Topic: Dimension variances  (Read 531 times)

Georg II

  • Newbie
  • *
  • Posts: 21
    • View Profile
Dimension variances
« on: May 16, 2012, 03:19:22 AM »
Hi folks,
In a multidimensional analysis with ConQuest I exported the person
parameters on the four dimensions to SPSS and computed their
variances. These variances are much higher than those reported by
ConQuest in the show file. It seems that variances reported by
ConQuest are not the true variances of the ability dimensions and are
adjusted. Can you commnet on this please?

Cheers
Georg II

ConQuest

  • Global Moderator
  • Newbie
  • *****
  • Posts: 24
    • View Profile
    • Email
Re: Dimension variances
« Reply #1 on: May 16, 2012, 03:53:03 AM »
Which person parameters did you export?   The variance of MLEs and WLEs will be greater than the ConQuest direct estimate.  The variance of EAPs willl be less than the ConQuest direct estimate and the variance of PVs will be equivalent to the ConQuest direct estimate.

You say "the variances reported by ConQuest are not the true variances".  In fact the reverse is the case.  The ConQuest direct estimate is unbiased whereas the MLE, WLE and EAP-based estimates are all distorted by measurement error, they are the "not true" variances.

Ray

Georg II

  • Newbie
  • *
  • Posts: 21
    • View Profile
Re: Dimension variances
« Reply #2 on: May 16, 2012, 05:41:44 AM »
Thank you Ray.
I exported both MLEs and WLEs.
So, ConQuest variances are the variances of PV's, right?
Therefore, when we report descriptive stats. for the ability dimensions, there is no need to directly compute varainces. We can report variances reported by ConQuest. Right?


ConQuest

  • Global Moderator
  • Newbie
  • *****
  • Posts: 24
    • View Profile
    • Email
Re: Dimension variances
« Reply #3 on: May 18, 2012, 02:14:24 AM »
ConQuest variance estimates are unbiased estimates of the variance of the latent variable.  If you want to report the variance of a latent variable, then yes it is the value you should use.

Ray