+ Reply to Thread
Results 1 to 3 of 3

Thread: analysis for sparse contingency table

  1. #1
    Points: 1,889, Level: 25
    Level completed: 89%, Points required for next Level: 11

    Thanked 0 Times in 0 Posts

    analysis for sparse contingency table

    I am analyzing a 2x2x3x2 contingency table. The covariates are treatment (2 different kinds, TR1 and TR2, both binary), location of treatment (3 levels A, B, C), and the outcome is an event that either occurred or did not occur. The table is large compared to the sample size, and observing the event is rare, so the table is quite sparse. However, there does appear to be a strong interaction between the outcome and the covariates of interest.

    Some of the suggested strategies were adding a small constant to all zero cells, and/or adjusting the degrees of freedom to account for the zeroes. I was planning on doing some kind of log-linear analysis. I am not too experienced with this kind of analysis so any help would be welcome. Thank you.
    Last edited by jpluta26; 08-31-2015 at 02:03 PM. Reason: formatting

  2. #2
    Points: 12,676, Level: 73
    Level completed: 57%, Points required for next Level: 174
    Master Tagger
    GretaGarbo's Avatar
    Thanked 462 Times in 402 Posts

    Re: analysis for sparse contingency table

    I would also think of a log linear model.

    I believe that the estimates would be OK but that the chi-squared test would maybe not be very well approximated with the chi squared distribution because of many zeros. (That could possibly be investigated with a simulation.)

    Try it!

  3. #3
    Omega Contributor
    Points: 38,396, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Not Ames, IA
    Thanked 1,186 Times in 1,147 Posts

    Re: analysis for sparse contingency table

    Hadn't ever heard of a degree of freedom approach?
    Stop cowardice, ban guns!

+ Reply to Thread


Tags for this Thread

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Advertise on Talk Stats