+ Reply to Thread
Results 1 to 3 of 3

Thread: Relevance of covariates?

  1. #1
    Points: 4, Level: 1
    Level completed: 7%, Points required for next Level: 46

    Thanked 0 Times in 0 Posts

    Relevance of covariates?

    I have a big group A of individuals that have one common characteristic that make them part of a study in which certain binary variable has to be accounted for. Logistic regression can be used in this case. This group of individuals can be separated in disjoint subgroups A_n based on the date they entered the study. When I perform logistic regression certain covariates appear to be statistically significant to explain log odds ration, but when I do perform the same analysis in each of the subgroups A_n most of the covariates that were significant globally are no longer significant, is there a good explanation for this?
    Last edited by hebertodelrio; 10-07-2017 at 11:01 AM.

  2. #2
    Points: 3,740, Level: 38
    Level completed: 60%, Points required for next Level: 60
    staassis's Avatar
    New York
    Thanked 42 Times in 40 Posts

    Re: Relevance of covariates?

    Yes, those covariates are correlated with when the subject entered the study.

  3. #3
    Omega Contributor
    Points: 39,120, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Not Ames, IA
    Thanked 1,194 Times in 1,155 Posts

    Re: Relevance of covariates?

    OR, when you run the sub-analyses the sample sizes are smaller and you no longer have the power to discern differences. Present the model outputs to better help us understand the results.
    Stop cowardice, ban guns!

+ Reply to 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