What could be the reason for not consistent of the result?

Home Forums Methodspace discussion What could be the reason for not consistent of the result?

Viewing 2 posts - 1 through 2 (of 2 total)
  • Author
    Posts
  • #685
    Arjun Mani Guragain
    Participant

    We have used the Survey package to investigate adolescent marriage in Nepal using svyglm with sum contrast. The summary of the svyglm,   shows the significant (p value <0.001) however, CI does not consistent to the p values . do u have any suggestion ?

    #686
    Stephen Gorard
    Participant

    Yes. Ignore both. No one seems to understand either p-values or CIs. I suspect you do not either. Just quote your effect size and the quality of your sample (attrition etc.).

Viewing 2 posts - 1 through 2 (of 2 total)
  • You must be logged in to reply to this topic.