+ Reply to Thread
Results 1 to 4 of 4

Thread: Help with interactions in regression

  1. #1
    Points: 883, Level: 15
    Level completed: 83%, Points required for next Level: 17

    Posts
    6
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Help with interactions in regression




    Hi
    I would really appreciate if anyone could please help me with this.
    I am doing a regression analysis, looking at the effect of 2 drugs (A or B) in a population where we stratified individuals by ethnic group:
    Estimates for European Population

    Effect OddsRatioEst LowerCL UpperCL ProbChiSq
    Age 1.005 0.973 1.037 0.7729
    Drug 1.862 1.229 2.821 0.0033
    Sex 1.469 0.925 2.334 0.1033
    Weight 1.015 1.001 1.028 0.0346
    eGFR 1.006 0.995 1.016 0.2967


    ________________________________________
    Estimates for Asian Population

    Obs Effect OddsRatioEst LowerCL UpperCL ProbChiSq
    1 Age 1.047 0.994 1.103 0.0839
    2 Drug 0.719 0.217 2.382 0.5892
    3 Sex 1.932 0.445 8.384 0.3795
    4 Weight 0.987 0.954 1.020 0.4357
    5 eGFR 1.014 0.991 1.036 0.2300


    As you can notice, the effect of the drug A is significantly better than B in the European, but not in the Asian population. One could interpret this as the effect of the drug being modified according to the study subpopulation, and hence expect the p value for interaction to be significant, but it is not at all! 
    ________________________________________
    Interactin term P value

    ProbChiSq
    0.1874



    Any explanation please? Am I missing something

  2. #2
    TS Contributor
    Points: 5,246, Level: 46
    Level completed: 48%, Points required for next Level: 104
    maartenbuis's Avatar
    Location
    Konstanz
    Posts
    372
    Thanks
    3
    Thanked 146 Times in 123 Posts

    Re: Help with interactions in regression

    The fact than an estimate is significant in one sub-population and not significant in another does not mean that the estimates are signficantly different. See: Andrew Gelman and Hal Stern (2006) "The Difference Between “Significant” and “Not Significant” is not Itself Statistically Significant" The American Statistician, 60(4):328-331. http://www.stat.columbia.edu/~gelman...ed/signif4.pdf

  3. The Following User Says Thank You to maartenbuis For This Useful Post:

    Bio_Stat (03-04-2015)

  4. #3
    TS Contributor
    Points: 17,749, Level: 84
    Level completed: 80%, Points required for next Level: 101
    Karabiner's Avatar
    Location
    FC Schalke 04, Germany
    Posts
    2,540
    Thanks
    56
    Thanked 639 Times in 601 Posts

    Re: Help with interactions in regression

    In addition, the sample size (dunno why hardly no-one posts
    this crucial information within his problem description) for Asians
    seems to be very low; although the effect goes into opposite
    direction compared to Europeans, interpretation of the significance
    test for A/B in Asians, or of the non-significant interaction will be
    difficult, due to low power.

    With kind regards

    K.

  5. The Following User Says Thank You to Karabiner For This Useful Post:

    Bio_Stat (03-04-2015)

  6. #4
    Omega Contributor
    Points: 38,289, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,992
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Help with interactions in regression


    It might also be of interest to plot the probability of outcome in euro with drug a and then same thing for drug b. Then draw a line connecting the plots. Then on the same graph do the same thing with Asians probabilities.

    See if lines cross. Also use the probabilities from the full model.
    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