+ Reply to Thread
Results 1 to 4 of 4

Thread: covariate for only clinical group

  1. #1
    Points: 21, Level: 1
    Level completed: 41%, Points required for next Level: 29

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    covariate for only clinical group




    HI
    I have tried to find an answer on the web but was not able, and will appreciate your help!
    I have a question regarding the use of a covariate in my analysis.
    I have 2 groups- 1 of patients with clinical variables and a healthy control group. I would like to assess differences between the 2 groups in a continuous dependent variable but to control for 3 vars, using GLM in SPSS.
    The problem is that 2 variables which I would like to control for are clinical so ONLY my patient group has these variables (and not the control group-sysmiss). The third variable I wish to control for is a variable that all subjects in both groups have a value.
    My question: Can I enter a zero value for all my control subjects in the GLM analysis? I this statistically correct? or am I supposed to run a different analysis to examine differences between the 2 groups while controlling for 3 covariates?
    Thank you in advance

  2. #2
    TS Contributor
    Points: 12,501, Level: 73
    Level completed: 13%, Points required for next Level: 349
    rogojel's Avatar
    Location
    I work in Europe, live in Hungary
    Posts
    1,491
    Thanks
    162
    Thanked 334 Times in 314 Posts

    Re: covariate for only clinical group

    hi,
    I think using the clinical variables would contradict the intent of "controlling" for a variable. The idea with that is to take into account differences between the two groups that are coming from differences in the controlled variable ans are not due to the factor you are checkung. E.g. you want to check whether the time spent playing basketball affects the performance - so your main variable is time. But you might want to control for height, because higher players might be better (and they may also spend more time playing). Now imagine you had the height data for successfull players only. There would be no way to dontrol fir height, right?

    regards

  3. #3
    Points: 21, Level: 1
    Level completed: 41%, Points required for next Level: 29

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: covariate for only clinical group

    Thank you! that makes sense!

  4. #4
    Omega Contributor
    Points: 39,045, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,070
    Thanks
    402
    Thanked 1,192 Times in 1,153 Posts

    Re: covariate for only clinical group


    In addition, I am guessing the control group could have a value for the covariate, but they don't given your study design (e.g., BMI, blood pressure, white blood cell count). So their value may not really be "0".
    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