+ Reply to Thread
Results 1 to 1 of 1

Thread: Mixed Models Linear Regression in SPSS

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

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Mixed Models Linear Regression in SPSS




    Hello all,

    I am running a Mixed Models Linear Regression analysis in SPSS and I'm having trouble determining if I need to include both /RANDOM and /REPEATED statements for my design.

    My unit of analysis is Country. Here is some information on my key variables:
    DV=Violence (rate) for country (continuous variable)
    IV=Political regime for country (e.g., Democracy, Autocracy, etc.) (categorical variable)
    Covariate=Time (in years where Time=0 is 1960, Time=1 is 1961, etc.)
    Repeated Measure=WAVE (time in 5-year intervals) Note: most measurements on the DV are taken every 5 years.

    Here is a version of the syntax I've been running:

    MIXED Violence BY Regime WITH Time
    /CRITERIA=CIN(95) MXITER(100) MXSTEP(10) SCORING(1) SINGULAR(0.000000000001) HCONVERGE(0,
    ABSOLUTE) LCONVERGE(0, ABSOLUTE) PCONVERGE(0.000001, ABSOLUTE)
    /FIXED=Violence Time Regime*Time | SSTYPE(3)
    /METHOD=REML
    /PRINT= SOLUTION TESTCOV
    /RANDOM=INTERCEPT Time | SUBJECT(Country) COVTYPE(UN) ***Is this necessary?
    /REPEATED=WAVE | SUBJECT(Country) COVTYPE(ARH1).

    So once again, do I need to include the /RANDOM statement? Since violence rates are not measured every year, should I consider Time to be a random sample of all available measurements? If I don't include the /RANDOM statement, does this mean that I am not running a "Mixed" model anymore. And lastly, which Covariance Structure should I use?
    Last edited by Paul CPH; 03-18-2013 at 07:08 PM.

+ 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