Help using Base SAS procedures

Proc mixed results

New Contributor
Posts: 2

Proc mixed results


So after using the mixed procedure, I get "." for the F value and p-value for my interaction term. Does this mean the interaction term is insignificant or did I do something wrong?

Frequent Contributor
Posts: 149

Re: Proc mixed results

Please show your code and say more about the variables. You ought to get at least one value, but some will be blank. See the examples in the documentation for PROC MIXED

New Contributor
Posts: 2

Re: Proc mixed results

My code:

proc mixed;

  class side event subj;

  model FA = event side event*side;

  repeated event / type=cs subject = subj;

  title2 "MIXED";


My results:


                                                  The Mixed Procedure

                                               Convergence criteria met.                   

                                             Covariance Parameter Estimates

                                            Cov Parm     Subject    Estimate

                                            CS           subj       0.002596

                                            Residual                0.001612

                                                    Fit Statistics

                                         -2 Res Log Likelihood          -363.5

                                         AIC (smaller is better)        -359.5

                                         AICC (smaller is better)       -359.4

                                         BIC (smaller is better)        -356.6

                                            Null Model Likelihood Ratio Test

                                              DF    Chi-Square      Pr > ChiSq

                                               1         55.28          <.0001

                                             Type 3 Tests of Fixed Effects

                                                   Num     Den

                                    Effect          DF      DF    F Value    Pr > F

                                    event            1      30       2.41    0.1312

                                    side             1      30       3.61    0.0672

                                    side*event       0       .        .       .   

I'm just wondering if the missing values for side*event means there's no interaction or if something is wrong with the code/data. Thanks~


Ask a Question
Discussion stats
  • 2 replies
  • 2 in conversation