When I tried to run proc mi for the following imputation, I noticed that the order of variables in regression model and in the var statement affects the imputed values. I want to understand what    proc mi data=WIDEDAT seed=93538001 nimpute=50 out=OUTMI noprint   minimum=0 maximum=14 minmaxiter=600 ;   by TRT01PN;   class CSIRSTR ;   fcs nbiter=50 reg(BASE = CSIRSTR);   fcs nbiter=50 reg(W2 = CSIRSTR BASE); /** Imputing missing mDSD values at W2**/   fcs nbiter=50 reg(W4 = CSIRSTR BASE W2); /**Imputing missing mDSD values at W4 **/   fcs nbiter=50 reg(W8 = CSIRSTR BASE W2 W4); /**Imputing missing mDSD values at W8 **/   fcs nbiter=50 reg(W12 = CSIRSTR BASE W2 W4 W8);  /** Imputing missing mDSD values at W12 **/   fcs nbiter=50 reg(W16 = CSIRSTR BASE W2 W4 W8 W12); /** Imputing missing mDSD values at W16 **/   fcs nbiter=50 reg(W20 = CSIRSTR BASE W2 W4 W8 W12 W16);    /** Imputing missing mDSD values at W20 **/    fcs nbiter=50 reg(W24 = CSIRSTR BASE W2 W4 W8 W12 W16 W20);    /** Imputing missing mDSD values at W24 **/    var CSIRSTR BASE W2 W4 W8 W12 W16 W20 W24; run; ... View more

proc mi data=widegrp1_2 seed=93538001 nimpute=50 out=newgrp1_2  noprint     minimum= .  0  0  maximum= .  14   14  minmaxiter=600 ;   class CSIRSTR TRT01PN ;   fcs nbiter=50 reg(BASE = CSIRSTR);   fcs nbiter=50 reg(W2 = CSIRSTR BASE); /*[MESURE]='DD'*/   MNAR model(W2/ modelobs=(TRT01PN = '3'));   var CSIRSTR  BASE W2; run;   For the above code, even after I specify minimum and maximum value for all variable listed inn VAR statment, I still get the following WARNING   WARNING: The specified nonmissing MINIMUM= 0 option for the CLASS variable CSIRSTR is not allowed. This option will be ignored. WARNING: The specified nonmissing MAXIMUM= 14 option for the CLASS variable CSIRSTR is not allowed. This option will be ignored.   Is there a way to avoid these WARNING ? Should I modify MNAR statement?     ... View more

proc glm data=outmi;    by _imputation_;   class TRT02PN;   model W24CHG=TRT02PN/solution;   means TRT02PN /hovtest=leven(type=abs);   ods output ParameterEstimates=coeff; run;   I am trying to obtain variance covariance matrix of the Estimates and don't know what line of code I should you.     ... View more

I am trying to obtain pooled p value from ANOVA statistics of 50 imputed datasets created by proc mi. Would appreciate if anyone know the code. ... View more