base control imputation using proc mi

[ndang3188]

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?

[SAS_Rob]

There is a known issue in Proc MI that will be fixed in an upcoming release that requires you also include the MODELOBS= variable in the MIN/MAX= list.  It appends it to the beginning of the variable list on the VAR statement.  Try this code instead:

proc mi data=widegrp1_2 seed=93538001 nimpute=50 out=newgrp1_2  noprint

    minimum= . .  0  0  maximum=.  .  14   14  minmaxiter=600 ;

  class TRT01PN CSIRSTR ;

  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;

[ndang3188]

Thank you for your quick reply. I tried the code and now the imputed result for BASE > 14, which is out of range. Is there any other way to fix this.

[SAS_Rob]

You could try the suggestions in the usage note below.

24475 - Handling the ERROR: "An imputed variable value is not in the specified range after 100 tries...

[ndang3188]

Thank you. I think the issue is with the extra dot in minimum and maximum option. Somehow it assigns no limit to BASE variable. Therefore, there is no error reported in SAS. I should just keep the original code. Thank you for your help.

[ndang3188]

I sincerely apologize. I implemented your approach in the wrong SAS code, that is why it gave the wrong results. This should be implemented for proc mi with MNAR statement. Thank you so much for your help.