Unable to retrive model information (Does not show results for one of my groups under study)

[pramodacharya]

I use SAS University edition to analyze my data. While using SAS PLM Procedure, it give a warning message: WARNING: Unable to retrieve model information from item store WORK.PROGRAM1 with a note of

NOTE: The above message was for the following BY group:

       depth=40-60 and does not show results for one of my groups (depth). However, it shows results for other three groups of my data. How can this problem be solved? I have pasted the codes that I have used. Thank you in advance.

proc sort data=WORK.IMPORT;
by depth year;
ods output type3=aov3;
proc mixed data=WORK.IMPORT method=type3;
by depth;
class year trt rep;
model avln = rep trt year trt*year /ddfm=satterth;
random rep*trt rep*year;
store Program1;
run;
proc print data = aov3;
run;
proc plm source=Program1;
lsmeans trt year trt*year /diff lines; * adjust=tukey;
run;

[PGStats]

That by-group must be flawed in some way, probably insufficient valid data. For example:

1665  /* Empty out one of the by-groups in sashelp.heart */
1666  data heartMod;
1667  set sashelp.heart;
1668  if smoking_status="Light (1-5)" then call missing(cholesterol);
1669  run;

NOTE: There were 5209 observations read from the data set SASHELP.HEART.
NOTE: The data set WORK.HEARTMOD has 5209 observations and 17 variables.
NOTE: DATA statement used (Total process time):
      real time           0.17 seconds
      cpu time            0.01 seconds


1670
1671  proc sort data=heartMod; by smoking_status; run;

NOTE: There were 5209 observations read from the data set WORK.HEARTMOD.
NOTE: The data set WORK.HEARTMOD has 5209 observations and 17 variables.
NOTE: PROCEDURE SORT used (Total process time):
      real time           0.07 seconds
      cpu time            0.00 seconds


1672
1673  proc mixed data=heartMod plots=none;
1674  by smoking_status;
1675  class sex;
1676  model cholesterol = sex;
1677  store heartStore;
1678  run;

NOTE: 28 observations are not included because of missing values.
NOTE: The above message was for the following BY group:
      Smoking Status=' '
NOTE: 17 observations are not included because of missing values.
NOTE: The above message was for the following BY group:
      Smoking Status=Heavy (16-25)
ERROR: No valid observations are present.
NOTE: The above message was for the following BY group:
      Smoking Status=Light (1-5)
NOTE: 13 observations are not included because of missing values.
NOTE: The above message was for the following BY group:
      Smoking Status=Moderate (6-15)
NOTE: 65 observations are not included because of missing values.
NOTE: The above message was for the following BY group:
      Smoking Status=Non-smoker
NOTE: 13 observations are not included because of missing values.
NOTE: The above message was for the following BY group:
      Smoking Status=Very Heavy (> 25)
NOTE: The MIXED procedure generated the model item store WORK.HEARTSTORE.
NOTE: PROCEDURE MIXED used (Total process time):
      real time           0.23 seconds
      cpu time            0.07 seconds


1679
1680  proc plm source=heartStore;
1681  lsmeans sex / diff;
1682  run;

WARNING: Unable to retrieve model information from item store WORK.HEARTSTORE.
NOTE: The above message was for the following BY group:
      Smoking_Status=Light (1-5)
NOTE: PROCEDURE PLM used (Total process time):
      real time           10.59 seconds
      cpu time            2.63 seconds

You will most likely have to exclude that group from the analysis. You can do so by adding a where statement in proc mixed, something like:

where depth ne "40-56";

[pramodacharya]

Thank you for your reply. 

WARNING: Unable to retrieve model information from item store WORK.HEARTSTORE.
NOTE: The above message was for the following BY group:
      Smoking_Status=Light (1-5)

I do have similar logs while analyzing data. But, I checked my data set, even created new excel file. But, it still showed the similar results. But, I need the results for that group as well. Can you say other possible reasons for this happening? I will check my dataset once again. Thank you so much. 

Pramod.

[PGStats]

Check the dataset AFTER it is imported into SAS. Some data might be lost during importation.