07-20-2016 01:07 PM
Hi All, I have 2 -yr field data that I want to analyse together (Multi-yr analysis). I have all parameters measured for the two years. but when I put my repeated measure code below
proc mixed data;
class Year Rep T_System;
model &var = T_System;
random Rep(year) year year*T_System/solution;
repeated year/subject=rep*T_System type=ar(1) RCORR;
I GET THIS MESSAGE "
NOTE: An infinite likelihood is assumed in iteration 0 because of a nonpositive definite estimated R matrix for Rep*T_System 1 HIGH
HIGH DUR is one of the crops am analysing. This code has been workingfor me before (even on other two yr-analysis), Please is there anything I am not doing right?. Or is there any special character in my data? (please find attached).