Portion of the following editor is producing the classic error statement: NOTE: An infinite likelihood is assumed in iteration 0 because of a nonpositive residual variance estimate Note the data below is just a sample of it - is fully factoral with all 1-4 repeated time samples present Data atracomp; Input strain $ comp $ time diam; Datalines; 95 Fus 1 1.825772287 95 Fus 2 1.42601572 95 Fus 3 1.420739244 95 Fus 4 1.456064902 95 Lep 1 1.859838703 Fus Fus 1580 3 1.549731159 Fus 1580 4 1.422556384 Fus 1645 1 1.414225347 Fus 1645 2 1.589653421 Fus 1645 3 1.530931089 Fus 1645 4 1.459880132 Lep 95 1 1.654991843 Lep 95 2 1.466500938 Lep 95 3 1.421560176 Lep 95 4 1.487391453 Lep 1210 1 1.414225347 Lep 1210 2 1.657105307 Lep 1210 3 1.476058942 Lep 1210 4 1.443722042 Lep 1580 1 1.749761889 Lep 1580 2 1.448447445 Lep 1580 3 1.479019946 Lep 1580 4 1.602472049 Lep 1645 1 1.414225347 Lep 1645 2 1.598117643 Lep 1645 3 1.433091065 Lep 1645 4 1.487279395 ; proc mixed data = atracomp; class strain comp time; model diam= strain|comp|time; repeated time / subject=strain*comp type = cs r rcorr; lsmeans comp*strain/slice=comp slice=strain pdiff adj=tukey; run; /*same stats but running with un error structure to compare AIC*/ proc mixed data = atracomp; class strain comp time; model diam= strain|comp|time; repeated time*comp / subject=strain*comp type = ar(1) r rcorr; lsmeans comp*strain/slice=comp slice=strain pdiff adj=tukey; run; ANYONE FIND THE ISSUE IN THIS CODE? It worked beautifully for a similar data set.
... View more