Hi, I would like help to filter my database. My database contains 1000 observations. The input data are: OBS COW_ID TREATMENT BULL PREGNANCY 2 Cow_2 B BULL_D 1 3 Cow_3 C BULL_B 1 4 Cow_4 B BULL_C 0 5 Cow_5 C BULL_H 1 6 Cow_6 A BULL_F 0 7 Cow_7 C BULL_H 1 8 Cow_8 B BULL_B 1 9 Cow_9 A BULL_D 1 10 Cow_10 A BULL_B 1 Would like to remove bulls who has frequency less than 50 observations, that is, keep only the bulls with frequency higher than 50 observations.   My strategy was to use PROC FREQ and find bulls with frequencies below 50 observations. The next step was to use the IF/THEN/DELETE statements to filter the database manually. I wonder if anyone has an alternative idea to reduce manual labor and make it automatic. I share the database and the procedures that I used, to understand the steps by steps.   /*----------------------------------------------------------------------------*/ /*----------------------------------------------------------------------------*/ proc freq data=work.bull_diagnosis order=freq; table Treatment Bull / nopercent nocol nocum ; run; /*----------------------------------------------------------------------------*/ /*----------------------------------------------------------------------------*/ Data Bull_filtered; set work.bull_diagnosis;      if BULL = "BULL_A"  then delete;      if BULL = "BULL_G" then delete;      if BULL = "BULL_J"  then delete;      if BULL = "BULL_I"   then delete;      if BULL = "BULL_E" then delete; run; quit; /*----------------------------------------------------------------------------*/ /*----------------------------------------------------------------------------*/ proc freq data=work.bull_filtered order=freq; table Treatment Bull / nopercent nocol nocum ; run; /*----------------------------------------------------------------------------*/   ... View more

Hello, using the PROC GLIMMIX - LSMEANS I would like to get the differences between the groups (A, B, C and D) for each time (1, 2, 3 and 4).   Exemple:    Only for Time = 1   Tukey-Kramer Grouping for Grupo Least Squares Means (Alpha=0.05) LS-means with the same letter are not significantly different. Grupo Estimate   Grupo D 1.8 A       Grupo B 1.7 B     B Grupo A 1.7 B     B Grupo C 1.6 B      Only for time 2:   Tukey-Kramer Grouping for Grupo Least Squares Means (Alpha=0.05) LS-means with the same letter are not significantly different. Grupo Estimate   Grupo B 1.9 A       Grupo C 1.5 B     B Grupo D 1.3 B     B Grupo A 1.0 B   Only for time 3 ... The same idea...   Only for time 4 ... The same idea...     My line commands were showed below:    PROC GLIMMIX DATA=WORK.Example; CLASS ID Group Time; MODEL var_study = Group Time Group*Time / DDFM=KR DIST=GAUSSIAN; RANDOM Time / RESIDUAL TYPE=CS SUBJECT = ID; LSMEANS Time*Group / LINES ADJUST=TUKEY; RUN; QUIT; /* Dosen´t work the sintaxe = Lsmeans Group*Time / Slice=Time adjust=tukey;     So, in order to get the differences between the groups (A, B, C and D) for each time (1, 2, 3 and 4), how do I construct the LSMEANS procedure?   Thanks a lot, Mingoti, Rodolfo. ... View more

Hello everyone! I have a longitudinal data base and I created one graphics using the Lsmeans of Proc Glimmix (using the Enterprise guide). However, the axis "x" didn't result in a correct order (Firstly the SAS got the output 'D10' folling 'D7', 'D8' and 'D9') However, I am trying to organize the axes "x" in a respective order: 'D7', 'D8', 'D9', and 'D10'. How can I do that? I will be really grateful if someone could help-me!!! Best regards, Rodolfo Mingoti.   ... View more