About Kristinos

Kristinos · ‎05-04-2019

Hi! I am making some sgplots, but the variables at the y-axis have capital letters in subscript: e.g. the "G" in "NEG" should be subscript. Is this possible to do in a sgplot? I have found a code for using unicode (http://support.sas.com/kb/39/267.html), but it seems like the subscript capital G does not have an unicode?? I am working in SAS 9.4 for windows

Kristinos · ‎05-26-2017

Ex.2 does not include "random fcode /solution;" an det ESTIMATE statement works. If I drop "random fcode /solution;" from ex. 1 the ESTIMATE works.

Kristinos · ‎05-24-2017

I don't think the use of Legendre polynomials is the problem in our case. It just seems like SAS won't let us include more than one random effect in the ESTIMATE statement, regardless of type of variable. I have written two exampes of RANDOM statements below. The MODEL run perfect in both exampes, but we have not been able to write the ESTIMATE statement without getting the following log: ERROR: SUBJECT contrasts not permitted with multiple RANDOM statements; the ESTIMATE statement is ignored RANDOM statement ex. 1: .... random fcode /solution; random LEG0 /subject=ID solution; .... RANDOM statement ex. 2: .... random LEG0 LEG1 /subject=ID solution; ...

Kristinos · ‎05-23-2017

Hi sId! Thank you for your reply! Our data consist of repeated body weight records of 80 heifers. Body weight was recorded every second week from 3 to 15 months of age. The heifers were assigned to four different treatments (20 heifers in each group). Legendre polynomials (Leg0 - Leg2) were fitted within treatment groups (TRT), and we attempt to include a random effect of ensilage (fcode) and also a random effect of individual (id). We have constructed a random regression model in BLUP without an additive relationship matrix on the random effects. The repeated statement was used as the individuals have repeated records, and heterogeneous error variance was by age group. What we attempt to do is to use the ESTIMATE statement to test hypotheses for treatment effects at a given time point. We are well aware that by correcting for random effects, the power of the test will be better, but we don’t know how to do to this in SAS. Explanation: id = 80 heifers TRT = 4 different treatment groups fcode = effect of feed batch (26 different batches) agegr = 5 different age groups to correct for heterogeneous variance LEG0, LEG1, LEG2 = Legendre polynomials of 1 st , 2 nd and 3 rd order to fit the data (The model is simplified) Proc mixed data=data1; class ID TRT fcode agegr; model BW = LEG0(TRT) LEG1(TRT) LEG2(TRT) / noint solution DDFM=satterthwaite ; random fcode /solution; random LEG0 /subject=ID solution; repeated /subject=ID TYPE=VC grp=agegr; estimate "TRT 1" LEG0(trt) 0.7071 0 0 0 LEG1(trt) -1.2247 0 0 0 LEG2(trt) 1.5811 0 0 0 | LEG0 0.7071 / sub 0 0.05 0 0 0 0.05 0 0 0.05 0 0 0 0 0 0 0.05 0.05 0 0 0 0 0 0.05 0 0 0.05 0 0 0.05 0 0 0 0 0 0.05 0.05 0 0 0 0.05 0 0 0 0 0 0 0 0 0.05 ; estimate "TRT 2" LEG0(trt) 0 0.7071 0 0 LEG1(trt) 0 -1.2247 0 0 LEG2(trt) 0 1.5811 0 0 | Leg0 0.7071 / sub 0 0 0 0.05 0 0 0.05 0 0 0 0 0.05 0 0 0.05 0 0 0 0.05 0 0.05 0 0 0 0.05 0 0 0 0 0 0.05 0 0 0 0 0 0.05 0 0.05 0 0 0 0 0 0.05 0.05 0 0 0 0.05 0 0 0 0 0 0 0 0.05 0.05 0 0.05 0 0 0 0 0 0.05 0.05 0.05 0 0 0 0 0 0 0 0 0.05 0 0 ; estimate "TRT 3" LEG0(trt) 0 0 0.7071 0 LEG1(trt) 0 0 -1.2247 0 LEG2(trt) 0 0 1.5811 0 | Leg0 0.7071 / sub 0.05 0 0 0 0 0 0 0.05 0 0 0.05 0 0 0.05 0 0 0 0 0 0.05 0 0 0 0.05 0 0 0.05 0 0 0.05 0 0 0 0 0 0 0 0.05 0 0 0.05 0.05 0.05 0 0 0 0 0 0 0 0.05 0 0.05 0 0 0 0 0 0 0 0 0.05 0.05 0.05 0 0 0 0 0 0.05 0 0 0.05 0 0 0.05 0 0 0 0 ; estimate "TRT 4" LEG0(trt) 0 0 0 0.7071 LEG1(trt) 0 0 0 -1.2247 LEG2(trt) 0 0 0 1.5811 |Leg0 0.7071 / sub 0 0 0.05 0 0.05 0 0 0 0 0.05 0 0 0.05 0 0 0 0 0.05 0 0 0 0.05 0 0 0 0 0 0.05 0 0 0 0.05 0.05 0.05 0 0 0 0 0 0 0 0 0 0.05 0 0 0.05 0.05 0 0 0 0.05 0 0 0 0 0.05 0 0 0 0 0 0 0 0.05 0 0 0 0 0 0 0 0 0.05 0.05 0 0 0 0.05 0.05 ; run;

Kristinos · ‎05-22-2017

Is it nobody who knows anything about this?

Kristinos · ‎05-19-2017

Hi! Is it possible to test multiple random effects in the estimate statement? I have a mixed model with two random statements. The model runs with no problem, but when I try to set up a lsmeans in the estimate statement SAS the problem starts... The log says: "ERROR: SUBJECT contrasts not permitted with multiple RANDOM statements; the ESTIMATE statement is ignored." It seems like there is not possible to have multiple random statements! ? Is this correct? Or is there a way around this problem? The progam looks something like this: Proc mixed data=data1; class ID TRT Age fcode; model weight = LEG0(TRT) LEG1(TRT) LEG2(TRT) Age index / noint solution DDFM=satterthwaite ; random fcode /solution; random LEG0 LEG1 /subject=ID solution; * estimate "TRT1 lsmeans" index 108.8 AGE 0.2 0.2 0.2 0.2 0.2 LEG0(trt) 0.7071 0 0 0 LEG1(trt) -1.2247 0 0 0 LEG2(trt) 1.5811 0 0 0 LEG3(trt) -1.8709 0 0 0 | LEG0 0.7071 Leg1 -1.2247 / sub 0 0.05 0 0 0 0.05 0 0 0.05 0 0 0 0 0 0 0.05 0.05 0 0 0 0 0 0.05 0 0 0.05 0 0 0.05 0 0 0 0 0 0.05 0.05 0 0 0 0.05 0 0 0 0 0 0 0 0 0.05 ; run;

Kristinos · ‎03-07-2017

Thank you so much for the help! Both RW9 and ballardw! This seems to work very fine! And thanks for keeping up with my slow brain...

Kristinos · ‎03-07-2017

I'm so sorry RW9! My brain is kind of chaotic today... 😞

Kristinos · ‎03-07-2017

I was not able to make sas understand that the first row was dates...

Kristinos · ‎03-07-2017

The dataset looks like this after import: Obs ID _2016_12_21 _2016_12_22 _2016_12_23 _2016_12_24 _2016_12_25 _2016_12_26 _2016_12_27 _2016_12_28 _2016_12_29 _2016_12_30 _2016_12_31 _2017_01_01 _2017_01_02 _2017_01_03 _2017_01_04 _2017_01_05 _2017_01_06 _2017_01_07 _2017_01_08 _2017_01_09 _2017_01_10 _2017_01_11 _2017_01_12 _2017_01_13 _2017_01_14 _2017_01_15 _2017_01_16 _2017_01_17 _2017_01_18 _2017_01_19 _2017_01_20 _2017_01_21 _2017_01_22 _2017_01_23 _2017_01_24 _2017_01_25 _2017_01_26 _2017_01_27 _2017_01_28 _2017_01_29 _2017_01_30 _2017_01_31 _2017_02_01 _2017_02_02 _2017_02_03 _2017_02_04 _2017_02_05 _2017_02_06 _2017_02_07 _2017_02_08 _2017_02_09 _2017_02_10 _2017_02_11 _2017_02_12 _2017_02_13 _2017_02_14 _2017_02_15 _2017_02_16 _2017_02_17 _2017_02_18 _2017_02_19 _2017_02_20 1 5575 32.77 41.7 28.12 38.52 45.02 33.65 32.21 38.85 40.52 29.31 38.93 33.1 33.94 32.59 36.65 33.75 33.76 34.04 34.02 19.08 35.1 36.95 26.12 48.02 16.14 36.57 42.76 28.95 36.67 18.09 29.66 35.63 34.75 41.29 33.85 36.25 21.24 41.29 41.73 20.72 39.71 20.71 40.59 31.64 39.44 33.12 27.28 42.64 35.73 20.55 41.71 41.07 21.97 23.64 42.19 21.19 42.83 38.4 20.13 39.33 31.5 36.44 2 5613 46.34 26.24 40.32 51.1 36.91 26.19 27.62 28.43 49.99 38.26 40.39 29.63 43.46 28.14 41.61 28.75 43.99 27.92 39.37 26.13 41.68 40.61 38.62 36.18 34.72 35.01 32.26 31.18 34.52 41.97 34.22 23.79 46.6 29.7 35.87 34.54 35.36 34.03 34.19 35.67 32.59 37.87 35.54 38.99 37.66 34.49 30.59 29.8 34.18 38.05 25.63 31.25 33.02 36.65 32.94 22.22 40.05 31.92 37.63 29.51 31.74 31.37 3 5651 29.75 36.73 54.97 35.04 44.19 34.97 22.21 36.97 34.95 45.28 40.22 37.15 36.43 46.33 27.89 35.41 43.52 36.52 34.15 39.46 23.78 48.23 33.41 39.23 37.88 25.65 45.69 29.11 35.66 36.76 37.09 26.23 32.73 35.34 37.5 33.44 26.54 37.65 31.71 41.41 33.82 22.88 40.01 30.7 40.43 28.24 38.1 29.59 31.33 38.35 34.86 29.66 29.65 35.49 36.93 27.5 37.58 32.34 28.79 32.26 33.98 34.24 4 5714 45.93 44.42 35.13 32.68 41.83 41.33 41.98 39.49 41.33 34.41 40 28.07 43.36 36.83 39.37 35.39 21.8 46.95 30.47 41.21 25.66 50.47 29.39 37.69 26.55 45.23 38.51 29.32 38.55 43.1 29.39 30.76 39.19 39.96 34.09 34.85 25.31 40.84 41.72 31.23 37.1 36.68 28.29 45.14 27.59 36.41 40.22 24.59 44.1 27.53 40.25 29.6 41.65 28.61 43.85 36.88 38.9 28.96 40.36 37.45 36.54 27.16 5 5725 19.67 45.94 31.02 34.2 32.03 45.44 15.83 34.11 33.42 28.87 33.11 33.21 31.7 32.14 30.39 33.02 31.94 33.52 25.31 33.06 20.56 41.44 28.85 23.69 28.44 34.46 23.71 28.75 31.26 15.65 33.35 24.34 18.02 27.56 24.67 26.9 14.41 32.43 21.77 26.16 29.05 35.7 23 25.97 26.2 12.53 32.44 15.06 33.83 13.76 26.54 26.42 17.18 19.52 32.38 14.1 31.15 24.45 12.9 30.1 24.8 24.08 It has 200 columns with dates and 140 rows with individuals

Kristinos · ‎03-07-2017

I'm importing with proc import: Title ; PROC Import OUT= work.Dataset_Milkyield DATAFILE= "Y:\\Dataset_milkyield.xlsx" DBMS=xlsx REPLACE; Getnames=YES; RUN;

Kristinos · ‎03-07-2017

I have a dataset in excel that looks like this: ID 2016.09.13 2016.09.14 2016.09.15 5756 28.74 35.87 35.04 5830 26.65 25.51 29.78 5838 13.2 . 17.03 The first column is ID-number The following columns are milk yield at a given dates. I want to import the data to SAS (which is not a problem), but to be able to work with the dataset in SAS I need it to look like this: ID Date Milk yield 5756 2016.09.13 28.74 5830 2016.09.13 26.65 5838 2016.09.13 13.2 5756 2016.09.14 35.87 5830 2016.09.14 25.51 5838 2016.09.14 . 5756 2016.09.15 35.04 5830 2016.09.15 29.78 5838 2016.09.15 17.03 Does anyone have a clue how to do that? I'm totaly blank!

Kristinos · ‎11-27-2014

Thank you very much for the suggestion and the articles, it seems to work!

Kristinos · ‎11-27-2014

I have actually tried both the ways I know of, but haven't succeeded. Guess I should have included it here, sorry. I know that when merging I should merge by one or several common variables, but since data1 and data2 have only ID as common variable the basic code: Data dataNEW; merge data1 data2 by ID; does not work, because the output will look like this: ID testday yield Age Weight 20 1 200 180 200 20 2 250 300 300 30 1 190 180 200 I have also tried the code with the in-statement: Data dataNEW; merge data1 (in=a) data2; by ID ; if a=1;run; My merge skills kind of stops here... But maybe one solution could be to make a variable called "Age" in data1, and then run a do-statement to give the Age variable the variables 180 and 300... Then I could use the "normal" by-statement in the merge procedure ! Hmm... I haven't thought of that solution before... Guess it could be done in other ways as well, but it should work. Thanks Patrick, It actually helps to find a solution only by writing down what the problem is, so I will remember that the next time I have problems in SAS!

Kristinos · ‎11-27-2014

Hi! Does anyone know how I can merge DATA1 and DATA2 in the example below? Data1 ID testday yield 20 1 200 20 2 250 30 1 190 Data2 ID Age Weight 20 180 200 20 300 300 30 180 200 Output: ID testday yield Age Weight 20 1 200 180 200 20 1 200 300 300 20 2 250 180 200 20 2 250 300 300 30 1 190 180 200 Thank you!

Online Status	Offline
Date Last Visited	‎05-04-2019 09:56 AM

Capital letters in subscript in proc sgplot, is it possible?

Re: Multiple random effects

Re: Multiple random effects

Re: Multiple random effects

Re: Multiple random effects

Multiple random effects

Re: I want only ONE date with observation in each row, but I have 200....

Re: I want only ONE date with observation in each row, but I have 200....

Re: I want only ONE date with observation in each row, but I have 200....

Re: I want only ONE date with observation in each row, but I have 200....

Re: I want only ONE date with observation in each row, but I have 200....

Re: Plotting large values in SGPLOT

Re: Plotting large values in SGPLOT

Capital letters in subscript in proc sgplot, is it possible?

Re: Multiple random effects

Re: Multiple random effects

Re: Multiple random effects

Re: Multiple random effects

Multiple random effects

Re: I want only ONE date with observation in each row, but I have 200....

Re: I want only ONE date with observation in each row, but I have 200....

Re: I want only ONE date with observation in each row, but I have 200....

Re: I want only ONE date with observation in each row, but I have 200....

Re: I want only ONE date with observation in each row, but I have 200....

I want only ONE date with observation in each row, but I have 200...

Re: How to merge??

Re: How to merge??

How to merge??