Group effect: the endless river [General Sta­tis­tics]

posted by PharmCat  – Russia, 2019-12-22 22:52  – Posting: # 21019
Views: 816

(edited by PharmCat on 2019-12-23 17:04)

Hi!

» Is it right that we can simply neglect the structure of this term as we can do in standard models with Subject instead of Subject(Sequence)?

Edited.

You can use just "Subject" in random statement in SAS. I think if you try to do this, you should get the same results. Of course, if your subject numbers not repeated.

Data:
DATA data;
infile datalines dlm=" " truncover;
input subject $ house $ room $ var;
datalines;
1 1 1 4
1 1 1 6
2 1 1 6
2 1 1 10
3 1 2 2
3 1 2 4
4 1 2 2
4 1 2 3
5 2 3 8
5 2 3 10
6 2 3 6
6 2 3 10
7 2 4 4
7 2 4 6
;
RUN;



Code 1

PROC MIXED data=data;
CLASSES subject house room;
MODEL  var = house room/ DDFM=SATTERTH solution;
RANDOM subject/V G;
ESTIMATE 'house' house -1 1/e;
RUN;


Fixed effect without denoted nested factors: problem with results, but coefficient calculated correctly.

Code 2

PROC MIXED data=data;
CLASSES subject house room;
MODEL  var = house room(house)/ DDFM=SATTERTH solution;
RANDOM subject/V G;
ESTIMATE 'house' house -1 1/e;
RUN;


Fixed effect with nested factor: no problems, but Subjects in Dimensions = 1. Look at horrible V matrix. In this case it does not matter, but it not corresponds with reality.

Code 3

PROC MIXED data=data;
CLASSES subject house room;
MODEL  var = house room(house)/ DDFM=SATTERTH solution;
RANDOM intercept/SUBJECT=subject V G;
ESTIMATE 'house' house -1 1/e;
RUN;


Good fit. Subjects in Dimensions = 8. We have individual V matrices and ready for structuring.

Code 4

PROC MIXED data=data;
CLASSES subject house room;
MODEL  var = house room(house)/ DDFM=SATTERTH solution;
RANDOM intercept/SUBJECT=subject(room) V G;
ESTIMATE 'house' house -1 1/e;
RUN;


Nested random part - no effect.

I can't find any difference between subject and subject(room). As I understand nested factors affect on fixed part. I don't know how nested statment can affect on random part, but I think - in this case there is no effect.

Complete thread:

Activity
 Admin contact
20,250 posts in 4,262 threads, 1,398 registered users;
online 19 (0 registered, 19 guests [including 9 identified bots]).
Forum time (Europe/Vienna): 06:50 CET

No written law has ever been more binding than
unwritten custom supported by popular opinion.    Carrie Chapman Catt

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5