mlmsumry Macro for Linear Models Analysis (GLM)

Difficulty Level

Beginner

Published on : 07/11/2022

The `mlmsumry` macro configures ODS outputs to capture model ANOVA tables and multivariate statistics. It executes `PROC GLM` with the provided parameters (classes, model, contrasts, repeated measures). Then, it processes the output tables (`_between_`, `_error_`) via DATA steps to consolidate results, calculate degrees of freedom, and format hypothesis types, before displaying the results.

Data Analysis

Type : EXTERNAL

The code expects an input dataset via the `data` macro parameter (default `_last_`). It does not create hardcoded data but manipulates temporary ODS tables generated by the procedure.

1 Code Block

PROC GLM

Explanation :
Configuration of ODS destinations to capture statistical results and execution of the GLM (General Linear Model) procedure with specified model parameters.

Copied!

1	ods OUTPUT MultStat = _within_ BetweenSubjects.ModelANOVA = _between_ ModelANOVA = _anova_;
2	ods OUTPUT Contrasts = _contrasts_;
3
4	PROC GLM DATA=&DATA;
5	class &class;
6	model &model;
7	&contrasts
8	&repeated
9	RUN;QUIT;

2 Code Block

DATA STEP Data

Explanation :
Processing of ODS results tables. Separates error sources and effects ('Between' vs 'Error'), calculates degrees of freedom (NumDF, DenDF), and restructures the table for the final report.

Copied!

1	DATA _between_ _error_;
2	SET _between_(in=inb) ... ;
3	IF SOURCE = 'Error' THEN OUTPUT _error_;
4	ELSE DO; ... OUTPUT _between_; END;
5	RUN;
6
7	DATA _between_;
8	retain SOURCE FValue NumDF DenDF ProbF;
9	IF _n_=1 THEN SET _error_(rename=(df=DenDF));
10	SET _between_;
11	RUN;

3 Code Block

PROC PRINT

Explanation :
Display of the consolidated statistics table if the multivariate tests option is enabled.

Copied!

1	PROC PRINT;
2	%END;

This material is provided "as is" by We Are Cas. There are no warranties, expressed or implied, as to merchantability or fitness for a particular purpose regarding the materials or code contained herein. We Are Cas is not responsible for errors in this material as it now exists or will exist, nor does We Are Cas provide technical support for it.

Difficulty Level

Published on : 07/11/2022

Data Analysis

1 Code Block

2 Code Block

3 Code Block

Related Documentation