Example 1 for PROC GENMOD

Difficulty Level

Beginner

Published on : 01/01/2023

The script begins by creating a dataset named 'drug' using a DATA statement and in-line data (datalines). This dataset contains information on different substances ('drug'), a continuous variable 'x', the number of successes 'r' and the total number of trials 'n'. Then, it uses PROC GENMOD to fit a logistic regression model. The 'drug' variable is declared as a classification variable (CLASS). The model specifies that 'r' events out of 'n' trials are modeled as a function of 'x' and 'drug', using a binomial distribution (dist=bin) and a logit link function (link=logit). The 'lrci' option requests the calculation of likelihood ratio confidence intervals.

Data Analysis

Type : CREATION_INTERNE

The 'drug' dataset is created directly in the script via the DATA statement and in-line data (datalines).

1 Code Block

DATA STEP Data

Explanation :
This code block uses a DATA step to create the 'drug' dataset by reading data directly included in the script via the DATALINES statement. The variables created are 'drug' (character), 'x', 'r', and 'n' (numeric).

Copied!

1	DATA drug;
2	INPUT drug$ x r n;
3	DATALINES;
4	A .1 1 10 A .23 2 12 A .67 1 9
5	B .2 3 13 B .3 4 15 B .45 5 16 B .78 5 13
6	C .04 0 10 C .15 0 11 C .56 1 12 C .7 2 12
7	D .34 5 10 D .6 5 9 D .7 8 10
8	E .2 12 20 E .34 15 20 E .56 13 15 E .8 17 20
9	;

2 Code Block

PROC GENMOD

Explanation :
This block executes the GENMOD procedure to fit a generalized linear model. It specifies the 'drug' dataset as input, declares 'drug' as a classification variable, and defines a logistic regression model ('dist=bin', 'link=logit') where the ratio 'r/n' is modeled as a function of 'x' and 'drug'. The 'lrci' option requests likelihood ratio-based confidence intervals.