Exam Score Correlation Analysis

This SAS^© script begins by creating a work table named 'EXAM' containing binary responses (0 or 1) to 8 questions for a set of subjects, entered manually via the DATALINES statement. A second DATA step creates the 'prob5_2' table by calculating the raw score ('raw_score') as the sum of questions Q1 to Q8. Finally, the CORR procedure is used to calculate the correlations between each individual question and the calculated total score.

Data Analysis

Type : CREATION_INTERNE

Data is statically generated within the code using the DATALINES statement.

1 Code Block

DATA STEP Data

Explanation :
Creation of the 'EXAM' table by reading data included in the script (DATALINES). 8 numeric variables (Q1 to Q8) are read with a width 1 format.

Copied!

1	DATA EXAM;
2	INPUT (Q1-Q8)(1.);
3
4	DATALINES;
5	10101010
6	11111111
7	11110101
8	01100000
9	11110001
10	11111111
11	11111101
12	11111101
13	10110101
14	00010110
15	;

2 Code Block

DATA STEP Data

Explanation :
Creation of the 'prob5_2' table from 'EXAM'. Calculation of a new variable 'raw_score' representing the sum of variables Q1 to Q8 for each observation.

Copied!

1	DATA prob5_2;
2	SET EXAM;
3	raw_score = sum (of Q1-Q8);
4	RUN;

3 Code Block

PROC CORR

Explanation :
Execution of the CORR procedure to analyze correlation. The 'nosimple' option suppresses simple descriptive statistics. The 'with' statement specifies that the correlation of 'raw_score' with the variables listed in 'var' (Q1-Q8) is desired.

Copied!

1	PROC CORR nosimple;
2	title 'Problem 5.2';
3	var Q1-Q8;
4	with raw_score;
5	RUN;

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.

Retour à la liste