The CORR Procedure

Example 4: Storing Partial Correlations in an Output Data Set

Procedure features:

PROC CORR statement options:

	COV
	KENDALL
	NOSIMPLE
	OUTP=
	SPEARMAN

PARTIAL statement

VAR statement

Data set:

FITNESS

This example

suppresses descriptive statistics
calculates three types of partial correlation coefficients
calculates a partial covariance matrix
excludes observations with missing values using listwise deletion
selects the analysis variables
creates an output data set with Pearson correlation statistics.

See OUTP= Data Set with Pearson Partial Correlations for a listing of the output data set.

Program

options nodate pageno=1 linesize=120 pagesize=60;

proc corr data=fitness spearman kendall cov nosimple
          outp=fitcorr;

   var weight oxygen runtime;

   partial age;

   label age      = 'Age of subject'
         weight   = 'Wt in kg'
         runtime  = '1.5 mi in minutes'
         oxygen   = 'O2 use';

   title1 'Partial Correlations for a Fitness and Exercise Study';
run;

Output

The report includes a partial covariance matrix and partial correlations for Pearson's rho, Spearman's rho, and Kendall's tau-b. The p-values for Kendall's tau-b are not available. Because observations with missing data are excluded, PROC CORR uses 28 observations to calculate correlation coefficients.

Chapter Contents
Previous
Next
Top of Page

The report includes a partial covariance matrix and partial correlations for Pearson's rho, Spearman's rho, and Kendall's tau-b. The p-values for Kendall's tau-b are not available. Because observations with missing data are excluded, PROC CORR uses 28 observations to calculate correlation coefficients.