Accession Number:

ADA021101

Title:

Some Aspects of Principal Component Regression,

Descriptive Note:

Corporate Author:

SOUTHERN METHODIST UNIV DALLAS TEX DEPT OF STATISTICS

Personal Author(s):

• Mansfield,E. R.
• Webster,J. T.
• Gunst,R. F.

Report Date:

1975-01-01

Pagination or Media Count:

38.0

Abstract:

Principal Component Regression Analysis has been popular among data analysts for some time. Lingering doubts remain about the use of this procedure due to the problem of 1 determining which, if any, components should be deleted from the estimator, and 2 establishing criteria for the removal of regressor variables from the model.

Descriptors:

• *RANDOM VARIABLES
• *LEAST SQUARES METHOD
• *LINEAR REGRESSION ANALYSIS
• MATHEMATICAL MODELS
• ESTIMATES
• CORRELATION TECHNIQUES

Subject Categories:

• Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE