Accession Number : AD0876630

Title :   A Backward Elimination General Significance Regression Model.

Descriptive Note : Technical rept.,

Corporate Author : ARMY MISSILE COMMAND REDSTONE ARSENAL AL SYSTEMS ANALYSIS DIV

Personal Author(s) : Colvin, Charles E. ; Machtolff, Maureen E.

Report Date : OCT 1970

Pagination or Media Count : 55

Abstract : The report develops a statistical procedure for selecting a proper set of independent variables in a linear regression model. The procedure is a backward elimination procedure in which initially a large model is hypothesized and systematically non-significant variables are eliminated one by one. Two different situations were investigated concerning sample estimates of the error: pure error, and using lack-of-fit as an error estimate, with the effects on the testing procedure for each case. (Author)

Descriptors :   (*REGRESSION ANALYSIS, STATISTICAL TESTS), SET THEORY, RANDOM VARIABLES, MATRICES(MATHEMATICS), MATHEMATICAL MODELS, WEAPON SYSTEMS, GUIDED MISSILES, ROCKET ENGINES.

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE