RefDoc
Haut

Faire une nouvelle recherche
Make a new search
Lancer la recherche


Titre du document / Document title

Backward, forward and stepwise automated subset selection algorithms : frequency of obtaining authentic and noise variables

Auteur(s) / Author(s)

DERKSEN S. ; KESELMAN H. J. ;

Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)

Univ. Manitoba, dep. psychology, Winnipeg MB R3T 2N2, CANADA

Résumé / Abstract

The use of automated subset search algorithms is reviewed and issues concerning model selection and selection criteria are discussed. In addition, a Monte Carlo study is reported which presents data regarding the frequency with which authentic and noise variables are selected by automated subset algorithms. In particular, the effects of the correlation between predictor variables, the number of candidate predictor variables, the size of the sample, and the level of significance for entry and deletion of variables were studied for three automated subset algorithms: BACKWARD ELIMINATION, FORWARD SELECTION, and STEPWISE

Revue / Journal Title

British journal of mathematical & statistical psychology    ISSN  0007-1102   CODEN BJMSAK 

Source / Source

1992, vol. 45, no2, pp. 265-282 (1 p.1/2)

Langue / Language

Anglais

Editeur / Publisher

British Psychological Society, Leicester, ROYAUME-UNI  (1948) (Revue)

Mots-clés anglais / English Keywords

Algorithm

;

Selection

;

Variable

;

Statistical method

;

Regression analysis

;

Stepwise mechanism

;

Simulation

;

Monte Carlo method

;

Human

;

Mots-clés français / French Keywords

Algorithme

;

Sélection

;

Variable

;

Méthode statistique

;

Analyse régression

;

Mécanisme par étape

;

Simulation

;

Méthode Monte Carlo

;

Homme

;

Mots-clés espagnols / Spanish Keywords

Algoritmo

;

Selección

;

Variable

;

Método estadístico

;

Análisis regresión

;

Mecanismo a etapas

;

Simulación

;

Método Monte Carlo

;

Hombre

;

Localisation / Location

INIST-CNRS, Cote INIST : 3116 B, 35400003218899.0060

Nº notice refdoc (ud4) : 4398639



Faire une nouvelle recherche
Make a new search
Lancer la recherche
Bas