Exploring function estimators as an alternative to regression in psychology

I Walker, S Milne

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Most forms of regression analysis make assumptions about the relationships between the variables being modeled. As a consequence, it can be difficult to know which form of analysis is most appropriate for a given data set. In this article, we explore the idea that function estimators might provide a better alternative in many situations. Function estimators discover the best function to link dependent and independent variables, no matter what form this takes. Four studies demonstrate that one type of function estimator (a neural network) not only performs the same tasks as linear regression and nonlinear regression, but often performs these tasks better and with more flexibility. Moreover, neural networks allow a useful secondary analysis in which useful groups of people can be identified. We recommend that function estimators be used in preference to regression-based techniques for many analyses. The Matlab script used to write this article may be downloaded from www.psychonomic.org/archive/.
Original languageEnglish
Pages (from-to)23-36
Number of pages14
JournalBehavior Research Methods
Volume37
Issue number1
Publication statusPublished - 2005

Fingerprint

Linear Models
Regression Analysis
Psychology
Datasets
Neural Networks
Linear Regression
Secondary Analysis

Cite this

Exploring function estimators as an alternative to regression in psychology. / Walker, I; Milne, S.

In: Behavior Research Methods, Vol. 37, No. 1, 2005, p. 23-36.

Research output: Contribution to journalArticle

@article{06b9210a40934d96b31012471ae9e5df,
title = "Exploring function estimators as an alternative to regression in psychology",
abstract = "Most forms of regression analysis make assumptions about the relationships between the variables being modeled. As a consequence, it can be difficult to know which form of analysis is most appropriate for a given data set. In this article, we explore the idea that function estimators might provide a better alternative in many situations. Function estimators discover the best function to link dependent and independent variables, no matter what form this takes. Four studies demonstrate that one type of function estimator (a neural network) not only performs the same tasks as linear regression and nonlinear regression, but often performs these tasks better and with more flexibility. Moreover, neural networks allow a useful secondary analysis in which useful groups of people can be identified. We recommend that function estimators be used in preference to regression-based techniques for many analyses. The Matlab script used to write this article may be downloaded from www.psychonomic.org/archive/.",
author = "I Walker and S Milne",
note = "ID number: ISI:000231147600004",
year = "2005",
language = "English",
volume = "37",
pages = "23--36",
journal = "Behavior Research Methods",
issn = "1554-351X",
publisher = "Psychonomic Society Inc.",
number = "1",

}

TY - JOUR

T1 - Exploring function estimators as an alternative to regression in psychology

AU - Walker, I

AU - Milne, S

N1 - ID number: ISI:000231147600004

PY - 2005

Y1 - 2005

N2 - Most forms of regression analysis make assumptions about the relationships between the variables being modeled. As a consequence, it can be difficult to know which form of analysis is most appropriate for a given data set. In this article, we explore the idea that function estimators might provide a better alternative in many situations. Function estimators discover the best function to link dependent and independent variables, no matter what form this takes. Four studies demonstrate that one type of function estimator (a neural network) not only performs the same tasks as linear regression and nonlinear regression, but often performs these tasks better and with more flexibility. Moreover, neural networks allow a useful secondary analysis in which useful groups of people can be identified. We recommend that function estimators be used in preference to regression-based techniques for many analyses. The Matlab script used to write this article may be downloaded from www.psychonomic.org/archive/.

AB - Most forms of regression analysis make assumptions about the relationships between the variables being modeled. As a consequence, it can be difficult to know which form of analysis is most appropriate for a given data set. In this article, we explore the idea that function estimators might provide a better alternative in many situations. Function estimators discover the best function to link dependent and independent variables, no matter what form this takes. Four studies demonstrate that one type of function estimator (a neural network) not only performs the same tasks as linear regression and nonlinear regression, but often performs these tasks better and with more flexibility. Moreover, neural networks allow a useful secondary analysis in which useful groups of people can be identified. We recommend that function estimators be used in preference to regression-based techniques for many analyses. The Matlab script used to write this article may be downloaded from www.psychonomic.org/archive/.

M3 - Article

VL - 37

SP - 23

EP - 36

JO - Behavior Research Methods

JF - Behavior Research Methods

SN - 1554-351X

IS - 1

ER -