Null distribution of the likelihood ratio statistic for feed-forward neural networks

Douglas Landsittel; Harshinder Singh; Vincent C. Arena; Stewart J. Anderson

doi:10.22237/jmasm/1036110120

Null distribution of the likelihood ratio statistic for feed-forward neural networks

Douglas Landsittel
, Harshinder Singh
, Vincent C. Arena
, Stewart J. Anderson

Department of Biostatistics

West Virginia University
NIOSH/HELD
University of Pittsburgh

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Despite recent publications exploring model complexity with modern regression methods, their dimensionality is rarely quantified in practice and the distributions of related test statistics are not well characterized. Through a simulation study, we describe the null distribution of the likelihood ratio statistic for several different feed-forward neural network models.

Original language	English
Pages (from-to)	333-342
Number of pages	10
Journal	Journal of Modern Applied Statistical Methods
Volume	1
Issue number	2
DOIs	https://doi.org/10.22237/jmasm/1036110120
State	Published - 2002

Keywords

Chi-square distribution
Degrees of freedom
Model complexity

Access to Document

10.22237/jmasm/1036110120

Cite this

@article{2e57fa0913654d74b51edff58eeaddee,

title = "Null distribution of the likelihood ratio statistic for feed-forward neural networks",

abstract = "Despite recent publications exploring model complexity with modern regression methods, their dimensionality is rarely quantified in practice and the distributions of related test statistics are not well characterized. Through a simulation study, we describe the null distribution of the likelihood ratio statistic for several different feed-forward neural network models.",

keywords = "Chi-square distribution, Degrees of freedom, Model complexity",

author = "Douglas Landsittel and Harshinder Singh and Arena, \{Vincent C.\} and Anderson, \{Stewart J.\}",

year = "2002",

doi = "10.22237/jmasm/1036110120",

language = "English",

volume = "1",

pages = "333--342",

journal = "Journal of Modern Applied Statistical Methods",

issn = "1538-9472",

publisher = "Wayne State University",

number = "2",

}

TY - JOUR

T1 - Null distribution of the likelihood ratio statistic for feed-forward neural networks

AU - Landsittel, Douglas

AU - Singh, Harshinder

AU - Arena, Vincent C.

AU - Anderson, Stewart J.

PY - 2002

Y1 - 2002

N2 - Despite recent publications exploring model complexity with modern regression methods, their dimensionality is rarely quantified in practice and the distributions of related test statistics are not well characterized. Through a simulation study, we describe the null distribution of the likelihood ratio statistic for several different feed-forward neural network models.

AB - Despite recent publications exploring model complexity with modern regression methods, their dimensionality is rarely quantified in practice and the distributions of related test statistics are not well characterized. Through a simulation study, we describe the null distribution of the likelihood ratio statistic for several different feed-forward neural network models.

KW - Chi-square distribution

KW - Degrees of freedom

KW - Model complexity

UR - https://www.scopus.com/pages/publications/18444412884

U2 - 10.22237/jmasm/1036110120

DO - 10.22237/jmasm/1036110120

M3 - Article

AN - SCOPUS:18444412884

SN - 1538-9472

VL - 1

SP - 333

EP - 342

JO - Journal of Modern Applied Statistical Methods

JF - Journal of Modern Applied Statistical Methods

IS - 2

ER -

Null distribution of the likelihood ratio statistic for feed-forward neural networks

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this