The costs of complex model optimization

C.M. Rubingh; H. Martens; H. van der Voet; A.K. Smilde

doi:10.1016/j.chemolab.2013.04.004

The costs of complex model optimization

C.M. Rubingh, H. Martens, H. van der Voet, A.K. Smilde

Biometris

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

5 Citations (Scopus)

Abstract

Each data-driven action in data modelling consumes degrees of freedom, whether it concerns estimation of parameters, estimation of meta-parameters or selecting variables. By using a double cross validation approach for degrees of freedom calculation the costs for meta-parameter estimation and variable selection can be determined explicitly. The only assumptions are independent and identically distributed errors, which make the approach applicable to many predictive modelling techniques

Original language	English
Pages (from-to)	139-146
Journal	Chemometrics and Intelligent Laboratory Systems
Volume	125
DOIs	https://doi.org/10.1016/j.chemolab.2013.04.004
Publication status	Published - 2013

Keywords

partial least-squares
metabolomics data
validation
selection
freedom

Access to Document

10.1016/j.chemolab.2013.04.004

Cite this

@article{097fbf02a8fa4a3c9c2fd4e834596dce,

title = "The costs of complex model optimization",

abstract = "Each data-driven action in data modelling consumes degrees of freedom, whether it concerns estimation of parameters, estimation of meta-parameters or selecting variables. By using a double cross validation approach for degrees of freedom calculation the costs for meta-parameter estimation and variable selection can be determined explicitly. The only assumptions are independent and identically distributed errors, which make the approach applicable to many predictive modelling techniques",

keywords = "partial least-squares, metabolomics data, validation, selection, freedom",

author = "C.M. Rubingh and H. Martens and {van der Voet}, H. and A.K. Smilde",

year = "2013",

doi = "10.1016/j.chemolab.2013.04.004",

language = "English",

volume = "125",

pages = "139--146",

journal = "Chemometrics and Intelligent Laboratory Systems",

issn = "0169-7439",

publisher = "Elsevier",

}

TY - JOUR

T1 - The costs of complex model optimization

AU - Rubingh, C.M.

AU - Martens, H.

AU - van der Voet, H.

AU - Smilde, A.K.

PY - 2013

Y1 - 2013

N2 - Each data-driven action in data modelling consumes degrees of freedom, whether it concerns estimation of parameters, estimation of meta-parameters or selecting variables. By using a double cross validation approach for degrees of freedom calculation the costs for meta-parameter estimation and variable selection can be determined explicitly. The only assumptions are independent and identically distributed errors, which make the approach applicable to many predictive modelling techniques

AB - Each data-driven action in data modelling consumes degrees of freedom, whether it concerns estimation of parameters, estimation of meta-parameters or selecting variables. By using a double cross validation approach for degrees of freedom calculation the costs for meta-parameter estimation and variable selection can be determined explicitly. The only assumptions are independent and identically distributed errors, which make the approach applicable to many predictive modelling techniques

KW - partial least-squares

KW - metabolomics data

KW - validation

KW - selection

KW - freedom

U2 - 10.1016/j.chemolab.2013.04.004

DO - 10.1016/j.chemolab.2013.04.004

M3 - Article

SN - 0169-7439

VL - 125

SP - 139

EP - 146

JO - Chemometrics and Intelligent Laboratory Systems

JF - Chemometrics and Intelligent Laboratory Systems

ER -

The costs of complex model optimization

Abstract

Keywords

Access to Document

Fingerprint

Cite this