Non-linear canonical correlation

Eeke van der Burg; Jan de Leeuw

doi:10.1111/j.2044-8317.1983.tb00765.x

Non-linear canonical correlation

Eeke van der Burg, Jan de Leeuw

Faculty of Behavioural, Management and Social Sciences

Research output: Contribution to journal › Article › Academic

63 Citations (Scopus)

89 Downloads (Pure)

Abstract

Non-linear canonical correlation analysis is a method for canonical correlation analysis with optimal scaling features. The method fits many kinds of discrete data. The different parameters are solved for in an alternating least squares way and the corresponding program is called CANALS. An application of CANALS is discussed and also a study of the stability of the scaling results.

Original language	Undefined
Pages (from-to)	54-80
Journal	British journal of mathematical and statistical psychology
Volume	36
Issue number	1
DOIs	https://doi.org/10.1111/j.2044-8317.1983.tb00765.x
Publication status	Published - 1983

Keywords

IR-104169

Access to Document

10.1111/j.2044-8317.1983.tb00765.x

vanderburg_deleeuw_A_83
open

Cite this

van der Burg, E., & de Leeuw, J. (1983). Non-linear canonical correlation. British journal of mathematical and statistical psychology, 36(1), 54-80. https://doi.org/10.1111/j.2044-8317.1983.tb00765.x

@article{92169065233e45589376f6b570cb9619,

title = "Non-linear canonical correlation",

abstract = "Non-linear canonical correlation analysis is a method for canonical correlation analysis with optimal scaling features. The method fits many kinds of discrete data. The different parameters are solved for in an alternating least squares way and the corresponding program is called CANALS. An application of CANALS is discussed and also a study of the stability of the scaling results.",

keywords = "IR-104169",

author = "{van der Burg}, Eeke and {de Leeuw}, Jan",

note = "The present article is an expanded and revised version of a paper presented at the European Meeting of the Psychometric Society in Groningen (The Netherlands) in June 1980",

year = "1983",

doi = "10.1111/j.2044-8317.1983.tb00765.x",

language = "Undefined",

volume = "36",

pages = "54--80",

journal = "British journal of mathematical and statistical psychology",

issn = "0007-1102",

publisher = "Wiley-Blackwell",

number = "1",

}

TY - JOUR

T1 - Non-linear canonical correlation

AU - van der Burg, Eeke

AU - de Leeuw, Jan

N1 - The present article is an expanded and revised version of a paper presented at the European Meeting of the Psychometric Society in Groningen (The Netherlands) in June 1980

PY - 1983

Y1 - 1983

N2 - Non-linear canonical correlation analysis is a method for canonical correlation analysis with optimal scaling features. The method fits many kinds of discrete data. The different parameters are solved for in an alternating least squares way and the corresponding program is called CANALS. An application of CANALS is discussed and also a study of the stability of the scaling results.

AB - Non-linear canonical correlation analysis is a method for canonical correlation analysis with optimal scaling features. The method fits many kinds of discrete data. The different parameters are solved for in an alternating least squares way and the corresponding program is called CANALS. An application of CANALS is discussed and also a study of the stability of the scaling results.

KW - IR-104169

U2 - 10.1111/j.2044-8317.1983.tb00765.x

DO - 10.1111/j.2044-8317.1983.tb00765.x

M3 - Article

VL - 36

SP - 54

EP - 80

JO - British journal of mathematical and statistical psychology

JF - British journal of mathematical and statistical psychology

SN - 0007-1102

IS - 1

ER -