Best linear predictors for factor scores

W.P. Krijnen; T.J. Wansbeek; J.M.F. Ten Berge

doi:10.1080/03610929608831883

Best linear predictors for factor scores

W.P. Krijnen, T.J. Wansbeek, J.M.F. Ten Berge

Onderzoeksoutput: Article › Academic › peer review

31 Citaten (Scopus)

Samenvatting

From the literature three types of predictors for factor scores are available. These are characterized by the constraints: linear, linear conditionally unbiased, and linear correlation preserving. Each of these constraints generates a class of predictors. Best predictors are defined in terms of Lowner's partial matrix order applied to matrices of mean square error of prediction. It is shown that within the first two classes a best predictor exists and that it does not exist in the third.

Originele taal-2	English
Pagina's (van-tot)	3013-3025
Aantal pagina's	13
Tijdschrift	Communications in Statistics. Part A: Theory and Methods
Volume	25
Nummer van het tijdschrift	12
DOI's	https://doi.org/10.1080/03610929608831883
Status	Published - 1996

Toegang tot document

10.1080/03610929608831883

Handle.net

Permanente koppeling

Citeer dit

@article{e2cc3fa90b1c4e2b820b73e4ff79eaeb,

title = "Best linear predictors for factor scores",

abstract = "From the literature three types of predictors for factor scores are available. These are characterized by the constraints: linear, linear conditionally unbiased, and linear correlation preserving. Each of these constraints generates a class of predictors. Best predictors are defined in terms of Lowner's partial matrix order applied to matrices of mean square error of prediction. It is shown that within the first two classes a best predictor exists and that it does not exist in the third.",

keywords = "Lowner's partial matrix order, mean square error, conditional unbiasedness, correlation preservation",

author = "W.P. Krijnen and T.J. Wansbeek and {Ten Berge}, J.M.F.",

note = "Jaargang 1996, nr. juli/augustus",

year = "1996",

doi = "10.1080/03610929608831883",

language = "English",

volume = "25",

pages = "3013--3025",

journal = "Communications in Statistics. Part A: Theory and Methods",

issn = "0361-0926",

number = "12",

}

TY - JOUR

T1 - Best linear predictors for factor scores

AU - Krijnen, W.P.

AU - Wansbeek, T.J.

AU - Ten Berge, J.M.F.

N1 - Jaargang 1996, nr. juli/augustus

PY - 1996

Y1 - 1996

N2 - From the literature three types of predictors for factor scores are available. These are characterized by the constraints: linear, linear conditionally unbiased, and linear correlation preserving. Each of these constraints generates a class of predictors. Best predictors are defined in terms of Lowner's partial matrix order applied to matrices of mean square error of prediction. It is shown that within the first two classes a best predictor exists and that it does not exist in the third.

AB - From the literature three types of predictors for factor scores are available. These are characterized by the constraints: linear, linear conditionally unbiased, and linear correlation preserving. Each of these constraints generates a class of predictors. Best predictors are defined in terms of Lowner's partial matrix order applied to matrices of mean square error of prediction. It is shown that within the first two classes a best predictor exists and that it does not exist in the third.

KW - Lowner's partial matrix order

KW - mean square error

KW - conditional unbiasedness

KW - correlation preservation

U2 - 10.1080/03610929608831883

DO - 10.1080/03610929608831883

M3 - Article

SN - 0361-0926

VL - 25

SP - 3013

EP - 3025

JO - Communications in Statistics. Part A: Theory and Methods

JF - Communications in Statistics. Part A: Theory and Methods

IS - 12

ER -