Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion

Karin Meyer; Mark Kirkpatrick; Daniel Gianola

Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion

Karin Meyer
, Mark Kirkpatrick
, Daniel Gianola

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

A simulation study examining the effects of 'regularization' on estimates of genetic covariance matrices for small samples is presented. This is achieved by penalizing the likelihood, and three types of penalties are examined. It is shown that regularized estimation can substantially enhance the accuracy of estimates of genetic parameters. Penalties shrinking estimates of genetic covariances or correlations towards their phenotypic counterparts acted somewhat differently to those aimed reducing the spread of sample eigenvalues. While improvements of estimates were found to be comparable overall, shrinkage of genetic towards phenotypic correlations resulted in least bias.

Original language	English
Title of host publication	Proceedings of the Association for the Advancement of Animal Breeding and Genetics
Editors	William Pattie
Place of Publication	Armidale, Australia
Publisher	Association for the Advancement of Animal Breeding and Genetics (AAABG)
Pages	87-90
Volume	19
ISBN (Print)	9780646559155
Publication status	Published - 2011
Event	AAABG 2011: 19th Conference of the Association for the Advancement of Animal Breeding and Genetics - Perth, Australia Duration: 19 Jul 2011 → 21 Jul 2011

Conference

Conference	AAABG 2011: 19th Conference of the Association for the Advancement of Animal Breeding and Genetics
City	Perth, Australia
Period	19/07/11 → 21/07/11

Keywords

Quantitative Genetics (incl Disease and Trait Mapping Genetics)
Animal Breeding

Access to Document

https://hdl.handle.net/1959.11/9871

Handle.net

Persistent link

Cite this

Meyer, K., Kirkpatrick, M., & Gianola, D. (2011). Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion. In W. Pattie (Ed.), Proceedings of the Association for the Advancement of Animal Breeding and Genetics (Vol. 19, pp. 87-90). Association for the Advancement of Animal Breeding and Genetics (AAABG). https://hdl.handle.net/1959.11/9871

Meyer, Karin ; Kirkpatrick, Mark ; Gianola, Daniel. / Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion. Proceedings of the Association for the Advancement of Animal Breeding and Genetics. editor / William Pattie. Vol. 19 Armidale, Australia : Association for the Advancement of Animal Breeding and Genetics (AAABG), 2011. pp. 87-90

@inproceedings{1b37bd0dcc8841aa80e1ed77ca05709f,

title = "Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion",

abstract = "A simulation study examining the effects of 'regularization' on estimates of genetic covariance matrices for small samples is presented. This is achieved by penalizing the likelihood, and three types of penalties are examined. It is shown that regularized estimation can substantially enhance the accuracy of estimates of genetic parameters. Penalties shrinking estimates of genetic covariances or correlations towards their phenotypic counterparts acted somewhat differently to those aimed reducing the spread of sample eigenvalues. While improvements of estimates were found to be comparable overall, shrinkage of genetic towards phenotypic correlations resulted in least bias.",

keywords = "Quantitative Genetics (incl Disease and Trait Mapping Genetics), Animal Breeding",

author = "Karin Meyer and Mark Kirkpatrick and Daniel Gianola",

year = "2011",

language = "English",

isbn = "9780646559155",

volume = "19",

pages = "87--90",

editor = "William Pattie",

booktitle = "Proceedings of the Association for the Advancement of Animal Breeding and Genetics",

publisher = "Association for the Advancement of Animal Breeding and Genetics (AAABG)",

note = "AAABG 2011: 19th Conference of the Association for the Advancement of Animal Breeding and Genetics ; Conference date: 19-07-2011 Through 21-07-2011",

}

Meyer, K, Kirkpatrick, M & Gianola, D 2011, Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion. in W Pattie (ed.), Proceedings of the Association for the Advancement of Animal Breeding and Genetics. vol. 19, Association for the Advancement of Animal Breeding and Genetics (AAABG), Armidale, Australia, pp. 87-90, AAABG 2011: 19th Conference of the Association for the Advancement of Animal Breeding and Genetics, Perth, Australia, 19/07/11. <https://hdl.handle.net/1959.11/9871>

Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion. / Meyer, Karin; Kirkpatrick, Mark; Gianola, Daniel.
Proceedings of the Association for the Advancement of Animal Breeding and Genetics. ed. / William Pattie. Vol. 19 Armidale, Australia: Association for the Advancement of Animal Breeding and Genetics (AAABG), 2011. p. 87-90.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion

AU - Meyer, Karin

AU - Kirkpatrick, Mark

AU - Gianola, Daniel

PY - 2011

Y1 - 2011

N2 - A simulation study examining the effects of 'regularization' on estimates of genetic covariance matrices for small samples is presented. This is achieved by penalizing the likelihood, and three types of penalties are examined. It is shown that regularized estimation can substantially enhance the accuracy of estimates of genetic parameters. Penalties shrinking estimates of genetic covariances or correlations towards their phenotypic counterparts acted somewhat differently to those aimed reducing the spread of sample eigenvalues. While improvements of estimates were found to be comparable overall, shrinkage of genetic towards phenotypic correlations resulted in least bias.

AB - A simulation study examining the effects of 'regularization' on estimates of genetic covariance matrices for small samples is presented. This is achieved by penalizing the likelihood, and three types of penalties are examined. It is shown that regularized estimation can substantially enhance the accuracy of estimates of genetic parameters. Penalties shrinking estimates of genetic covariances or correlations towards their phenotypic counterparts acted somewhat differently to those aimed reducing the spread of sample eigenvalues. While improvements of estimates were found to be comparable overall, shrinkage of genetic towards phenotypic correlations resulted in least bias.

KW - Quantitative Genetics (incl Disease and Trait Mapping Genetics)

KW - Animal Breeding

UR - http://trove.nla.gov.au/work/162660639

UR - http://www.aaabg.org/aaabg19/

M3 - Conference contribution

SN - 9780646559155

VL - 19

SP - 87

EP - 90

BT - Proceedings of the Association for the Advancement of Animal Breeding and Genetics

A2 - Pattie, William

PB - Association for the Advancement of Animal Breeding and Genetics (AAABG)

CY - Armidale, Australia

T2 - AAABG 2011: 19th Conference of the Association for the Advancement of Animal Breeding and Genetics

Y2 - 19 July 2011 through 21 July 2011

ER -

Meyer K, Kirkpatrick M, Gianola D. Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion. In Pattie W, editor, Proceedings of the Association for the Advancement of Animal Breeding and Genetics. Vol. 19. Armidale, Australia: Association for the Advancement of Animal Breeding and Genetics (AAABG). 2011. p. 87-90

Penalized maximum likelihood estimates of genetic covariance matrices with shrinkage towards phenotypic dispersion

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this