[vsni.co.uk] Contact us
Author Message
Post new topic

  ASReml  ~  What is the ridge regression penalties in multitrait GBLUP

ZachHu
Posted: Mon Nov 20, 2017 1:46 am Reply with quote
Joined: 12 May 2017 Posts: 11
Dear Arthur,

Could you please introduce a bit about the ridge regression penalties in multi-trait GBLUP analysis in AsREML.

In Henderson's original paper 1973, the ridge regression penalty in single-trait analysis is

lambda = signma^2_e/sigma^2_beta

On the ridge regression penalties in mulit-trait GBLUP in asREML, does each trait have its own ridge regression penalty? For example, whether the penalty for the i'th trait is

lambda_i = signma^2_e_i/sigma^2_beta_i

Thank you very much for the help.

Regards,

Zach
View user's profile Send private message
Arthur
Posted: Thu Nov 30, 2017 10:42 am Reply with quote
Joined: 05 Aug 2008 Posts: 471 Location: Orange, NSW
Dear Zach,

The logical extension of ridge regression to multiple traits involves matrices for error and genotype since traits are not independent. If they were independent, then yo would analyse them independently and could specify different parameters for each.

Ridge regression is essential BLUP analysis with (assumed) known variances.

_________________
Arthur Gilmour

Retired Principal Research Scientist (Biometrics)
View user's profile Send private message Send e-mail Visit poster's website
ZachHu
Posted: Mon Dec 04, 2017 3:50 pm Reply with quote
Joined: 12 May 2017 Posts: 11
Thanks Arthur.
Arthur wrote:
Dear Zach,

The logical extension of ridge regression to multiple traits involves matrices for error and genotype since traits are not independent. If they were independent, then yo would analyse them independently and could specify different parameters for each.

Ridge regression is essential BLUP analysis with (assumed) known variances.
View user's profile Send private message

Display posts from previous:  

All times are GMT
Page 1 of 1
Post new topic

Jump to:  

You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
You can attach files in this forum
You can download files in this forum