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

  ASReml  ~  is it possible to get a negative reliability for some cases

Zhiqiang
Posted: Wed Nov 29, 2017 11:47 pm Reply with quote
Joined: 07 Dec 2014 Posts: 12
Dear all,

I am using the prediction error variance(PEV) to estimate the reliability for animal model.
Based on the book (Mrode 2014), reliability= 1-prediction error variance(PEV)/additive variance. Originally, I thought the minimum value would be zero, but I got some negative values for some individuals without phenotypic values.

Is it possible to get a negative value in ASReml?


Cheers
Zhiqiang
View user's profile Send private message
Arthur
Posted: Thu Nov 30, 2017 10:37 am Reply with quote
Joined: 05 Aug 2008 Posts: 471 Location: Orange, NSW
Dear Zhigiang,

The expression given in the ASReml Guide (search accuracy) inflates the divisor according to inbreeding.

Maybe you are ignoring that component.

I expect it would be possible to get a negative value but unusual.

_________________
Arthur Gilmour

Retired Principal Research Scientist (Biometrics)
View user's profile Send private message Send e-mail Visit poster's website
Zhiqiang
Posted: Sat Dec 02, 2017 7:56 pm Reply with quote
Joined: 07 Dec 2014 Posts: 12
Dear Arthur,

you are right. I missed the inbreeding part in denominator.

Cheers
Zhiqiang
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