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

  ASReml  ~  Estimation of reliability and seEffects

emheu
Posted: Thu Nov 12, 2015 5:10 pm Reply with quote
Joined: 25 Mar 2015 Posts: 5
Dear all,

I would like to estimate the reliability and afterwards the accuracy of my estimated Effects (BLUPS/BLUES) in the .sln file. In the file I can find the seEffect for my fixed and random effects. Can I then estimate the reliability with

r^2 = 1 - (SEP^2/sa^2)

where I use the seEffect from the .sln file as SEP (meaning standard error of prediction) and my genetic variance derived from the animal model as sa^2 (meaning genetic variance)?

Or differently asked: What is the seEffect exactly?

Thank you very much and have a nice day!
View user's profile Send private message
Arthur
Posted: Fri Nov 13, 2015 2:37 pm Reply with quote
Joined: 05 Aug 2008 Posts: 471 Location: Orange, NSW
Dear Sir,
SEP is the square root of the Prediction Error Variance.

Search for 'accuracy' in the User Guide.

_________________
Arthur Gilmour

Retired Principal Research Scientist (Biometrics)
View user's profile Send private message Send e-mail Visit poster's website
emheu
Posted: Fri Nov 13, 2015 3:47 pm Reply with quote
Joined: 25 Mar 2015 Posts: 5
Daar Mr. Gilmour,

thank you very much for your fast and helpful reply. Unfortunately an additional question came to my mind, and I hope is not as easy to find as the other one would have been. If I use a !LOGIT model in the analysis of a binary trait, do I have to count back the seEffect estimated for the variable or can I use it directly like that.

Thank you very much and have a nice weekend!
Kind regards,
emheu
View user's profile Send private message
Arthur
Posted: Sat Dec 12, 2015 2:07 am Reply with quote
Joined: 05 Aug 2008 Posts: 471 Location: Orange, NSW
The BINOMIAL LOGIT analysis is an analysis of a 'working variable' and so the BLUP obtained is that of the working variable, which is typically regarded as an 'underlying variable'. Provided you recognise that we are analysing this underlying variable, calculation of reliability just carries through.

_________________
Arthur Gilmour

Retired Principal Research Scientist (Biometrics)
View user's profile Send private message Send e-mail Visit poster's website

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