Posterior distribution of gebvs (or other parameters)

[jslate1]

Is it possible to output the MCMC estimates of gebvs every, e.g. 100th sample, of the MCMC chain? Sometimes it is useful to see the posterior distribution of each individual's gebv. I realise this would result in large files, and perhaps not everybody needs them, but it would be nice to have the option. Perhaps I missed it somewhere. This looks like a really nice package anyway - thank you!

[YinLiLin]

Thank you. Very nice suggestion. We will add this function in the next version, and once finished, i will leave you a message here.

[jslate1]

That sounds great - thank you 👍

[YinLiLin]

Hi, the latest version (1.1.0) on GitHub has been updated with the function of returning the MCMC estimates of all model parameters, it can be easily obtained from the list $MCMCsamples, taking individual-level Bayesian model for an example, the returned results are as follows:

> str(fit)
List of 10
 $ Vg         : num 3.91
 $ Ve         : num 24.9
 $ h2         : num 0.136
 $ mu         : num 0.405
 $ alpha      : num [1:7385, 1] 0.00 -3.17e-04 2.56e-04 -2.36e-05 0.00 ...
 $ pi         : num [1:2, 1] 0.99762 0.00238
 $ g          : num [1:4798] -2.98 -5.45 1.52 -2.34 -3.26 ...
 $ e          : num [1:4798] 0.527 -2.744 1.479 -8.43 3.317 ...
 $ pip        : num [1:7385, 1] 0.000125 0.0005 0.000625 0.0005 0.000375 ...
 $ MCMCsamples:List of 7
  ..$ Vg   : num [1, 1:400] 3.68 3.83 3.88 3.9 3.93 ...
  ..$ Ve   : num [1, 1:400] 25.3 24.6 24.5 24.3 25.4 ...
  ..$ h2   : num [1, 1:400] 0.127 0.135 0.137 0.138 0.134 ...
  ..$ mu   : num [1, 1:400] 0.4576 0.4069 0.4688 -0.0538 -0.0587 ...
  ..$ alpha: num [1:7385, 1:400] 0 0 0 0 0 0 0 0 0 0 ...
  ..$ pi   : num [1:2, 1:400] 0.99648 0.00352 0.99881 0.00119 0.99812 ...
  ..$ g    : num [1:4798, 1:400] -2.02 -6.15 1.51 -2.42 -2.28 ...

Please feel free to have a try. Thanks.

[jslate1]

That sounds great - thank you. I will give it a try.

Best regards Jon

Professor Jon Slate (he/him/his)
School of Biosciences
University of Sheffield
http://jon-slate.staff.shef.ac.uk
twitter: @jon_slate
Editor-in-Chief: Evolution Letters <http://www.evolutionletters.com>

I don't expect you to respond to my email outside your working hours. At the University of Sheffield we value and encourage flexible working. Please be assured that I respect your working patterns and look forward to your response when you are next at work.

On Wed, 6 Apr 2022 at 11:35, Lilin Yin @.***> wrote:

Hi, the latest version (1.1.0) on GitHub has been updated with the function of returning the MCMC estimates of all model parameters, it can be easily obtained from the list $MCMCsamples, taking individual-level Bayesian model for an example, the returned results are as follows:

str(fit)List of 10 $ Vg : num 3.91 $ Ve : num 24.9 $ h2 : num 0.136 $ mu : num 0.405 $ alpha : num [1:7385, 1] 0.00 -3.17e-04 2.56e-04 -2.36e-05 0.00 ... $ pi : num [1:2, 1] 0.99762 0.00238 $ g : num [1:4798] -2.98 -5.45 1.52 -2.34 -3.26 ... $ e : num [1:4798] 0.527 -2.744 1.479 -8.43 3.317 ... $ pip : num [1:7385, 1] 0.000125 0.0005 0.000625 0.0005 0.000375 ... $ MCMCsamples:List of 7 ..$ Vg : num [1, 1:400] 3.68 3.83 3.88 3.9 3.93 ... ..$ Ve : num [1, 1:400] 25.3 24.6 24.5 24.3 25.4 ... ..$ h2 : num [1, 1:400] 0.127 0.135 0.137 0.138 0.134 ... ..$ mu : num [1, 1:400] 0.4576 0.4069 0.4688 -0.0538 -0.0587 ... ..$ alpha: num [1:7385, 1:400] 0 0 0 0 0 0 0 0 0 0 ... ..$ pi : num [1:2, 1:400] 0.99648 0.00352 0.99881 0.00119 0.99812 ... ..$ g : num [1:4798, 1:400] -2.02 -6.15 1.51 -2.42 -2.28 ...

Please feel free to have a try. Thanks.

— Reply to this email directly, view it on GitHub https://github.com/YinLiLin/hibayes/issues/13#issuecomment-1090115340, or unsubscribe https://github.com/notifications/unsubscribe-auth/AC3QRC7EMBHOQKSNAZBIOM3VDVSH7ANCNFSM5PCVWK7A . You are receiving this because you authored the thread.Message ID: @.***>