[prev in list] [next in list] [prev in thread] [next in thread] 

List:       r-sig-mixed-models
Subject:    Re: [R-sig-ME] Observation-level random effects
From:       David Duffy <David.Duffy () qimrberghofer ! edu ! au>
Date:       2021-04-13 6:51:09
Message-ID: a694364940f7414d865e008a986afa83 () qimrberghofer ! edu ! au
[Download RAW message or body]

Dear Shahin. I have attempted to fit the "animal model" for "development", =
treating each observation as a single offspring, with egg and Tank as fixed=
 effects (Tanks has 5 levels), and Cross as a RE. (These data are odd, with=
 development falling on just 26 values, and Tank 5 has  20 obs at 895.3, an=
d 2 x 901.1!). This was done in a couple of non-R genetics oriented LMM pac=
kages, incl Wombat (Karin Meyers' AI-REML package). This model still does n=
ot converge, but roughly Cross is 3/4 of the variance, and additive genetic=
 ~1/4, with residual variance small (driven by repeated parents). You will =
have to seek local statistical advice re priors for a Bayesian model in, sa=
y, MCMCglmm, or augment your data with other datasets for this organism.
________________________________________
From: Shahinur, Islam <shahinur.islam@mun.ca>
Sent: Monday, 12 April 2021 9:40:22 PM
To: David Duffy
Cc: Shahinur, Islam; Thierry Onkelinx; r-sig-mixed-models
Subject: Re: [R-sig-ME] Observation-level random effects

Hello David,

Thank you for the reply (also thanks to Thierry).

You are right- I was trying to see paternal (Male.ID; 42 levels out of 103 =
observations) and maternal (Female.ID; 53 levels out of 103 observations) c=
ontribution, but still getting boundary (singular) fit: see ?isSingular  er=
rors  for development.overall or for some of the other traits (response var=
iables).

Thanks,

Shahin

<><><><><><><><><><><><><><><><><><><><><><><><><><>

Shahinur S. Islam
PhD Candidate, Department of Ocean Sciences
Ocean Sciences Centre, Memorial University of Newfoundland
St. John's, NL  A1C 5S7, Canada
Cell: (+1)709-740-3324; Twitter: @EcoEvoGen


On Mon, Apr 12, 2021 at 4:03 AM David Duffy <David.Duffy@qimrberghofer.edu.=
au<mailto:David.Duffy@qimrberghofer.edu.au>> wrote:
> No, they are not the replicates of the same family, but 20 different
> families under Cross (Population) Farm.NA.

Dear Shahin.
Thierry has already answered your question, in that unless you provide a wi=
thin-family standard deviation for each
"development.overall" or "egg.size" observation, there is no information ab=
out familial random effects. You can examine paternal
and maternal contributions, since some of these are repeated across familie=
s (in your example data),
but you will not have a lot of power, I fear.





[EXTERNAL EMAIL] This message originates from an external email address, pl=
ease exercise caution when clicking any links or opening attachments. If yo=
u believe the sender is impersonating someone at QIMR Berghofer, please for=
ward this message to phishing@qimrberghofer.edu.au.

_______________________________________________
R-sig-mixed-models@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
[prev in list] [next in list] [prev in thread] [next in thread]