View source: R/defineModelsSpecifications.R
defineModelsSpecifications | R Documentation |
Return an object containing the specifications that can be used as in the argument "model_specifications" of the functions computeVariancePartition, computeCovariancePartition and computeVarianceCovariancePartition. See "MCMCglmm" R package documentation for further information.
defineModelsSpecifications(
number_iterations = 100,
burning = 10,
thinning = 2,
uniresponse_prior = list(R = list(V = 1, nu = 0.002), G = list(G1 = list(V = 1, nu =
0.002))),
biresponse_prior = list(R = list(V = diag(2)/2, nu = 2), G = list(G1 = list(V =
diag(2)/2, nu = 2))),
triresponse_prior = list(R = list(V = diag(3)/2, nu = 2), G = list(G1 = list(V =
diag(3)/2, nu = 2)))
)
number_iterations |
(integer) Number of iterations of the MCMCglmm model. |
burning |
(integer) Number of burning iterations. This initial iterations will be excluded from when estimating the posterior distribution. It allows achieving convergence. |
thinning |
(integer) Number of thinning iterations. Number of iterations that will be discarded after a sampled one. It allows to deal with autocorrelation. |
uniresponse_prior |
(list) Parameters for the random effects for uni-response models. Default is set to an inverse-Gamma distribution, which is canonical and considered non-informative. |
biresponse_prior |
(list) Parameters for the random effects of bi-response models. Normally, these are the models including two traits. Default is set to an inverse-Gamma distribution, which is canonical and considered non-informative. |
triresponse_prior |
(list) Parameters for the random effects of tri-response models. Normally, these are the models including two traits and one environmental variable. Default is set to an inverse-Gamma distribution, which is canonical and considered non-informative. |
List of mcmcglmm model specifications.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.