check_model.fit_model_bh_GxE: Check if the Hierarchical Bayesian GxE model went well

In priviere/PPBstats: An R package to perform analysis found within PPB programmes

Description

check_model.fit_model_bh_GxE computes tests to assess if the model went well. It is important to run this step before going ahead with the analysis otherwise you may make mistakes in the interpretation of the results.

Usage

## S3 method for class 'fit_model_bh_GxE'
check_model(x)

Arguments

x	outputs from model_bh_GxE

Details

S3 method. The different test apply to the model are explained in the book here.

Value

It returns a list with the following elements:

• MCMC : a data fame resulting from the concatenation of the two MCMC for each parameter. (See details for more information).

• MCMC_conv_not_ok : a data fame resulting from the concatenation of the two MCMC for each parameter for environment where some parameters did not converge for mu and beta

• model2.presence.absence.matrix : a matrix germplasm x environment with the number of occurence in the data used for the model (i.e. with at least two germplasm by environments.)

• data_ggplot a list containing information for ggplot:

  • alpha

  • beta

  • theta

  • epsilon

Author(s)

Pierre Riviere

See Also

• check_model

• plot.check_model_bh_GxE

• mean_comparisons

• mean_comparisons.check_model_bh_GxE

• parameter_groups

• predict_the_past_model_bh_GxE

• cross_validation_model_bh_GxE

priviere/PPBstats documentation built on May 6, 2021, 1:20 a.m.