mean_comparisons performs mean comparisons from object coming from check_model.fit_model_bh_GxE

# S3 method for check_model_bh_GxE
mean_comparisons(x, parameter, alpha = 0.05,
  type = 1, get.at.least.X.groups = 2, precision = 5e-04,
  threshold = 1, p.adj = "soft.bonf", ...)

Arguments

x

outputs from check_model.fit_model_bh_GxE

parameter

parameter on which the mean comparison is done. The possible values are "alpha", "beta" and "theta"

alpha

level of type one error. 0.05 (5%) by default

type

type of comparisons

  • type = 1 for comparison two by two

  • type = 2 for comparison to a specific threshold

get.at.least.X.groups

For type = 1. If there are only one group with alpha, the minimum number of groups wanted with a higher type one error (i.e. lower confidence). If NULL, nothing is done.

precision

For type = 1. The precision of the alpha with the correspondong groups from get.at.least.X.groups. The smaller the better, but the smaller the more time consuming due to computing matters

threshold

For type = 2. The threshold to which a parameter is different

p.adj

For all except type = 2. NULL for no adjustement of the type one error. p.adj can be "soft.bonf".

p.adj = "soft.bonf" for a soft bonferonni correction to take into account multiple comparisons (alpha / nb of parameters).. The comparisons is based on the probability of having a common distribution for each pair of parameter. When there is only one group with the value of alpha, the function (via get.at.least.X.groups argument) returns at least X groups with a new value of alpha.

...

further arguments passed to or from other methods#'

Value

A list of two elements:

  • mean.comparisons: a dataframe with the following columns : parameter, median, groups, number of groups, alpha (type one error), alpha.correction (correction used), entry, environment, location and year.

  • Mpvalue : a square matrix with pvalue computed for each pair of parameter.

Details

S3 method. For more details, see in the book : https://priviere.github.io/PPBstats_book/intro-agro.html#section-bayes

See also