Bootstrap_test_prmtrc: Parametric bootstrap test of trait-environment assocation...

In CajoterBraak/TraitEnvMLMWA: Weighted Averaging (WA) and Multi-Level Methods (MLM) for Trait-Environment Association in Functional and Community Ecology

Parametric bootstrap test of trait-environment assocation using the MLM models

Description

Bootstrap_test_prmtrc performs a parametric bootstrap test on trait-environment interaction, starting from a fitted MLM3 object (or any other MLM object with the trait:env term as last fixed parameter).

Usage

Bootstrap_test_prmtrc(
  MLM3,
  test_stat = "Wald",
  nrepet = 19,
  Binomial_total = 0,
  nAGQ = 0
)

Arguments

MLM3	the fitted MLM3 object, created by glmer (lme4) or glmmTMB.
test_stat	choice of test statistic; 'Wald' (default), 'LRT' or 'both'. The default is quicker.
nrepet	number of bootstraps
Binomial_total	scalar, 0 for count-like data and the binomial total for logit models (1 for presence-absence).
nAGQ	integer scalar (default 0), used only for an object created by glmer

Details

The code assumes that the parameter for trait-environment interaction (trait:env) is the last fixed parameter in summary(MLM3). First, the formula of the null model is created by deleting the trait:env term from the formula of object MLM3 (the non-null model). Second, the null model (MLM0) is fitted. Three, sampling is from this null model. For each simulated data set, the model is refitted using the formula of the MLM3 object. The code works therefore also for MLM1 and MLM2, although their use is not recommended. See also Box A2 in Appendix A4 and Appendix A1.

Value

A named list,

p_values	the parametric and bootstrap p-values
MLM0	the fitted null model
obs	value of the test statistic(s)
nrepet	number of bootstraps
sim.boot	values of the test statistic(s) for the nrepet bootstrapped data
test_stat	the chosen test statistic(s)

References

ter Braak (2019) New robust weighted averaging- and model-based methods for assessing trait-environment relationships. Methods in Ecology and Evolution (https://doi.org/10.1111/2041-210X.13278)

See Also

expand4glmm.

Examples

## Not run: 
#use a precomputed MLM3 model, e.g. from the Revisit data
data("MLM3")
## or compute the MLM3 model from the data
# data("Revisit")
# formula.MLM3 <- y ~ poly(env,2) + poly(trait,2) +
 env : trait  + (1 + env|species) + (1 + trait| site)
# MLM3 <- glmmTMB(formula.MLM3, family = betabinomial,  data=Revisit)
summary(MLM3)
res_boot <- Bootstrap_test_prmtrc(MLM3, test_stat = "Wald", nrepet = nrepet, Binomial_total = 100)
names(res_boot)
round(res_boot$p_values,3)

## End(Not run)

CajoterBraak/TraitEnvMLMWA documentation built on Jan. 25, 2023, 7:36 p.m.