pime.error.prediction: Error prediction

In microEcology/pime: Prevalence Interval for Microbiome Evaluation

Description

For each prevalence interval it randomizes the samples labels into arbitrary groupings using n random permutations (user defined). For each, randomized and prevalence filtered, dataset the OOB error rate is calculated to estimate whether the original differences in groups of samples occur by chance. Results are in a list containing a table and a boxplot summarizing the results.

Usage

pime.error.prediction(physeq, variable, bootstrap, max.prev,
  parallel = TRUE)

Arguments

physeq	Input in phyloseq format, original data, pime.prevalence unfiltered
variable	Variable to run the model, to be randomized
bootstrap	Number to run randomizations
max.prev	Max prevalence reached with pime.prevalence()
parallel	Whether or not to run in parallel. Default is TRUE

Examples

phylist=pime.split.by.variable(restroom, "Environment")
prev=pime.prevalence(phylist)
pime.best.prevalence(prev, "Environment")
set.seed(42)
result=pime.error.prediction(restroom, "Environment", bootstrap=10, max.prev=90, parallel=TRUE)
result$Plot
result$'Results table'

microEcology/pime documentation built on Nov. 13, 2019, 11:16 p.m.