RarefactionStat: Non-Parametric rarefacted population samples and statistic...

In lem-usp/EvolQG: Evolutionary Quantitative Genetics

Non-Parametric rarefacted population samples and statistic comparison

Description

Calculates the repeatability of a statistic of the data, such as correlation or covariance matrix, via resampling with varying sample sizes, from 2 to the size of the original data.

Usage

RarefactionStat(
  ind.data,
  StatFunc,
  ComparisonFunc,
  ...,
  num.reps = 10,
  replace = FALSE,
  parallel = FALSE
)

Arguments

ind.data	Matrix of residuals or indiviual measurments
StatFunc	Function for calculating the statistic
ComparisonFunc	comparison function
...	Aditional arguments passed to ComparisonFunc
num.reps	number of populations sampled per sample size
replace	If true, samples are taken with replacement
parallel	if TRUE computations are done in parallel. Some foreach backend must be registered, like doParallel or doMC.

Details

Samples of various sizes, without replacement, are taken from the full population, a statistic calculated and compared to the full population statistic.

A specialized ploting function displays the results in publication quality.

Bootstraping may be misleading with very small sample sizes. Use with caution.

Value

returns the mean value of comparisons from samples to original statistic, for all sample sizes.

Author(s)

Diogo Melo, Guilherme Garcia

See Also

BootstrapRep

Examples

ind.data <- iris[1:50,1:4]

#Can be used to calculate any statistic via Rarefaction, not just comparisons
#Integration, for example:
results.R2 <- RarefactionStat(ind.data, cor, function(x, y) CalcR2(y), num.reps = 5)

#Easy access
library(reshape2)
melt(results.R2)

## Not run: 
#Multiple threads can be used with some foreach backend library, like doMC or doParallel
library(doMC)
registerDoMC(cores = 2)
results.R2 <- RarefactionStat(ind.data, cor, function(x, y) CalcR2(y), parallel = TRUE)

## End(Not run)

lem-usp/EvolQG documentation built on April 14, 2024, 6:21 a.m.