mfm: Find a sample representative of a given population by...

In AlexisDerumigny/MFunctMatching: Subsample Selection by Multifunctional Matching

Description

Find a sample representative of a given population by multifunctional matching

Usage

mfm(
  data,
  listfns,
  listinputs,
  coordX = NULL,
  coordY = NULL,
  minDistance = 0,
  nDraws,
  sizeSample,
  methodNormalization,
  weightsfns = NULL,
  progressBar = TRUE
)

Arguments

data	the dataframe to use
listfns	the list of functionals
listinputs	the list of inputs, where each input is a vector of columns corresponding to each functional
coordX	the vector of X-coordinates
coordY	the vector of Y-coordinates
minDistance	minimum distance between two observations of the selected sample
nDraws	the number of random samples to generate from the population
sizeSample	the size of the sample
methodNormalization	the method used for normalization. Can be ecdf for normalization by the empirical cumulative distribution function or meansd for the normalization (X-E[X])/sd(X).
weightsfns	weights for each of the functionals. These weights can be used to give more or less importance to some of the functionals. It should be a vector of the same length as the listfns.
progressBar	TRUE: display a progressbar

Value

a list with two elements

• sample: the optimal set of (indices) of observations representing best the population.

• crit: the value of the MFM criteria.

Examples

# matching the first mean of a two-dimensional dataset
df = data.frame(rnorm(2000), rnorm(2000))
mfm(data = df, listfns = list(mean), listinputs = list(1),
    nDraws = 500, sizeSample = 10, methodNormalization = "ecdf")

AlexisDerumigny/MFunctMatching documentation built on Dec. 31, 2020, 9:47 a.m.