khi2: khi2 test

In Rankcluster: Model-Based Clustering for Multivariate Partial Ranking Data

Description

This function computes the p-value of the khi2 adequation test (only for univariate data).

Usage

khi2(data, proportion, mu, pi, nBoot = 1000)

Arguments

data	a matrix in which each row is a rank of size m.
proportion	a vector (which sums to 1) containing the K mixture proportion.
mu	a matrix of size K*m, where m is the size of a rank, containing the modal rankings of the model (position parameters).
pi	a vector of size K, where K is the number of clusters, containing the probabilities of a good paired comparaison of the model (dispersion parameters).
nBoot	number of bootstrap iterations used to estimate the khi2 adequation test p-value.

Value

a real, the p-value of the khi2 adequation test.

Author(s)

Quentin Grimonprez

Examples

proportion  <- c(0.4, 0.6)
pi <- c(0.8, 0.75)
mu <- matrix(c(1, 2, 3, 4, 4, 2, 1, 3), nrow = 2, byrow = TRUE)
# simulate a data set with declared parameters.
data <- rbind(simulISR(proportion[1] * 100, pi[1], mu[1,]),
simulISR(proportion[2] * 100, pi[2], mu[2,]))
pval <- khi2(data, proportion, mu, pi)

Example output

WARNING : Since Rancluster 0.92, the ranks have to be given to the package in the ranking notation (see convertRank function), with the following convention :
- missing positions are replaced by 0
- tied are replaced by the lowest position they share

Rankcluster documentation built on Aug. 26, 2019, 3 p.m.