MANOVA-methods: Methods for Function MANOVA in Package `MAINT.Data'

Description

Performs MANOVA tests based on likelihood ratios allowing for both homocedastic and heterocedastic setups

Usage

MANOVA(Idt, grouping, Model="Normal", Config=1:5,
			SelCrit=c("AIC","BIC"), Mxt=c("Hom","Het"), tol=1.0e-4)

Arguments

Idt

An IData object representing NObs interval-valued entities

grouping

Factor indicating the group to which each observation belongs to

Model

The joint distribution assumed for the MidPoint and LogRanges; currently, only Gaussian (Normal) distributions are implemented

Config

Configuration of the variance-covariance matrix: a vector of integers between 1 and 5

SelCrit

The model selection criterion

Mxt

Indicates whether we consider an homocedastic ("Hom") or a hetereocedasic ("Het") model configuration

tol

Tolerance level for the standard deviation of non-constant variables. When a MidPoint or LogRange has a within-groups standard deviation below tol, it is considered to be a constant

Value

Methods

signature(Idt = "IData"): Performs MANOVA tests on interval-valued data

Examples

Run this code


# Create an Interval-Data object containing the intervals for 899 observations 
# on the temperatures by quarter in 60 Chinese meteorological stations.
ChinaT <- IData(ChinaTemp[1:8],VarNames=c("T1","T2","T3","T4"))

#MANOVA tests, assuming that one of C3, C4 or C5 restricted configurations holds

#Classical (homocedastic) MANOVA tests
ManvChina <- MANOVA(ChinaT,ChinaTemp$GeoReg,Config=3:5)
cat("China, MANOVA by geografical regions results =\n") 
print(ManvChina)

#Heterocedastic MANOVA tests
HetManvChina <- MANOVA(ChinaT,ChinaTemp$GeoReg,Mxt="Het",Config=3:5)
cat("China, heterocedastic MANOVA by geografical regions results =\n") 
print(HetManvChina)