hqa: Combination of Qualitative Harmonic and Multiple Factor...

Description Usage Arguments Details Value Author(s) References Examples

Description

It realizes the combination between two methods for the processing of longitudinal categorical data: the Qualitative Harmonic and the Multiple Factorial Analysis.

Usage

1
2
3
hqa(base, conteos=FALSE, units=NULL, durat=FALSE, periodos=NULL, pesos = NULL,
    ilustra=NULL,ilustc = NULL,ilust.type = NULL, nfact=5, nfcl=5, k.clust=NULL, 
    combinat=TRUE, vector, tableclass=FALSE, clasifica=TRUE)

Arguments

base

object of type data frame or matrix

conteos

TRUE if you want to do data frame ID,MOD,DURATION. Default TRUE

units

time: "secs", "mins", "hours", "days", "weeks", "months", "years". Default = NULL

durat

TRUE if you want to calculate the DURATION by the function. Default FALSE

periodos

a vector containing the duration of each period of time

pesos

a vector of row weights

ilustra

object of type data frame or matrix with the illustrative variables. Default NULL

ilustc

a vector containing the number of variables in each ilustrative group

ilust.type

the type of variable in each ilustrative group: "c" for quantitative variables, "s" for quantitative variables scales to unit variance, "n" for qualitative variables. By default all variables are qualitative

nfact

number of axes to use into the factorial analysis . Default nfact=5

nfcl

number of axes to use in the classification. Default nfcl=5

k.clust

number of classes to work. Default k.clust= NULL

combinat

TRUE if you want to do combination HQA and MFA, FALSE if you want to do only AAC. Default TRUE)

vector

a vector containing the number of categories for each fuzzy variable

tableclass

TRUE if you want a function to Suggest you the number of axes to use in the classificacion. Default FALSE

clasifica

TRUE if you want to do the classificacion. Default TRUE

Details

A new statistical methodology is proposed in order to analyze longitudinal categorical data. This methodology considers the use of two methods: Qualitative Harmonic and Multiple Factor Analysis. The analysis is complemented by an analysis of classification using the first coordinates factoriales of the data.

Value

HQA

An object of type dudi or MFA

Clases

An object of class "kmeans"

Active

characterization of the classes considering the longitudinal active variable

Ilust

characterization of the classes considering the ilustratives variables

Author(s)

Martha Lucia Corrales <martha.corrales@usa.edu.co> & Campo Elias Pardo <cepardot@unal.edu.co>

References

Corrales, M. L., & Pardo, C. E. (2015). Analisis de datos longitudinales cualitativos con analisis de correspondencias y clasificacion. Comunicaciones en Estadistica, 8(1), 11-32. http://dx.doi.org/10.15332/s2027-3355.2015.0001.01

Examples

1
2
3
4
5
6
7
#data(ratingTV)
#rating <- hqa(base=ratingTV$tab,ilustra=ratingTV$ilus, #vector=c(15,15,15,15,15,15), ilustc=c(4))
#10
#rating$HQA
#rating$Clases
#rating$Active
#rating$Ilust

Example output

Loading required package: ade4
Loading required package: FactoClass
Loading required package: xtable
Loading required package: scatterplot3d
Loading required package: KernSmooth
KernSmooth 2.23 loaded
Copyright M. P. Wand 1997-2009
Loading required package: FactoMineR

Attaching package: 'FactoMineR'

The following object is masked from 'package:ade4':

    reconst

qha documentation built on May 2, 2019, 1:44 p.m.

Related to hqa in qha...