soc.csa: Class Specific Multiple Correspondence Analysis

In soc.ca: Specific Correspondence Analysis for the Social Sciences

Description

soc.csa performs a class specific multiple correspondence analysis on a data.frame of factors, where cases are rows and columns are variables. Most descriptive and analytical functions that work for soc.mca, also work for soc.csa

Usage

soc.csa(object, class.indicator, sup = NULL)

Arguments

object	is a soc.ca class object created with soc.mca
class.indicator	the row indices of the class specific individuals
sup	Defines the supplementary modalities in a data.frame with rows of individuals and columns of factors, without NA's

Value

nd	Number of active dimensions
n.ind	The number of active individuals
n.mod	The number of active modalities
eigen	Eigenvectors
total.inertia	The sum of inertia
adj.inertia	A matrix with all active dimensions, adjusted and unadjusted inertias. See variance
freq.mod	Frequencies for the active modalities. See add.to.label
freq.sup	Frequencies for the supplementary modalities. See add.to.label
ctr.mod	A matrix with the contribution values of the active modalities per dimension. See contribution
ctr.ind	A matrix with the contribution values of the individuals per dimension.
cor.mod	The correlation or quality of each modality per dimension.
cor.ind	The correlation or quality of each individual per dimension.
mass.mod	The mass of each modality
coord.mod	A matrix with the principal coordinates of each active modality per dimension.
coord.ind	A matrix with the principal coordinates of each individual per dimension.
coord.sup	A matrix with the principal coordinates of each supplementary modality per dimension. Notice that the position of the supplementary modalities in class specific analysis is the mean point of the individuals, which is not directly comparable with the cloud of the active modalities.
indicator.matrix	A indicator matrix. See indicator
names.mod	The names of the active modalities
names.ind	The names of the individuals
names.sup	The names of the supplementary modalities
names.passive	The names of the passive modalities
modal	A matrix with the number of modalities per variable and their location
variable	A vector with the name of the variable for each of the active modalities
variable.sup	A vector with the name of the variable for each of the supplementary modalities
original.class.indicator	The class indicator
original.result	The original soc.ca object used for the CSA

Author(s)

Anton Grau Larsen, University of Copenhagen

Stefan Bastholm Andrade, University of Copenhagen

Christoph Ellersgaard, University of Copenhagen

References

Le Roux, B., og H. Rouanet. 2010. Multiple correspondence analysis. Thousand Oaks: Sage.

See Also

add.to.label, contribution

Examples

example(soc.ca)
class.age    <- which(taste$Age == '55-64')
res.csa      <- soc.csa(result, class.age)
res.csa

Example output

Loading required package: ggplot2

soc.ca> data(taste)

soc.ca> # Create a data frame of factors containing all the active variables 
soc.ca> taste          <- taste[which(taste$Isup == 'Active'), ]

soc.ca> attach(taste)

soc.ca> active         <- data.frame(TV, Film, Art, Eat)

soc.ca> sup            <- data.frame(Gender, Age, Income)

soc.ca> detach(taste)

soc.ca> # Runs the analysis
soc.ca> result         <- soc.mca(active, sup)
                     Class Specific Multiple Correspondence Analysis:                      
 
                    Statistics                                   Scree plot               
	Active dimensions:                            10  |  1.     44.7%   **********************
	Dimensions explaining 80% of inertia:          3  |  2.     24.0%   ************
	Active modalities:                            29  |  3.     14.4%   *******
	Supplementary modalities:                      0  |  4.      6.8%   ****
	Individuals:                                 183  |  5.      4.9%   **
	Share of passive mass:                         0  |  6.      2.3%   *
	Number of passive modalities:                  0  |  7.      1.7%   *

                    The 4 active variables: [No. modalities - share of variance]                    

             TV [8 - 28%]            Film [8 - 28%]             Art [7 - 24%] 
            Eat [6 - 20%]

soc.ca documentation built on Sept. 5, 2021, 5:21 p.m.