Links

F. Husson website





Book Exploratory Multivariate Analysis Using R

Outline

Introduction

Principal Component Analysis

Correspondence Analysis

Multiple Correspondence Analysis

Clustering

Multiple Factor Analysis

To conclude

Forum

Quiz 4 on Mutiple Correspondence Analysis: Interpretation aids

Q1) The inertia of an axis (tick the true statement(s))
is equal to the mean of the correlation ratios between the axis and the qualitative variables
is equal to the mean of the squared correlation ratios between the axis and the qualitative variables
is always less than 1/J, where J is the number of variables

Q2) Suppose we perform an MCA on a table with 10 rows and 2 variables. The squares of the correlation ratios between the variables and factors are the following:
coord var
What is the value of the second eigenvalue?

0.5
1
2
we cannot calculate the values with the given informations

Q3) The quantitative variables (tick the true statement(s))
can only be used as supplementary variables
can be divided up into classes if we want to treat them as active variables
are represented on a correlation plot
are represented on a plot with the categories

Q4) Burt tables and complete disjunctive tables (tick the true statement(s))
Burt tables match pairs of variables against each other, in terms of their categories
Burt tables can be used to do CA
The eigenvalues of a factor analysis applied to a Burt table are always between 0 and 1
The eigenvalues of a factor analysis applied to a Burt table are larger than (or equal to) those from a factor analysis applied to the corresponding complete disjunctive table
The percentage of inertia given in the first dimension of a factor analysis applied to a Burt table is larger than that of a factor analysis of the corresponding complete disjunctive table

Score =
Correct answers: