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 5 correspondence analysis: interpretation aids

We asked a group of tasters to associate words with 10 wines. The results were placed in a table putting the 9 words (groups of words here) up against the 10 wines. A CA of this table lead to the following results on the words.


Q1) What is the quality of representation of the word "Citrus" on the first factor plane?
15.040
0.836
-5.111
0.646

Q2) What is the total contribution of Fruity and Fruity flavour to the second factor axis?
36 %
0.626
7.5 %
we cannot calculate it

Q3) To help with interpretation, we decide to represent the row called Sum which corresponds to the total number of times each word was used (over all wines) as a supplementary variable. What is the coordinate value of this in the 1st dimension?
we have to calculate the sum of the coordinates of all the words
we cannot calculate it
0

Q4) How many eigenvalues are non-zero?
8
9
5
the number of rows plus the number of columns

Q5) On the 1st axis, the group of words "Sweet, smooth, syrupy" has its coordinate value closer to 0 than the group "light, supple". Even though it contributes more to construction of the 1st axis. Why? Select the correct reason or reasons.
Because the group "Sweet, smooth, syrupy" involves 3 words, while "light, supple" only 2.
Because the group "Sweet, smooth, syrupy" is mentioned many more times, so has a bigger weight in the analyses. It therefore contributes more to construction of the 1st axis.
Because its coordinate value is further out on the 2nd axis

Score =
Correct answers: