# Optional results for Multiple Correspondence Analysis

## Indicator table

Each indicator variable (column of the worksheet) corresponds with a level (category) of each categorical variable. An observation (row) has a 1 in columns that correspond to levels that are true for this observation and a 0 otherwise. An indicator table (also called a disjunctive matrix) has one column for each level (category) of each categorical variable.

For example, consider the following 3 categorical variables: Gender (male, female), Hair color (blond, brown, black), and Age (under 20, from 20 to 50, over 50), arranged in this order in an indicator Table. These data have 2 + 3 + 3 = 8 columns in the indicator table. The row for a female with blond hair who is 40 years old is 0 1 1 0 0 0 1 0. The row for a male with black hair who is 15 years old is 1 0 0 0 1 1 0 0. For more information, go to Indicator table.

## Burt table

A Burt matrix is a symmetric matrix which has one column and one row for each level (category) of each categorical variable. The entry in row i and column j is the number of observations that have the level corresponding to row i and also the level corresponding to column j. The Burt table is the result of the inner product of the indicator matrix. More specifically, if X is the indicator matrix then the corresponding Burt matrix is X'X.

Suppose there are 3 categorical variables: Gender (male, female), Hair color (blond, brown, black), and Age (under 20, from 20 to 50, over 50), arranged in the rows and columns of the Burt table in that order. Then the Burt table will have 2 + 3 + 3 = 8 rows and 8 columns. The entry in row 1 and column 1 is the number of observations that are male in both row and column, which is the number of males in the data set. The entry in row 1 and column 2 is the number of observations that are both male and female, which is 0. The entry in row 1 and column 3 is the number of observations that are both males and have blond hair, and so on.