How to Create a Contingency Table in R

---

A contingency table (sometimes called “crosstabs”) is a type of table that summarizes the relationship between two categorical variables.

Fortunately it’s easy to create a contingency table for variables in R by using the pivot table function. This tutorial shows an example of how to do so.

Example: Contingency Table in R

Suppose we have the following dataset that shows information for 20 different product orders, including the type of product purchased along with the country that the product was purchased in:

#create data
df rep(c('TV', 'Radio', 'Computer'), times=c(9, 6, 5)),
                 country=rep(c('A', 'B', 'C', 'D'), times=5))

#view data
df

   order_num  product country
1          1       TV       A
2          2       TV       B
3          3       TV       C
4          4       TV       D
5          5       TV       A
6          6       TV       B
7          7       TV       C
8          8       TV       D
9          9       TV       A
10        10    Radio       B
11        11    Radio       C
12        12    Radio       D
13        13    Radio       A
14        14    Radio       B
15        15    Radio       C
16        16 Computer       D
17        17 Computer       A
18        18 Computer       B
19        19 Computer       C
20        20 Computer       D

To create a contingency table, we can simply use the table() function and provide the variables product and country as the arguments:

#create contingency table
table #view contingency table
table

           A B C D
  Computer 1 1 1 2
  Radio    1 2 2 1
  TV       3 2 2 2

We can also use the addmargins() function to add margins to the table:

#add margins to contingency table
table_w_margins #view contingency table
table_w_margins

            A  B  C  D Sum
  Computer  1  1  1  2   5
  Radio     1  2  2  1   6
  TV        3  2  2  2   9
  Sum       5  5  5  5  20

Here is how to interpret the table:

• The value in the bottom right corner shows the total number of products ordered: 20.
• The values along the right side show the row sums: A total of 5 computers were ordered, 6 radios were ordered, and 9 TV’s were ordered.
• The values along the bottom of the table show the column sums: A total of 5 products were ordered from country A, 5 from country B, 5 from country C, and 5 from country D.
• The values inside the table show the number of specific products ordered from each country: 1 computer from country A, 1 radio from country A, 3 TV’s from country A, etc.

Additional Resources

How to Average Across Columns in R
How to Sum Specific Columns in R
How to Calculate the Mean of Multiple Columns in R