Contingency Tables > Expected Frequency
What is Expected Frequency?
The expected frequency is a probability count that appears in contingency table calculations including the chi-square test. Expected frequencies also used to calculate standardized residuals, where the expected count is subtracted from the observed count in the numerator.
- Observed Frequencies are counts made from experimental data. In other words, you actually observe the data happening and take measurements. For example, you roll a die ten times and then count how many times each number is rolled. The count is made after the experiment.
- Expected Frequencies are counts calculated using probability theory. For example, before you roll a six-sided die, you calculate the probability of any one number being rolled as 1/6.
How to Calculate Expected Frequency by Hand
Expected frequencies are calculated for each cell in a contingency table. So if you have, say, 16 cells, you’ll need to perform the steps 16 times (one for each cell). The formula to calculate expected frequency is:
Tip: You can think of this equation more simply as (row total * column total) / grand total.
Sample question: What are the expected cell frequencies for the following table?
Step 1: Find Ti = total in the ith row. The first cell is in the first row (i=1), which has a total of 114.
Set this number aside for a moment.
Step 3: Find N, or the total number of participants/items in the experiment. In a contingency table, this is usually done for you and is tallied up in the bottom right-hand corner. For this example, the total number of participants is 173.
Step 5: Repeat Steps 1 through 4 for each of the other cells.
The solutions for the remaining cells are:
- Cell 2 (top right) = (114 * 71) / /173 = 48.786
- Cell 3 (bottom left) = (59 * 102) / 173 = 34.786
- Cell 4 (bottom right) = (59 * 71) / 173 = 24.214.
If you prefer an online interactive environment to learn R and statistics, this free R Tutorial by Datacamp is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try this Statistics with R track.Comments? Need to post a correction? Please post on our Facebook page.