Frequency Table

What is a Frequency Table?

A frequency table is a table that shows how often each value or category of a variable occurs in a dataset. In statistics, the frequency of a value is simply the number of times it appears in the data. A frequency table provides a clear overview of the data, helps identify patterns, and makes it easy to compare categories. Because it shows how the frequencies are distributed across the categories, it is also called a frequency distribution table.

A frequency table for the variable 'gender' shows, for example, how often the categories 'male', 'female' and 'diverse' are represented in the sample.

A frequency table typically contains two key pieces of information: absolute frequencies and relative frequencies.

Depending on the context, categories may be people, companies, locations, or households.

Frequency tables are often used to get a first overview of the data. The result can then be displayed graphically in a bar chart.

Valid Percent

The difference between percent and valid percent is that the percent column is based on all cases, while the valid percent is calculated using only the valid cases, i.e. excluding missing values.

It is particularly important to pay attention to missing or invalid values when creating and interpreting frequency tables. In the field of survey research, missing values are usually found where people have answered with "no answer", "Can't say" or "Don't know". Reporting both the percentage and the valid percentage makes it clear whether missing values are included in the denominator.

How to calculate valid percent?

To calculate valid percent, the absolute frequencies of a characteristic must be divided by the total number of valid cases. If you have asked 30 people in a survey what their favorite car brand is and 7 have said "Don't know", then there are 23 valid cases. If 5 people have answered Ford, then the valid percentage is 5/23 = 21.7%.

Example for Valid Percent:

Let's assume that a Sunday poll is conducted asking, "Which party would you vote for if the election were next Sunday?" There might be some undecided respondents. In this case, both the overall percentages and valid percentages are important. The overall percentages, based on all respondents, show support for each party, including the undecided. In contrast, the valid percentages reflect the support among only those who have already made a decision.

How to Create a Frequency Table

To find the frequency of a value in statistics, you simply count how many times that value occurs in your data – there is no formula needed for the absolute frequency, counting is the calculation. For the percentage, you then divide this count by the total number of observations and multiply by 100.

First, you need a dataset, such as survey data, from which you want to calculate the frequency of a particular variable. For example, let's take the variable "gender" with the categories "male", "female" and "diverse" in a survey of 10 people.

Sample Dataset:

To calculate the absolute frequency, count how often each category (e.g., "male", "female", "diverse") appears in your dataset.

• male: 4 persons
• female: 5 persons
• diverse: 1 person

You calculate the relative frequency by dividing the absolute frequency by the total number of observations and multiplying by 100. The percentage frequency formula is therefore: percentage = (absolute frequency / total number of observations) × 100.

• male: (4/10) * 100 = 40%
• female: (5/10) * 100 = 50%
• diverse: (1/10) * 100 = 10%

If your dataset contains missing values (e.g., people who did not answer the question), you only use the valid responses for calculating the valid percentages. The missing values are ignored, so only the valid data is considered. In our example, there are no missing values, so the percentages and valid percentages are the same.

Now you can summarize all the values in a frequency table:

Example with Missing Values:

Suppose one person did not respond to the question about gender, leaving only 9 valid responses. The table would look like this:

In this case, the "Percentage" column is based on all 10 cases (including the missing values), while the "Valid Percentage" only considers the 9 valid responses.

Frequency Table Example

With the frequency table calculator from numiqo you can easily create frequency tables for your data. The procedure is now illustrated with an example:

In a statistics course the participants were asked which brand of car they drive.

That's how it works with numiqo: Simply copy the table into the descriptive statistics calculator and select the variable Car Brand. Now you can choose which values you want to calculate. The result of the frequency table now looks like this:

Finally, numiqo also automatically gives you a graphical visualization of the frequency distribution of car brand, here in the form of a bar chart:

If the variable is metric (e.g. age or income), the individual values are usually grouped into class intervals first – this is called a grouped frequency table. The frequencies are then displayed in a histogram instead of a bar chart.

Frequency Table APA Style

If you want to create a frequency table in APA format, you have to take the following into account:

An extension of frequency tables are crosstabs. In crosstabs, not only one but two variables are considered.