How to calculate relative frequency
Relative frequency is how often a value occurs as a share of all observations. Divide the count for the category by the total number of observations, then multiply by 100 for a percent. For a frequency of 5 out of a total of 20, the relative frequency is 5 ÷ 20 × 100 = 25%. Over enough trials a relative frequency settles down towards the theoretical figure given by the probability calculator.
How to use this calculator
Enter the count for one category as the frequency and the total number of observations. The big result is the percentage share, and the badge shows the decimal fraction. The total must be greater than zero. For a value at a given rank, see the percentile calculator.
The total means every observation in the data set, not just the ones in other categories, so the frequency can never exceed it. If a category count is larger than the total, one of the two figures has been entered incorrectly.
Relative frequency in tables
In a frequency table, the relative frequencies of all categories add up to 100%. They turn raw counts into proportions, which makes data sets of different sizes comparable. To measure association between two variables, see the correlation coefficient calculator.
Frequently asked questions
- How do I calculate relative frequency?
- Divide the category's count by the total number of observations and multiply by 100. A frequency of 5 out of 20 gives 25%.
- What is the difference between frequency and relative frequency?
- Frequency is the raw count; relative frequency expresses that count as a fraction or percentage of the total.
- Do all relative frequencies add up to 100%?
- Yes. Across all categories in a data set, the relative frequencies sum to 1 (or 100%).
- Why can't the total be zero?
- Relative frequency divides by the total, and division by zero is undefined, so the total must be greater than zero.
- Is relative frequency the same as probability?
- Not quite. Relative frequency is what was actually observed in a sample, while probability is the underlying long-run chance. The two converge as the number of observations grows, which is why relative frequency is used to estimate probabilities empirically.