How to build a frequency table
- List each distinct value once, in order.
- Count how many times each appears: that is the frequency f. The frequencies add up to n.
- Divide each f by n for the relative frequency. These add up to 1 (100%).
- Add the frequencies row by row for the cumulative frequency; the final row equals n.
Relative frequency as probability
Relative frequency is the experimental probability of each value: if a die lands on 6 in 9 of 50 rolls, the relative frequency of 6 is 0.18. With more trials it settles towards the theoretical probability (1/6 ≈ 0.167 for a fair die), which is the law of large numbers. For theoretical probabilities, see the probability calculator.
Frequently asked questions
What is the difference between frequency and relative frequency?
Frequency is a count (how many times). Relative frequency is that count divided by the total, so it is a proportion between 0 and 1 or a percentage.
Do relative frequencies always add up to 1?
Yes, apart from small rounding differences, because every observation is counted in exactly one row.
What is cumulative relative frequency used for?
It tells you the share of data at or below a value, which is the idea behind percentiles and the ogive (cumulative frequency graph).