Part of the Math & Statistics suite · 235 calculators

Negative Binomial Distribution Calculator

How many trials it takes to reach a target number of successes — the distribution of waiting, rather than of counting.

The binomial fixes the trials and asks how many successes; the negative binomial fixes the successes and asks how many trials.

%
Results update as you type
Results
P(the rth success is on trial x)
6.039798%
P(done by trial x)
P(still going after trial x)
Expected trials needed
Standard deviation
Most likely trial number
Expected failures along the way
Reviewed September 2026. Pure mathematics: the result does not depend on where you are. Terminology follows US usage (math, parentheses, decimal point).
No account required · Google Analytics off unless allowedCalculator arithmetic runs in your browserResults update as you type
All calculations run 100% in your browser. The calculator code does not submit your figures to GlobalCalc to obtain a result.
About negative binomial distribution

How the negative binomial distribution calculator works

The binomial fixes the trials and asks how many successes; the negative binomial fixes the successes and asks how many trials. The chance that the rth success arrives on trial number x is C(x − 1, r − 1) pʳ (1 − p)^(x − r).

With r = 1 it collapses to the geometric distribution — the chance of the first success on trial x — which is why the calculator reports the expected wait as r ÷ p.

Formula: P(X = x) = C(x − 1, r − 1) pʳ (1 − p)^(x − r)

Worked examples

InputsP(the rth success is on trial x)Note
3rd success on trial 10 at 20%6.039798%about 6.0%
First success on trial 5 at 20%8.192%geometric — 8.19%
2 sixes by the 12th roll4.934893%about 5.4%

Frequently asked questions

How is this different from the binomial?

The binomial fixes the number of trials; the negative binomial fixes the number of successes and lets the trial count vary.

What is the geometric distribution?

The special case r = 1 — the wait for the first success.

How many rolls to see two sixes?

On average 12, since r/p = 2 ÷ (1/6). But the distribution has a long tail: about 11% of the time it takes more than 25.

Why "negative" binomial?

Because the probabilities come from expanding a binomial series with a negative exponent. The name is about the algebra, not the values.

Where is it used?

Modelling counts that are more variable than Poisson allows — insurance claims, defects, and read counts in genomics.

Where these figures come from

Last checked: September 2026. Formulas are fixed by mathematics and do not change with tax years or regulations.