Overview

The geometric distribution answers 'how many tries until the first success?' when each try has the same chance, such as rolling until you get a six.

Enter the chance of success on each try and the trial number k.

Worked examples

InputsResult
Success Probability per Trial (%)22Trial Number (k)4P(first success on trial 4): 10.44%P(success within 4 trials): 62.98%
Show 2 more examples
Success Probability per Trial (%)16.67Trial Number (k)6P(first success on trial 6): 6.7%P(success within 6 trials): 66.52%
Success Probability per Trial (%)5Trial Number (k)20P(first success on trial 20): 1.89%P(success within 20 trials): 64.15%

P(first success on trial 4) by success probability per trial

With the calculator's starting values, the p(first success on trial 4) is 10.44%. The table shows how it changes with the success probability per trial.

Success Probability per Trial (%)P(first success on trial 4)
15%9.21%
20%10.24%
22%starting value10.44%
25%10.55%
30%10.29%

Other inputs: Trial Number: 4 k. Change them in the calculator above for your own numbers.

How it works

The first success lands exactly on trial k if the first k − 1 tries all fail and then one succeeds. The chance of success within k tries is 1 minus the chance of failing all k. The average number of tries needed is 1 ÷ p.

The formula

P(X = k) = (1 − p)^(k − 1) × p
pChance of success on each try
kTrial number

Practical tips

  • At 22% per try, the first success lands on try 4 with a 10.44% chance, and 62.98% of the time it has happened by then.
  • Rolling a six takes 6 tries on average, but there's still about a 33.5% chance you'll need more than 6.
  • Each try is independent, so a long losing run doesn't make the next success more likely.

Frequently asked questions

What is the expected number of trials?

1 ÷ p. At 22%, that's about 4.5 tries.

How many tries for a 90% chance?

Solve 1 − (1 − p)^k ≥ 0.9. For p = 0.22, k = 10.

Is this the same as the binomial distribution?

No. Binomial counts successes in a fixed number of tries. Geometric counts tries until the first success.