Geometric Distribution
Waiting for the First Success
Choose and state the convention
Let X be the trial number of the first success. Then X=1,2,... and P(X=k)=(1-p)^(k-1)p: k-1 failures followed by one success. The survival probability is P(X>k)=(1-p)^k, the mean is 1/p, and the variance is Var(X)=(1-p)/p2, meaning (1-p) divided by p squared.
For example, when p=0.40, the probability that the first success occurs on trial 4 is 0.6 cubed times 0.4 = 0.0864. The chance of needing more than 4 trials is 0.6 to the fourth = 0.1296.
Memorylessness means that after observed failures, the remaining wait has the same distribution if p stays fixed and trials remain independent. It does not mean failures make success due. Another convention counts failures before success and starts at zero; state which variable is used.
Independent trials each have success probability p=0.20. Let X be the trial number of the first success. What is E(X)?
Mark Yourself Question
- Grab a piece of paper and try this problem yourself.
- When you're done, check the "I have answered this question" box below.
- View the solution and report whether you got it right or wrong.
A component passes inspection independently with probability 0.65. Find the probability that the first pass occurs after the fourth component is tested.