The 2010 American Community Survey estimates that 47.1% of women ages 15 years and over are married.
Assuming the probability of each woman being married is independent, let \(X\) be the random variable having a geometric distribution where \(X\) is the location of the first success.
\[P(X = k) = (1-p)^{k-1}p\] \[P(X = 3) = (1-0.471)^{3-1}(0.471) \approx 0.1318\]
dgeom(2, 0.471) ## note that the R function takes the number of failures (k-1) as its input ## [1] 0.1318051
Again assuming independence, the probability that all three women are married may be calculated with the general multiplication rule.
\[P(\text{all three are married}) = (0.471)(0.471)(0.471) \approx 0.1045\]
For a geometric distribution, the expected value is \(\frac{1}{p}\) and the standard deviation is \(\sqrt{\frac{1-p}{p^2}}\). Therefore:
\[\mu = \frac{1}{0.471} \approx 2.12\]
\[\sigma = \frac{1-0.471}{(0.471)^2} \approx 2.38\]
\[\mu = \frac{1}{0.30} \approx 3.33\]
\[\sigma = \frac{1-0.30}{(0.30)^2} \approx 7.78\]
For random variables with a geometric distribution, the mean wait time for the first success is (intuitively) longer for variables with smaller probability. The standard deviation is greater for the wait time of success as well.