12.07.2015 Views

Fundamentals of Probability and Statistics for Engineers

Fundamentals of Probability and Statistics for Engineers

Fundamentals of Probability and Statistics for Engineers

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

Some Important Discrete Distributions 165The moments <strong>and</strong> distribution <strong>of</strong> X can be easily found by using Equation(6.10). Sinceit follows from Equation (4.38) thatEfX j gˆ0…q†‡1…p† ˆp; j ˆ 1; 2; ...; n;EfXg ˆp ‡ p ‡‡p ˆ np;…6:11†which is in agreement with the corresponding expression in Equations (6.8).Similarly, its variance, characteristic function, <strong>and</strong> pmf are easily found followingour discussion in Section 4.4 concerning sums <strong>of</strong> independent r<strong>and</strong>omvariables.We have seen binomial distributions in Example 3.5 (page 52), Example 3.9(page 64), <strong>and</strong> Example 4.11 (page 96). Its applications in other areas arefurther illustrated by the following additional examples.Example 6.1. Problem: a homeowner has just installed 20 light bulbs in a newhome. Suppose that each has a probability 0.2 <strong>of</strong> functioning more than threemonths. What is the probability that at least five <strong>of</strong> these function more thanthree months? What is the average number <strong>of</strong> bulbs the homeowner has toreplace in three months?Answer: it is reasonable to assume that the light bulbs per<strong>for</strong>m independently.If X is the number <strong>of</strong> bulbs functioning more than three months(success), it has a binomial distribution with n ˆ 20 <strong>and</strong> p ˆ 0:2. The answerto the first question is thus given byX 20kˆ5p X …k† ˆ1ˆ 1ˆ 1X 4kˆ0X 4kˆ0p X …k† 20…0:2† k …0:8† 20kk…0:012 ‡ 0:058 ‡ 0:137 ‡ 0:205 ‡ 0:218† ˆ0:37:The average number <strong>of</strong> replacements is20 EfXg ˆ20 np ˆ 20 20…0:2† ˆ16:Example 6.2. Suppose that three telephone users use the same number <strong>and</strong>that we are interested in estimating the probability that more than one will useit at the same time. If independence <strong>of</strong> telephone habit is assumed, the probability<strong>of</strong> exactly k persons requiring use <strong>of</strong> the telephone at the same time isgiven by the mass function p X (k) associated with the binomial distribution. LetTLFeBOOK

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!