Probability Distributions - Oxford University Press
Probability Distributions - Oxford University Press
Probability Distributions - Oxford University Press
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
226 Business Statistics Using Excel<br />
❉ Interpretation We can see from Excel that the binomial and Poisson distributions<br />
provide approximately equal results, 45.92% and 46.28% respectively.<br />
The degree of agreement between the binomial and Poisson probability distributions<br />
for this problem can be observed in Figure 5.43. They virtually overlap.<br />
P(X = r)<br />
0.35<br />
0.3<br />
0.25<br />
0.2<br />
0.15<br />
0.1<br />
0.05<br />
0<br />
Comparison between binomial and Poisson<br />
distributions<br />
0 5 10<br />
X<br />
Note The solution process is as follows:<br />
15<br />
Binomial<br />
Poisson<br />
Figure 5.43<br />
1. Binomial Solution: P(less than 2 rotten) = P(X < 2) = P(X = 0) + P(X = 1).<br />
− −<br />
( ) 0<br />
1<br />
0 60<br />
1 59<br />
0 ( ) ( ) 1(<br />
) ( )<br />
60 0 600 60 1 601 60<br />
60<br />
PX< 2 = C pq + Cpq = C 0.3 0.97 + C 0.3 0.97<br />
P( X< 2)=<br />
0. 1608 + 0. 2984 = 0. 4592<br />
2. Poisson Solution: P(less than 2 rotten) = P(X < 2) = P(X = 0) + P(X = 1). Since n is large and<br />
p is small we can use the Poisson distribution. To check we will see if the mean and the<br />
variance of the distribution are equal: Mean = np = 60 * 0.03 = 1.8, Variance = npq = 60 *<br />
0.03 * 0.97 = 1.746. Comparing the two values we see that they are approximately equal<br />
and the binomial distribution can be approximated using the Poisson distribution:<br />
0 −1.8 1 −1.8<br />
1.8 e 1.8e<br />
P( X< 2)<br />
= + = 0. 1652 + 0. 2975=<br />
0. 4627<br />
0! 1!<br />
Table 5.15 compares the two solutions:<br />
Problem Binomial Poisson<br />
P(X < 2) 0.4592 0.4627<br />
Table 5.15