You are on page 1of 2

Department of Biotechnology

BBP 112 – Statistics for life sciences


Ref.: BBP 112/A-3
Discrete distributions

Binomial distribution

1. If two carriers of the gene for albinism marry, each of their children has probability 1/4 of being albino. The
chance that the second child is albino is the same (1/4) whether or not the first child is albino; similarly, the outcome for
the third child is independent of the first two, and so on. Using the labels “success” for albino and “failure” for
nonalbino, the independent-trials model applies with p = 1/4 and n = the number of children in the family.
The binomial distribution specifies the probabilities of various numbers of successes and failures when the basic chance
operation consists on n independent trails. Before giving the general formula for the binomial distribution, we consider a
simple example.
Suppose two carriers of the genes for albinism marry and have two children. Then the probability that both of their
children are albino is
 1  1   1 
Pr(both children are albino) =    =  
 4  4   16 
The reason for this probability can be seen by considering the relative frequency interpretation of probability. Of a great
many such families with two children, ¼ would have the first child albino; furthermore, ¼ of these would have the
second child albino; thus, ¼ of ¼ or 1/16 of all the couples would have both albino children. A similar kind of reasoning
shows that the probability that both children are not albino is
 3  3  9
Pr (both children are not albino )   =
 4  4  16
A new twist enters if we consider the probability that one child is albino and the other is not. There are two possible
ways this can happen:
 1  3  3
Pr ( first child is albino , sec ond is not ) =    =
 4  4  16
 3  1  3
Pr( first child is not albino, sec ond is ) =    =
 4  4  16
To see how to combine these possibilities, we again consider the relative frequency interpretation of probability. Of a
great many such families with two children, the fraction of families with one albino and one nonalbino child would be
the total of the two possibilities or
 3  3  6
 +  = 
 16   16   16 

Pr(one child is albino, the other is not) =


6
Thus, the corresponding probability is
16

The Binomial Distribution Formula


The same problem can be solved by using the Binomial distribution model
Pr (x; n, p )
n!
= n
Cx
x! (n − x )!
2. A study of cats in Omaha, Nebraska, found the 37% of them have a certain mutant trait. Suppose that 37% of
all cats have this mutant trait and that a random sample of cats in chosen from the population. As each cat is
chosen for the sample, the probability is 0.37 that it will be mutant. This probability is the same as each cat is
chosen, regardless of the results of the other cats, because the percentage of mutants in the large population
remains equal to 0.37 even when a few individual cats have been removed. Using the labels “success” for
mutant and “failure” for nonmutant, the independent-trails model applies with p = 0.37 and n = the sample
size.
Suppose we draw a random sample of five individuals from a large population in which 37% of the individuals
are mutants. The probabilities of the various possible samples are then given by the binomial distribution
formula with n =5 and = 0.37. Compute the probabilities and draw the probability mass function for x = 0 to 5.

3. In a large Drosophila population, 30% of the flies are black (B) and 70% are grey (G). Suppose two flies are
randomly chosen from the population. The binomial distribution with n = 2 and p= 0.3 gives probabilities for
the possible outcomes. Compute the probabilities and draw the probability mass function for x = 0 to 5.

The Poisson Distribution

4. In a study of drug-induced anaphylaxis among patients taking rocuronium bromide as part of their anesthesia,
Laake and Røttinges found that the occurrence of anaphylaxis followed a Poisson model with ƛ =12 incidents
per year in Norway. Find the probability that in the next year, among patients receiving rocuronium, exactly
three will experience anaphylaxis.
e −12 12 3
P( X = 3) = = 0.0177
3!

5. Refer to Problem 4. What is the probability that at least three patients in the next year will experience
anaphylaxis is administered with anesthesia ?

We can use the concept of complementary events in this case. Since


P(X ≤ 2) is the complement of P(X ≥ 3), we have

P(X ≥ 3) = 1 - P(X ≤ 2) = 1 – [P(X=0) + P(X = 1) + P(X=2)]


 e 12 0 e12 12 1 e −12 12 2 
−12
= 1−  + + 
 0! 1! 2! 
= 1 – [.00000614 + .00007373 + .00044238]
= 1 - .00052225
= .99947775

6. In the study of certain aquatic organism, a large number of samples were taken from a pond, and the number of
organisms in each sample was counted. The average number of organisms per sample was found to be two.
Assuming that the number of organisms follows a Poisson distribution, find the probability that the next
sample taken will contain one or fewer organisms.

That is, P(X ≤ 1) = 0.406

6.1 Refer to Problem 6. Find the probability that the next sample taken will contain exactly three organisms.
P(X = 3) = 0.180

6.2 Refer to Problem 6.1. Find the probability that the next sample taken will contain more than five organisms.

Since the set of more than five organisms does not include five, we are asking for the probability that six or
more organisms will be observed. This is obtained by subtracting the probability of observing five or fewer
from one. That is ,

P(X > 5 ) = P(X ≤ 5) = 1 - 0.983 = 0.017

You might also like