Chapter 17

Binomial and
Geometric
Distributions
 Binomial Distribution B(n,p)
• Each trial results is one of two mutually
exclusive outcomes. (success/failure)
• There are a fixed number of trials
• Outcomes of different trials are
independent (or sample is smaller than
10% of the population)
• The probability that a trial results in
success is the same for all trials
• The binomial random variable x is
defined as the number of successes out
of the fixed number
Are these binomial distributions?
1) Toss a coin 10 times and count the
number of heads
Yes
2) Deal 10 cards from a shuffled deck
and count the number of red cards
No, probability does not remain constant
3) Two parents with genes for O and A
blood types and count the number of
children with blood type O
No, no fixed number
Toss 3 coins and count the number of
heads

Find the discrete probability distribution

X 0 1 2 3
P(x) .125 .375 .375 .125

Out of 3 coins that are tossed, what is

the probability of getting exactly 2 heads?
Binomial Formula:

n  k
P (x  k )    p 1  p  n k
k
 
Where:

n 
 n C k
k 
Out of 3 coins that are tossed,
Must see
whatthisis the
work. I probability of
getting exactly
will take off
EACH
2 heads?
problem if I
don’t see it

3 2
P (x  2)   0.5  0.5  .375
1

2
The number of inaccurate gauges in a
group of four is a binomial random
variable. If the probability of a defect
is 0.1, what is the probability that only
1 is defective?
4 1
  3
P (x  1)   0.1 0.9  .2916
 
1 
More than 1 is defective?

P (x  1)  1  (P (0)  P (1))  .0523

Calculator
• Binomialpdf(n,p,x) – this calculates
the probability of a single binomial
P(x = k)

• Binomialcdf(n,p,x) – this calculates

the cumulative probabilities from
P(0) to P(k) OR P(X < k)
 A genetic trait of one family
manifests itself in 25% of the
offspring. If eight offspring are
randomly selected, find the
probability that the trait will
appear in exactly three of them.
P (X  3)  binomialpd f (8,.25,3)  .2076

At least 5?
P (X  5)  1  binomialcd f (8,.25,4)  .0273
In a certain county, 30% of the
voters are Republicans. If ten
voters are selected at random,
find the probability that no more
than six of them will be
Republicans.
P(x < 6) = binomcdf(10,.3,6) = .9894
What is the probability that at least 7
are not Republicans?
P(x > 7) = 1 - binomcdf(10,.7,6) = .6496
Binomial formulas for mean
and standard deviation
This is on

 x  np formula
sheet

 x  np 1  p 
In a certain county, 30% of the
voters are Republicans. How
many Republicans would you expect
in ten randomly selected voters?
What is the standard deviation for
this distribution?
 x  10(.3)  3 Republicans
 x  10(.3)(.7)  1.45 Republicans
•In L1 – seq(x,x,0,10)
•In L2 – binompdf(10, .1 ,L1)
•Sketch histogram on board
What happened to the
shape of the distribution
as the probability of
success increased?
As the probability of success
increases, the shape changes from
being skewed right to symmetrical
at p =.5 to skewed left.
•Calculate the mean and standard
deviations for each of the
probabilities
What do you notice?
As the probability of success increase,
•the means increase.
•the standard deviations increase to p = .5, then
decrease. Their values are also symmetrical.
 Binomial Distribution

A Binomial model is
approximately normal if we
http://homepage.stat.uiowa.edu/~mbo
expect at least 10 successes and
gnar/applets/bin.html 10 failures.
np ≥ 10 AND nq ≥10
What happens as we (Must SHOW!!)
increase sample size?
Geometric Distributions:
• There are two mutually exclusive
outcomes How far will So what are the
this go?
To infinity
possible values of X
• Each trial is independent of the
others
• The probability of success remains
constant for each trial.
• The random variable x is the number
X trials
of 1 UNTIL
2 3the4FIRST . . success
.
occurs.
Differences between binomial
& geometric distributions

• The difference between

binomial and geometric
properties is that there is
NOT a fixed number of
trials in geometric
distributions!
Other differences:

•Binomial random variables

start with 0 while geometric
random variables start with 1
•Binomial distributions are
finite, while geometric
distributions are infinite
Geometric Formulas:

P (x )  p  1  p  x 1

1 Not on formula
x  sheet – they will
p
not be given on
1p quiz or test
x 
p 2
Count the number of boys in a
family of four children.
What are the
Binomial: values for these
X 0 1 2 3 4 random
variables?
Count children until first son
is born
Geometric:

X 1 2 3 4 . . .
Calculator
• geometpdf(p,x) – finds the
geometric probability for P(X = k)
No “n” because
there is no
• Geometcdf(p,x)
fixed– number!
finds the
cumulative probability for P(X < k)
What is the probability that the
first son is the fourth child born?
P (X  4)  geometricpdf (.5,4)  .0625
What is the probability that the first
son born is at most the fourth child?
P (X  4)  geometriccdf (.5,4)  .9375
What is the probability that the first
son born is at least the third child?
P (X  3)  1  geometriccdf (.5,2)  .25
A real estate agent shows a house to
prospective buyers. The probability that
the house will be sold to the person is
35%. What is the probability that the
agent will sell the house to the third
person she shows it to?
P (x  3)  geometricpdf (.35,3)  .1479
How many prospective buyers does she
expect to show the house to before
someone buys the house? SD?
1 1  .35
x   2.86 buyers  x   2.304 buyers
.35 .35 2
•In L1 – input the x-values
•In L2 – geometpdf(.1 ,L1)
•Sketch histogram on board
What happened to the
shape of the distribution
as the probability of
success increased?

As the probability of success

increases, the shape becomes more
& more strongly skewed right
•Calculate the mean and standard
deviations for each of the probabilities
What do you notice?
As the probability of success increase,
•the means decrease
•the standard deviations decrease.
•http://www.personal.psu.edu/dpl14/java/proba
bility/geometric/index.html