Download Binomial Distribution

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts
no text concepts found
Transcript
Binomial Distribution
The binomial distribution
discrete distribution.
is
a
Binomial Experiment
 A binomial experiment has the following properties:

experiment consists of n identical and independent trials

each trial results in one of two outcomes: success or failure
 P(success) = p
 P(failure) = q = 1 - p for all trials

The random variable of interest, X, is the number of successes
in the n trials.

X has a binomial distribution with parameters n and p
EXAMPLES
 A coin is flipped 10 times. Success = head.
 X =
n=
p=
 Twelve pregnant women selected at random, take a home
pregnancy test. Success = test says pregnant.
 X =
n=
p=?
 Random guessing on a multiple choice exam. 25 questions.
4 answers per question. Success = right answer.
 X =
n=
p=
Examples when assumptions do not hold
 Basketball player shoots ten free throws

Feedback affects independence and constant p
 Barrel contains 3 red apples and 4 green apples;
select 4 apples without replacement; X = # of red
apples.

Without replacement implies dependence
What is P(x) for binomial?
n!
x n− x
p q
P( x) =
x!(n − x)!
Mean and Standard Deviation
 The mean (expected value) of a binomial
random variable is µ = np
 The standard deviation of a binomial random
variable is σ = npq
Example
 Random Guessing; n = 100 questions.



Probability of correct guess; p = 1/4
Probability of wrong guess; q = 3/4
1
Expected Value = µ= np= 100  =
 25
4


 On average, you will get 25 right.
 Standard Deviation =
=
σ
=
npq
− p)
np (1=
 1  3 
100   =
 4.33
 4  4 
Example
 Cancer Treatment; n = 20 patients
 Probability of successful treatments; p = 0.7
 Probability of no success; q = ?
 Calculate the mean and standard deviation.
Normal Approximation
 For large n, the binomial distribution
can be approximated by the normal,
X − np
Z=
npq
is approximately standard normal for
large n.
Related documents