chapter 5: discrete probability...
TRANSCRIPT
FAROUQ ALAM, Ph.D.
Department of Statistics, KAU
Textbook:
Bluman, A. G. (2016). Elementary Statistics a Step by Step Approach. McGraw-Hill Education. Customized edition for the Department of Statistics at King Abdulaziz University, pp. 258 – 309
Chapter 5: Discrete Probability Distributions
5 – 1: Probability Distributions
A random variable is a variable whose values are
determined by chance.
A discrete probability distribution consists of the
values a random variable can assume and the
corresponding probabilities of the values. The
probabilities are determined theoretically or by
observation.
Example 5 – 1: Rolling a Die
The probability distribution for rolling a single
die is:
Outcomes
X
1 2 3 4 5 6
Probability
P(X)
1/6 1/6 1/6 1/6 1/6 1/6
The random variable and its values
The probabilities of the values of the
random variable
Example 5 – 2: Tossing Coins
Find the probability distribution of the number
of heads when tossing three coins.
Solution: If X represents the number of heads,
then X = 0 (no heads), 1 (one head), 2 (two
heads), 3 (three heads).
Example 5 – 2 (cont.)
Sample space:
TTT, HTT, THT, TTH, HHT, HTH, THH, HHH
X = 0 means TTT; hence, P(X = 0) = 1/8.
X = 1 means HTT, THT, or TTH; hence, P(X = 1)
= 1/8 + 1/8 + 1/8 = 3/8.
X = 2 means HHT, HTH, or THH; hence, P(X =
2) = 1/8 + 1/8 + 1/8 = 3/8.
X = 3 means HHH; hence, P(X = 3) = 1/8.
Example 5 – 2 (cont.)
The probability distribution of the number of
heads when tossing three coins is:
Number of
heads X
0 1 2 3 Total
Probability
P(X)
1/8 3/8 3/8 1/8 8/8
= 1
Extra example:Example 5 – 3 (Page 260-261)
Two Requirements for a Probability
Distribution
Requirement #1:
0 ≤ 𝑃 𝑋 ≤ 1, ∀𝑋
Requirement #2:
∑𝑃 𝑋 = 1
Example 5 – 4: Probability Distributions
Determine whether each distribution is a probability
distribution.
(a)
(b)
X 5 8 11 14
P(X) 0.2 0.6 0.1 0.3
Not a probability
distribution!
X 1 2 3 4 5
P(X) 1/4 1/8 3/8 1/8 1/8
A probability
distribution!
Example 5 – 4 (cont.)
(c)
(d)
X -1 2 3 4
P(X) ¼ ¼ ¼ ¼
A probability
distribution!
X 4 8 12
P(X) -0.5 0.6 0.4
Not a probability
distribution!
5 – 2: Mean, Variance, Standard
Deviation, and Expectation
Mean (expected value) of X:
𝜇 = 𝐸 𝑋 = ∑𝑋 ⋅ 𝑃(𝑋)
Variance of X:
𝜎2 = ∑𝑋2 ⋅ 𝑃 𝑋 − 𝜇2
Standard Deviation of X:
𝜎 = 𝜎2 = ∑𝑋2 ⋅ 𝑃 𝑋 − 𝜇2
Example 5 – 5 and 5 – 9: Rolling a Die
Find the missing value K, mean, variance, and
standard deviation of the number of spots that
appear when a die is tossed.
𝑿 1 2 3 4 5 6
𝑃(𝑋) 1/6 K 1/6 1/6 1/6 1/6
Example 5 – 5 and 5 – 9 (cont.)
𝑿 1 2 3 4 5 6 ∑
𝑃(𝑋) 1/6 1/6 1/6 1/6 1/6 1/6 1
𝑋 ⋅ 𝑃(𝑋) 1/6 2/6 3/6 4/6 5/6 6/6 21/6
𝑋2 ⋅ 𝑃(𝑋) 1/6 4/6 9/6 16/6 25/6 36/6 91/6
The mean (expected value):
𝜇 = 𝐸 𝑋 = ∑𝑋 ⋅ 𝑃 𝑋 =𝟐𝟏
𝟔= 𝟑. 𝟓
Example 5 – 5 and 5 – 9 (cont.)
The variance:
𝜎2 = ∑𝑋2 ⋅ 𝑃 𝑋 − 𝜇2 =𝟗𝟏
𝟔−
𝟐𝟏
𝟔
2
=91
6−441
36
=546 − 441
36=𝟏𝟎𝟓
𝟑𝟔= 𝟐. 𝟗𝟏𝟕
The standard deviation:
𝜎 = 2.917 ≈ 𝟏. 𝟕𝟎𝟖
The Expected value of X
The expected value E(X) of a discrete random
variable X of a probability distribution is the
theoretical average of the variable.
Example 5 – 14: Bond Investment
A financial adviser suggests that his client select one
of two types of bonds in which to invest $5000.
Bond A pays a return of 4% and has a default
rate of 2%. Bond B has a return 2.5% and a
default rate of 1%. Find the expected rate of
return and decide which bond would be a better
investment. When the bond defaults, the investor
loses all the investment.
Example 5 – 14 (cont.)
Bond A:
E(X) = $96
Win Lose
X $200 -$5000
𝑃(𝑋) 0.98 0.02
𝑋 ⋅ 𝑃(𝑋) 196 -100
Example 5 – 14 (cont.)
Bond B:
E(X) = $73.75
Win Lose
X $125 -$5000
𝑃(𝑋) 0.99 0.01
𝑋 ⋅ 𝑃(𝑋) 123.75 -50
Other examples
Mean: Examples 5 – 6, 5 – 7, and 5 – 8.
Variance and standard deviation: Examples 5 –
10, and 5 – 11.
Expected value: Example 5 – 12.
5 – 3: The binomial distribution
A binomial experiment is a probability experiment that
satisfies the following four requirements:
1. There must be a fixed number of trials.
2. Each trial can have only two outcomes or outcomes
that can be reduced to two outcomes. These
outcomes can be considered as either success or
failure.
3. The outcomes of each trial must be independent of
one another.
4. The probability of a success must remain the same
for each trial.
Example 5 – 15
Decide whether each experiment is a binomial
experiment:
Selecting 20 university students and recording their class
rank.
This is not a binomial experiment because we have
more than two outcomes.
Example 5 – 15 (cont.)
Selecting 20 university students and recording their
gender.
This is a binomial experiment since all four
requirements are met.
Selecting 5 cards without replacement and recording
whether they are red or black cards.
This is not a binomial experiment because the
outcomes of each trial are not independent.
Example 5 – 15 (cont.)
Selecting five students from a large school and asking if
they are on the dean’s list.
This is a binomial experiment since all four
requirements are met.
Recording the number of children in 50 randomly selected
families.
This is not a binomial experiment because we have more
than two outcomes.
The binomial distribution
The outcomes of a binomial experiment and the corresponding probabilities of these outcomes are called a binomial distribution.
In a binomial experiment, the probability of exactly X successes in n trials is:
𝑃 𝑋 =𝑛!
𝑛 − 𝑋 ! 𝑋!𝑝𝑋𝑞𝑛−𝑋
Important note: 𝑝 + 𝑞 = 1, 0 ≤ 𝑝, 𝑞 ≤ 1
The binomial distribution (cont.)
Notation Meaning
𝑛 The number of trials
𝑋The number of successes in 𝑛 trials
𝑋 = 0,1, … , 𝑛
𝑝 The probability of success
𝑞 The probability of failure
Example 5 – 18: Survey on Employment
A survey from Teenage Research Unlimited (Northbrook, Illinois) found that 30% of teenage consumers receive their spending money from part-time jobs. If 5 teenagers are selected at random, find the probability that:
Exactly 3 of them will have part-time jobs.
At most 3 of them will have part-time jobs.
At least 3 of them will have part-time jobs.
Solution: Notice that n = 5, p = 0.30, and q = 0.70.
Example 5 – 18 (cont.)
𝑃 0 =5!
5−0 !0!0.3 0 0.7 5−0 ≈ 0.168
𝑃 1 =5!
5−1 !1!0.3 1 0.7 5−1 ≈ 0.360
𝑃 2 =5!
5−2 !2!0.3 2 0.7 5−2 ≈ 0.309
𝑃 3 =5!
5−3 !3!0.3 3 0.7 5−3 ≈ 0.132
𝑃 4 =5!
5−4 !4!0.3 4 0.7 5−4 ≈ 0.028
𝑃 5 =5!
5−5 !5!0.3 5 0.7 5−5 ≈ 0.002
Example 5 – 18 (cont.)
Exactly 3 of them will have part-time jobs:
𝑃 3 ≈ 0.132
At most 3 of them will have part-time jobs:
𝑃 At most 3 of them will have part − time jobs= 𝑃 3 +⋯+ 𝑃 0 ≈ 0.132 + 0.309 + 0.360 + 0.168= 0.969
At least 3 of them will have part-time jobs.
𝑃 At least 3 of them will have part − time jobs= 𝑃 3 + 𝑃 4 + 𝑃 5 ≈ 0.132 + 0.028 + 0.002 = 0.162
Mean, Variance, and Standard Deviation
for the binomial distribution
The mean:
𝜇 = 𝑛 ⋅ 𝑝
The variance:
𝜎2 = 𝑛 ⋅ 𝑝 ⋅ 𝑞
The standard deviation:
𝜎 = 𝜎2 = 𝑛 ⋅ 𝑝 ⋅ 𝑞
Example 5 – 22: Tossing a Coin
A coin is tossed 4 times. Find the mean, variance, and standard deviation of the number of heads that will be obtained.
Solution: First, the probability of getting a head is ½; therefore, p = ½ and q = ½. Second, the coin is tossed four times, so n = 4. Hence,
𝜇 = 4 ⋅1
2= 2, 𝜎2 = 4 ⋅
1
2⋅1
2= 1, 𝜎 = 1 = 1
Other examples
The binomial distribution: Examples 5 – 16, and 5
– 17.
Mean, variance and standard deviation for the
binomial distribution: Examples 5 – 23, and 5 –
24.