Probability and Statistics

LECTURE 4
RANDOM VARIABLES
AND PROBABILITY DISTRIBUTIONS

Adapted from http://www.prenhall.com/mcclave

OUTLINE

1. Random variables
2. Discrete probability distribution
3. Binomial distribution
4. Continuous probability distribution
5. Normal distribution

4-2
RANDOM VARIABLES

 Random variable
 A variable that assumes numerical values associated
with the outcomes of a random experiment
 Example: Number of Heads in 2 Coin Tosses

 Two types
 Discrete random variables
 Continuous random variables

4-3
RANDOM VARIABLES
 Discrete Random Variables
 Obtained by Counting (Values of a random variable
can be listed)
 Usually Finite Number of Values
 Poisson Random Variable Is Exception ()

4-4
RANDOM VARIABLES

 Continuous Random Variable

 Obtained by Measuring
 Infinite Number of Values in Interval
 Too Many to List Like Discrete Variable

4-5
DISCRETE RANDOM VARIABLE EXAMPLES

Experiment Random Possible

Variable Values

Make 100 Sales Calls # Sales 0, 1, 2, ..., 100

Inspect 70 Radios # Defective 0, 1, 2, ..., 70

Answer 33 Questions # Correct 0, 1, 2, ..., 33

Count Cars at Toll # Cars 0, 1, 2, ..., 

Between 11:00 & 1:00 Arriving
4-6
CONTINUOUS RANDOM VARIABLE EXAMPLES

Experiment Random Possible

Variable Values
Weigh 100 People Weight 45.1, 78, ...

Measure Part Life Hours 900, 875.9, ...

Ask Food Spending Spending 54.12, 42, ...

Measure Time Inter-Arrival 0, 1.3, 2.78, ...

Between Arrivals Time

4-7
DISCRETE PROBABILITY DISTRIBUTION

1. A graph, table or formula that lists all possible

[x, p(x)] pairs
 x = Value of Random Variable
 p(x) = Probability Associated with Value
2. Mutually Exclusive (No Overlap)
3. Collectively Exhaustive (Nothing Left Out)
4. 0  p(x)  1
5.  p(x) = 1

4-8
DISCRETE PROBABILITY DISTRIBUTION EXAMPLE

Experiment: Toss 2 Coins. Count # Tails.

Probability Distribution
Values, x Probabilities, p(x)
0 1/4 = .25
1 2/4 = .50
2 1/4 = .25

© 1984-1994 T/Maker Co.

4-9
VISUALIZING DISCRETE PROBABILITY
DISTRIBUTIONS

Listing Table
{ (0, 0.25), (1, 0.50), (2, 0.25) } # Tails f(x) p(x)
Count
0 1 .25
1 2 .50
2 1 .25

p(x) Graph Equation

.50
n!
.25 p ( x)  p x (1  p) n  x
x !(n  x)!
.00 x
0 1 2
4 - 10
 SUMMARY MEASURES
1. Expected Value
 Mean of a random variable
 Weighted Average of All Possible Values
 𝜇 = 𝐸𝑋 = ∑𝑥𝑝 𝑥

2. Variance
 Weighted Average of Squared Deviation about Mean
 𝜎 2 = 𝐸 𝑋 − 𝜇 2 = ∑ 𝑥 − 𝜇 2𝑝 𝑥
= 𝐸 𝑋 2 − 𝐸𝑋 2 = ∑𝑥 2 𝑝 𝑥 − 𝜇2
3. Standard deviation

4 - 11
SUMMARY MEASURES CALCULATION TABLE

2
x p(x) x p(x ) x- (x -) (x -) p( x )
2

x p(x ) (x -) p( x )

2
Total

4 - 12
EXERCISE 1

You toss 2 coins. You’re

interested in the number of
tails. What are the
expected value &
standard deviation of
this random variable,
number of tails?

© 1984-1994 T/Maker Co.

4 - 13
SOLUTION

What is the value of the standard deviation?

2
x p(x) x p(x ) x- (x -) (x -) p( x )
2

0 .25 0 -1.00 1.00 .25

1 .50 .50 0 0 0
2 .25 .50 1.00 1.00 .25
 = 1.0  = .50
2

How do we interpret the expected value and

standard deviation?
4 - 14
 BINOMIAL PROBABILITY DISTRIBUTION

A discrete probability distribution with many

applications.

4 - 15
BINOMIAL EXPERIMENT

1. Sequence of n identical trials

2. Each trial has 2 outcomes:
 ‘Success’ (Desired Outcome)
 or ‘Failure’
3. Constant trial probability (of success)
4. Trials are independent

4 - 16
BINOMIAL RANDOM VARIABLE

 Binomial random variable is number of ‘successes’

in the n trials of a binomial experiment.
Notation: X ~ B(n, p)
 Is binomial random variable discrete or continuous?
 Example:

4 - 17
BINOMIAL PROBABILITY FUNCTION

𝒏 𝒙 𝒏−𝒙
𝒏!
𝒑 𝒙 = 𝒑 𝟏−𝒑 = 𝒑𝒙 𝟏 − 𝒑 𝒏−𝒙
𝒙 𝒙! 𝒏 − 𝒙 !
n = number of trials
x = number of successes
p = probability of a success on one trial
p(x) = probability of x successes in n trials

4 - 18
EXAMPLE

Experiment: Toss 1 Fair Coin 5 Times in a Row.

Note # Tails.
What’s the Probability of 3 Tails?

4 - 19
 SOLUTION

4 - 20
BINOMIAL DISTRIBUTION CHARACTERISTICS

Mean P(X)
n = 5 p = 0.1
1.0
  E ( X )  np .5
.0 X
0 1 2 3 4 5
Standard Deviation

  np(1  p) P(X) n = 5 p = 0.5

.6
.4
.2
.0 X
0 1 2 3 4 5
4 - 21
 BINOMIAL PROBABILITY TABLE

Table 5 in your textbook shows binomial

probabilities for each value of X.
For example, if n = 15, p = 0.3 and you want to find
P(x = 5). Look within Table 5, find n = 15, p = 0.3
and x = 5, the probability is 0.2061

4 - 22
EXERCISE 2

You’re a telemarketer selling

service contracts for Macy’s.
You’ve sold 20 in your last 100
calls (p = .20). If you call 15
people tonight,
what’s the probability of
a. No sales?

b. Exactly 2 sales?

c. At most 2 sales?

d. At least 2 sales?

4 - 23
SOLUTION
Using the Binomial Tables:
A. p(0) = .0352
B. p(2) = .2309
C. p(at most 2) = P(X  2) = p(0) + p(1) + p(2)
= .398
D. p(at least 2) = p(2) + p(3)...+ p(15)
= 1 - [p(0) + p(1)]
= 1 – 0.1671
= .8329

4 - 24
CONTINUOUS PROBABILITY DISTRIBUTION
Question:
Can we represent probability distributions for
continuous random variables the same way as for
discrete random variables?

4 - 25
 PROBABILITY DENSITY FUNCTION

1. f(x)  0 for all values of x Probability density

2. The area under the function
probability density function
f(x) over all values of the
random variable X within its f(x)
range, is equal to 1.0:

න 𝑓 𝑥 𝑑𝑥 = 1
𝐷 x

4 - 26
MEASURING PROBABILITY FOR CONTINUOUS
RANDOM VARIABLES

d
Probability Is Area P (c  x  d)  c f ( x ) dx
Under Curve!
f(x)

X
c d

© 1984-1994 T/Maker Co.

4 - 27
SMALL DISCUSSION

Suppose X is a continuous random variable, does

it make any difference if we write: P(a  X  b) or
P(a  X  b) or P(a  X  b) or P(a  X  b)?

4 - 28
EXERCISE 3
Let X be a random variable whose density function
is:
𝑐𝑥 2 1 − 𝑥 𝑖𝑓 𝑥 ∈ 0,1
𝑓 𝑥 =ቊ
0 𝑖𝑓 𝑥 ∉ [0,1]
a. Find the constant 𝑐?
b. Find 𝑃(0.4 < 𝑋 ≤ 0.6)?

4 - 29
NORMAL DISTRIBUTION
 Specific distribution having a characteristic bell-
shaped form.
 The most important continuous probability
distribution.
 Why normal distributions are important?

4 - 30
A (HYPOTHETICAL) EXAMPLE

Suppose we gather data about math scores of all 10th

graders in country A.
 Plot a histogram: see next slide.

 Histogram and smooth curve.

4 - 31
HISTOGRAM

4 - 32
NORMAL PROBABILITY DENSITY FUNCTION

1 (x μ)2 /2σ 2

f(x)  e
2π 2

4 - 33
NORMAL DISTRIBUTION

 Bell-shaped and symmetric

 Mean = median = mode

 A normal distribution is completely determined by µ

and 
 Notation:

X ~ N(μ,σ ) 2

4 - 34
MANY NORMAL DISTRIBUTIONS

f(X)
B

A C

4 - 35
FINDING PROBABILITIES OF NORMAL
RANDOM VARIABLES

 Probability of a single value

 Probability of X within an interval

 What if we try to table the normal distribution

probabilities?

4 - 36
STANDARDIZE THE NORMAL DISTRIBUTION

𝑋−𝜇
If X~𝑁 𝜇, 𝜎 2 𝑡ℎ𝑒𝑛 𝑍 = ~𝑁 0,1
𝜎

Normal Standard Normal

Distribution Distribution

= 1


 X =0 Z
4 - 37 Notation: Z ~ N(0,1)
EXAMPLE
Suppose X is normally distributed with mean = 5,
and standard deviation = 10, P(X < 13.3) = ?

4 - 38
OBTAINING THE PROBABILITY

Table 1 in Appendix B of your textbook

z .00 .01 .02 .03 .04 .05 .06 .07 .08 .09
. . . . . . . . . . .
.5 .6915 .6950 .6985 .7019 .7054 .7088 .7123 .7157 .7190 .7224
.6 .7257 .7291 .7324 .7357 .7389 .7422 .7454 .7486 .7517 .7549
.7 .7580 .7611 .7642 .7673 .7704 .7734 .7764 .7794 .7823 .7852
.8 .7881 .7910 .7939 .7967 .7995 .8023 .8051 .8078 .8106 .8133
.9 .8159 .8186 .8212 .8238 .8264 .8289 .8315 .8340 .8365 .8389
. . . . . . . . . . .

4 - 39
EXERCISE 4: P(3.8  X  5)=?

Normal
Distribution

 = 10

3.8 = 5 X

4 - 40
SOLUTION X   3.8  5
Z    .12
 10
P(3.8  X  5) = P(-0.12  Z  0)
Normal = P(Z < 0) – P(Z < -0.12)
Distribution

 = 10 =1

3.8 = 5 X -.12  = 0 Z

4 - 41 Shaded area exaggerated
EXERCISE 5: P(X  8)=?

Normal
Distribution
 = 10

=5 8 X

4 - 42
SELF-STUDY: FINDING Z VALUES FOR KNOWN
PROBABILITIES

What is z* given
P(Z < z*) = .7704?

What is z* given
P(Z > z*) = 0.1935

4 - 43
EXERCISE 6

You work in Quality Control for GE.

Light bulb lifetime has a normal
distribution with µ = 2000 hours & 𝝈 =
200 hours.
a. What’s the probability that a
randomly selected bulb will last
between 2000 & 2400 hours?
b. (Self-Study) Find the lifetime
range of the 5% most durable light
bulbs.

4 - 44
SOLUTION
2400−2000
a) 𝑍 = =2
2000

P(2000 < X < 2400) = P(0 < Z < 2) = 0.4772

b) Do it individually or in a group

4 - 45
CONCLUSION

1. Random variables
2. Discrete probability distribution
3. Binomial distribution
4. Continuous probability distribution
5. Normal distribution

4 - 46