Random Variables

&
Probability Distributions
Mathematical Sciences Department
 Outcomes
1. Define a Random Variable - RV
2. Described Types of RVs
3. Defined a Probability Distribution - PD
Random Variables & Probability

4. State the Conditions of a PD

5. Calculate the Expectation & Variance of a PD
Distributions

6. Describe the properties of the Expectation of a PD

 Random Variable
 Toss two coins:
 Sample Space:
S = {HH, HT, TH, TT}
Random Variables & Probability

 Now, let X = Number of heads obtained

Distributions

Sample point HH HT TH TT
Assigned X value 2 1 1 0
 Mapping:  HH 
   0 X : S   0,1, 2
 HT   
 TH   1
   2 Random
 
 TT  Variable
 Random Variable cont…
 Dfn:
 A random variable is a function that associates each element
in a sample space with a real number i.e.
Random Variables & Probability

A r.v. is a function defined on a sample space that associates

real numbers to outcomes of an experiment.
A r.v. is a numerically valued function defined on a sample
Distributions

space and its value is determined by chance.

 Notation:
X denotes the random variable (or any upper case letter)
x denotes a value assumed by the rv (i.e. corresponding
lower case letter)
 Example
Let X be a r.v. representing the number of times the letter ‘e’
appears in a name. Evaluate x for each of the following names:
Mercy, Leshole, Hyacinta,
Random Variables & Probability

Rebeccah, Dumisan, and Subeda.

Distributions

Solution:
Name Mercy Leshole Hyacinta Rebeccah Dumisan Subeda
X=x 1 2 0 2 0 1
 Types of Random Variables
 Discrete R.V.:
A r.v. whose set of possible values is finite, x   x1 , x2 , ..., xn 
Values are obtained by counting and are clearly separate
Random Variables & Probability

E.g. number of children in a family, number of employees in a

department, number of defective items…
 Continuous R.V.:
Distributions

A r.v. whose set of possible values is infinite i.e. values in a

continuous interval,
Values are obtained by measuring
E.g. height, salary, age, time taken to serve a customer,
temperature…
 Discrete Probability Distribution
 Recall the tossing of two coins:
Represent the distribution of X=x on a frequency distribution:
Random Variables & Probability

X=x 0 1 2
Frequency, f 1 2 1
Probabilities
Relative freq, r.f. 1/4 1/2 1/4
Distributions

 The possible values of X with their probabilities are:

X=x 0 1 2
P(X=x) ¼ ½ ¼
Probability
Distribution
 Probability Distribution
 Dfn: Properties of a PD:
The probability distribution  A function f(x) is a PD of a
of a discrete rv is a listing of discrete rv X if:
Random Variables & Probability

all possible values of the rv, Probability of each outcome

x, and their corresponding lies between 0 and 1
probabilities.
Distributions

0  f ( x) 1 or 0  P ( X  x) 1

A probability distribution The sum of the probabilities

of all the individual
can be presented as a outcomes in the sample
table, a function, graph or space is 1
statement …  f ( x) 1
x
 Example
State whether each of these is a PD:
a) X=x 0 1 2
Yes
P(X=x) ¼ ½ ¼
Random Variables & Probability

b) Y=y 15 20 23 25 30
Yes
Distributions

f(y) 0.12 0.2 0.08 0.1 0.

5
c)
Weekly demand, X (ton) 5 12 14 17 19
No
f(x) 0.2 0.5 -0.2 0.25 0.25
  Activity
a) Construct a PD table for the number of heads observed when
three fair coins are tossed. Y=y 0 1 2 3
f(y) 1/8 3/8 3/8 1/8
Random Variables & Probability

b) The MUBAS EDO’s office reported the following information for

a sample of 250 cars parked on campus. Convert the table to a PD.
Distributions

Number of days parked 1 2 3 4 5 6 7 8

Frequency (cars) 20 38 53 45 40 13 5 36

X=x 1 2 3 4 5 6 7 8
f(x) 0.08 0.152 0.212 0.18 0.16 0.052 0.02 0.144
 Mean or Expectation of a Discrete RV
What are
 Recall the tossing of 3 coins: Review these?
 1  3  3  1
x 0    1    2    3  
X=x 0 1 2 3  8  8  8  8
Random Variables & Probability

f 1 3 3 1
Probabili
Find the mean of the ties
Distributions

distribution. Ans: 1.5 X=x 0 1 2 3

Mean: f(x) 1/8 3/8 3/8 1/8
x
 fx

0 1  1 3  2 3  3 1
f 8  x  xf  x 
x
Expectati
 1  3  3  1
0   1  2   3   on of x
 8  8  8  8
1.5
 Expectation
 Dfn:
If X is a discrete r.v. with probability distribution or probability
mass function f(x), then the expectation or expected value of
Random Variables & Probability

x is
E  X   xf  x  Alternative presentation
x
 X  E  X   xf  x 
Distributions

x

n
 X  E  X   xi f  xi 
i 1
 Variance and Standard Deviation
 Dfn:
If X is a discrete r.v. with probability distribution or probability
mass function f(x), then the variance of x is
Random Variables & Probability

2
  Recall from sem 1
Var  X   x f  x     xf  x 
2
2
x  x   fx 2
  fx 
Distributions

 2
 
  f 
f  
   
  E  X   E X 2   X 2
2
Var  X   E X 2

 xf  x 
NB: Var  X   X 2 x

Std Deviation,  X  Var  X   f x 

x
x
2

f(x) = Probability
of x
 Example
A random variable X has the following probability distribution
X 3 5 6 8
P(X = x) 0.4 0.5 0.03 0.07
Random Variables & Probability

Find:
Distributions

a) P(X = 6)
b) P(X > 5)
c) Var(X)
 Solution X 3 5 6 8
 a) P(X = 6)):
P(X = x) 0.4 0.5 0.03 0.07
P  X 6  0.03
 b) P(X > 5):
xP  x  1.2 2.5 0.18 0.56
x2 P x 
Random Variables & Probability

3.6 12.5 1.08 4.48

P ( X  5)  P (6)  P(8)
0.03  0.07 E  X  1.2  2.5  0.18  0.56
Distributions

0.1 4.44

 c) Var(X): E  X 2  3.6  12.5  1.08  4.48

Var  X  E  X 2    E  X 
2
21.66
E  X   xP  x  Var  X  21.66  4.442
1.9464
E  X 2   x P x 
2
 Example
A discrete r.v. Y has a pmf defined as
0.2, y 0
0.3, y 1

f  y  
Random Variables & Probability

0.1, 2  y 6

0, Otherwise
Distributions

Find:
a) f(5)
b) f(y < 4)
c) f(3 < y < 10)
d) E(Y) and Var(Y)
 0.2, y 0
Solution 0.3,
 y 1
f  y  
 a) f(5): 0.1, 2  y 6

0, Otherwise
f 5  0.1
 b) f(y < 4):
Random Variables & Probability

3
f ( y  4)   f ( y )  f (0)  f (1)  f (2)  f (3)
y 0

0.2  0.3  2 0.1

Distributions

0.7
 c) f(3<y<10):
9 6
f 3  y  10    f  y    f  y   f 4   f 5   f 6 
y 4 y 4

3 0.1 0.3
 0.2, y 0
Solution cont… 0.3,
 y 1
f  y  
 d) E(Y) & Var(Y): 0.1, 2  y 6

0, Otherwise
E Y   yf ( y )
Random Variables & Probability

y

Y=y 0 1 2 3 4 5 6
f(y) 0.2 0.3 0.1 0.1 0.1 0.1 0.1 Total
Distributions

yf ( y ) 0 0.3 0.2 0.3 0.4 0.5 0.6 2.3  E Y  2.3

y 2 f ( y) 0 0.3 0.4 0.9 1.6 2.5 3.6 9.3
Var  y   y 2 f ( y )  E 2  y 
y

9.3  2.32
4.01 NB : Std Dev,  Y = Var  y   4.01 2.0025
 Example
You are given K800,000 to invest.
You must choose between:
Random Variables & Probability

a) a sure gain of K400,000 and

b) a 0.4 chance of a gain of
K800,000 and a 0.6 chance to
Distributions

gain nothing.
What is the expected gain for each
strategy?
 Solution
 Let X be the r.v. representing gain
 To find Expectation i.e. E(X)
 Strategy a):
Random Variables & Probability

One possible gain: K400,000 with P(x) = 1 (i.e. sure gain)

E  X   xP ( x) 400, 000 1  K 400, 000
Distributions

x
 Strategy b):
Two possible gains: K800,000 with P(x) = 0.4 & K0 with
P(x) = 0.6
X=x K800,000 K0
E  X   xP ( x) 800, 000 0.4   0 0.6 
x P(x) 0.4 0.6
 K 320, 000
  Activity
1. Phillip bought 2 raffle draw tickets at K5,000 each. If a total of
210 tickets are sold and the only prize is dinner for two at Max
& Sherry valued at K50,000;
Random Variables & Probability

a) Construct a probability distribution for the gain, X.

b) Calculate Phillip’s expected gain. -K9,523.81
Distributions

2. X is a discrete r.v. whose pmf is defined as

f ( x)  5C x 0.4 x 0.65 x , where x 0,1, 2,3, 4,5

Find:
a) f 3 b)  X c)  X
a) 0.2304 b) 2 c) 1.0954
 Probability Distribution for Continuous RV
 Dfn:
The probability distribution of a continuous rv is a function f(x)
such that
Random Variables & Probability

1) 0  f (a  x b) 1 0  f  x  dx 1
a
Distributions


2) f (   x ) 1  f  x dx 1

 Example
A continuous rv X has a probability density function (pdf)
defined as
0.125, 0  x  8
Random Variables & Probability

f  x  
0, Otherwise
Distributions

a) Show that satisfies the second condition for PDs.

b) Find
 0.125, 0  x  8
Solution f  x  
0, Otherwise
 a) Show that condition 2 for PDs holds: f(x) = 0 f(x) = 0.125 f(x) = 0

f    x    1 - 0 8 ∞
0 0
Random Variables & Probability

Since X is  0 8 
cont, use
integration
 f  x dx 
 
f  x  dx   f  x  dx   f  x  dx
0 8
Distributions

8
  f  x  dx
0

8
  0.125dx
0

0.125x 0 0.125 8   0.125 0  1

8
 0.125, 0  x  8
Solution cont… f  x  
0, Otherwise
 b) :
6 6
 f  x dx  0.125dx
Random Variables & Probability

3 3

6
0.125x 3
Distributions

0.125 6   0.125 3

0.375
 Expectation and Variance
 Dfn:
If X is a continuous rv with a pdf f(x), then:
Random Variables & Probability

1) The expectation of X is

E  X    xf  x  dx
Distributions



2) The variance of X is
  2
Var  X    x f  x  dx    xf  x  dx 
2
    

   E  X 
2
Var  X   E X 2
 Activity
A continuous r.v. X has a probability density function (pdf)
defined as
0.125, 0  x  8
Random Variables & Probability

f  x  
0, Otherwise
Distributions

Find
a) E(X) a) 4
b) b) 2.3094
 Activity
In commuting to campus, a student first gets a Kabanza near her
house and then transfers to a minibus. If the total waiting time (in
minutes) for the Kabanza and minibus is a r.v. X with the pdf:
0.04 x, 0 x  5
Random Variables & Probability


f  x   0.4  0.04 x, 5  x 10
0, Otherwise

Distributions

Find the probability that the total waiting time is

a) less than 3 minutes.
b) at most 8 minutes.
c) between 3 and 8 minutes.
d) either less than 2 minutes or more than 6 minutes.
Thank You.