Probability
Distributions:
Random Variable
Dr. Kishore Morya
Random Variable: A variable that takes on different values
as a result of the outcomes of a random experiment.
The possible outcomes of a chance situation are often numbers,
such as:
The number of boys in a family chosen at random (0, 1, 2, 3, or 4)
Random The maximum temperature in New Delhi on a particular day
The percentage of respondents who vote BJP in an opinion poll
Variable The marks given by a judge in a gymnastic competition
The age of a student selected at random
The number of telephone calls received by a receptionist in a day
The time it takes an athlete to run 100m
Discrete Random Variable: if a random variable is allowed to
take only a limited number of values, which can be listed.
Examples:
Types of The result of throwing a dice is a discrete random variable because
it can only take some of the values between 1 and 6 inclusive.
Random The number of cars arriving at a toll booth in a 5-minute period.
Variable The number of defective items in a batch
The number of people queuing at a supermarket checkout
The run scored by a batsman in a game of cricket
The number of wickets taken by a bowler.
If a variable is allowed to take any value within a range then
it is a continuous random variable.
Continuous Examples:
The minimum or maximum temperature of a city on a particular day.
Random The amount of water used by a household in a day
Variable Time to travel Jaipur from Delhi by Car
Air contained in a tire of a car
Change in share price of a script on BSE Sensex on a given day
The depth of the sea at a randomly chosen point
The number of phone calls received by a switchboard in a minute.
Check this: The number of attempts an individual needs to pass their driving
Are the following test
The price of a particular share at close of business tomorrow
random variables
The number of students who pass an exam
continuous or
The proportion of a large group of students who pass an exam
discrete
The time taken for an athlete to run 200 meters
The number of heads when a coin is tossed 10 times in succession
The probability distribution of X, the number shown on a single
die, is:
X P(x)
1 1/6
2 1/6
Probability 3 1/6
Distribution 4
5
1/6
1/6
6 1/6
A coin is tossed twice. What is the probability distribution of X,
the number of heads observed?
1st toss 2nd toss
Head Head
Head Tail
Tail Head
Probability Tail Tail
Distribution
x P(x)
0 ¼
1 1/2
2 1/4
In a game I throw two fair coins. If I throw two heads my opponent
will give me Rupees 50, but if not, I must pay Rupees 20. The
probability distribution of X, the amount I gain, is:
Expected
Value or Gain x P(x)
of a Random 50 ¼
Variable -20 ¾
Would you play such as game?
Suppose I play the game for 10000 times.
Outcomes
Two heads receive Rupees 50 for 10000 * ¼ times
Other than two heads pay Rupees 20 for 10000 * ¾ times
So, My Expected Value or Gain:
(50 * 10000 * ¼ ) – (20 * 10000 * ¾ ) = - 25000
Expected Gain of a single game:
-25000/10000 = -2.5 rupees.
Take the example of a fruits and vegetable wholesaler who sells strawberries.
The product has very limited useful life. If not sold on the day of delivery, it is
worthless. One case of strawberries costs $20, and the wholesaler’s selling
price is $50. The leftover loss to the wholesaler is $20/case. The number of
Use of cases sold per day for 100 days is given in the following table:
Daily sales Number of days sold Probability of each
Expected 10 15
number being sold 10
0.15
Value in 11 20 0.20
Decision 12 40 0.40
13 25 0.25
Making Total 100 1
How many cases of strawberries should the wholesaler stock so that minimum
loss occur?
Possible Stock Option
Possible demand 10 11 12 13
for Strawberries
cases
Conditional 10 $0 $ 20 $ 40 $ 60
Loss Table 11 30 0 20 40
12 60 30 0 20
13 60 60 30 0
Possible request Conditional loss Probability of this Expected Loss
demand
10 $0 * 0.15 = $ 0.00
Expected Loss 11
12
30
60
*
*
0.20 =
0.40 =
6.00
24.00
from stocking 13 90 * 0.25 = 22.50
10 cases Total 1.00 = $ 52.50
Possible request Conditional loss Probability of this Expected Loss
demand
10 $ 20 * 0.15 = $ 3.00
Expected Loss 11
12
0
30
*
*
0.20 =
0.40 =
0.00
12.00
from stocking 13 60 * 0.25 = 15.50
11 cases Total 1.00 = $ 30.00
Possible request Conditional loss Probability of this Expected Loss
demand
10 $ 40 * 0.15 = $ 6.00
Expected Loss 11
12
20 *
0*
0.20 =
0.40 =
4.00
0.00
from stocking 13 30 * 0.25 = 7.50
12 cases Total 1.00 = $ 17.50
Possible request Conditional loss Probability of this Expected Loss
demand
10 $ 60 * 0.15 = $ 9.00
Expected Loss 11
12
40 *
20 *
0.20 =
0.40 =
8.00
8.00
from stocking 13 0 * 0.25 = 00.00
13 cases Total 1.00 = $ 25.00