Introduction to

Probability and Statistics

Sayantan Banerjee
IPS Session 3
Joint probability distribution

Example
Bradley has invested in two stocks, Markley Oil and Collins
Mining. Bradley has determined that the possible outcomes of
these investments three months from now are as follows (in ’000 $)

Markley Oil Collins Mining

10 8
5 -2
0
-20

Sayantan Banerjee 1
Joint probability distribution

Sample points and assigned probabilities are as below.

Sample points Probability

10,8 0.20
10,-2 0.08
5,8 0.16
5,-2 0.26
0,8 0.10
0,-2 0.12
-20,8 0.02
-20,-2 0.06

Sayantan Banerjee 2
Joint Probability distribution

Shares Collins Total

Profitable Non-Profitable
Markley Profitable 0.36 0.34 0.70
Non-Profitable 0.12 0.18 0.30
Total 0.48 0.52 1

1. What is the probability that Bradley gains from shares of

Markley Oil?
2. Find the probability of gaining from Collins Mining given that
Markley Oil shares were not profitable.

Sayantan Banerjee 3
Problems
The accompanying table gives information (proportion) on the
type of coffee selected by someone purchasing a single cup at a
particular airport kiosk.

Small Medium Large

Regular 0.14 0.20 0.26
Decaf 0.20 0.10 0.10

Consider randomly selecting such a coffee purchaser.

1. What is the probability that the individual purchased a small
cup? A cup of decaf coffee?
2. If we learn that the selected individual purchased a small cup,
what is the probability that they chose a decaf coffee?
3. If we learn that the selected individual purchased decaf, what
is the probability that a small size was selected?
Sayantan Banerjee 4
Bayes’ Theorem

Example: Incidence of rare disease

A particular medical test for a certain rare disease gives a positive
result with probability 99% when the patient is indeed affected by
the disease, while it gives a negative result with 98% probability
when the patient is not affected by that disease. If a patient is
drawn at random from a population in which 0.1% of individuals
are affected by that disease and he is found positive, what is the
probability that he actually has that disease?

Sayantan Banerjee 5
Bayes’ Theorem

Let A1 , . . . , Ak be a collection of k mutually exclusive and

exhaustive set of events with prior probabilities
P (Ai ), i = 1, . . . , k. Then for any event B for which P (B) > 0,
the posterior probability of Aj given than B has occured is given by

P (B | Aj )P (Aj )
P (Aj | B) = Pk , j = 1, . . . , k.
i=1 P (B | Ai )P (Ai )

Sayantan Banerjee 6
Bayes’ Theorem
Solution: Incidence of rare disease
Let us denote the events A: the person has the rare disease, and
B: the test result is positive.

Sayantan Banerjee 7
Bayes’ Theorem
Solution: Incidence of rare disease
Let us denote the events A: the person has the rare disease, and
B: the test result is positive. Then,

P (A) = 0.001, P (Ac ) = 0.999.

Sayantan Banerjee 7
Bayes’ Theorem
Solution: Incidence of rare disease
Let us denote the events A: the person has the rare disease, and
B: the test result is positive. Then,

P (A) = 0.001, P (Ac ) = 0.999.

P (B | A) = 0.99, P (B | Ac ) = 0.02.

Sayantan Banerjee 7
Bayes’ Theorem
Solution: Incidence of rare disease
Let us denote the events A: the person has the rare disease, and
B: the test result is positive. Then,

P (A) = 0.001, P (Ac ) = 0.999.

P (B | A) = 0.99, P (B | Ac ) = 0.02.
By applying Bayes’ theorem,

P (B | A)P (A)
P (A | B) =
P (B | A)P (A) + P (B | Ac )P (Ac )
0.00099
= = 0.047.
0.00099 + 0.01998
Are you surprised by the result above?
Sayantan Banerjee 7
Some problems on Bayes’ theorem
Professor Stan der Deviation can take one of two routes on his way
back home from office. On the first route, there are four railroad
crossings. The probability that he will be stopped by a train at any
particular one of the crossings is 0.1, and trains operate
independently at the four crossings. The other route, though
longer, has only two railroad crossings, independent of one
another, with the same stoppage probability for each as on the first
route. On a particular day, Prof Deviation has a meeting at home
at a certain time. Whichever route he takes, he calculates that he
will be late if he is stopped by trains in at least half the crossings
encountered.
• Which route should he take to minimize the probability of
being late at the meeting?
• If he tosses a fair coin to decide on a route and he is late,
what is the probability that he took the first route?
Sayantan Banerjee 8
Some problems on Bayes’ theorem

There has been a great deal of controversy over the last several
years regarding what types of surveillance are appropriate to
prevent terrorism. Suppose a particular system has a 99% chance
of correctly identifying a future terrorist and a 99.9% chance of
correctly identifying someone who is not a future terrorist. If there
are 1000 future terrorists in a population of 300 million, and one of
these 300 million is randomly selected, scrutinized by the system,
and identified as a future terrorist, what is the probability that
he/she is actually a future terrorist? Does the value of this
probability make you uneasy about using the surveillance system?
Explain.

Sayantan Banerjee 9
Some problems on Bayes’ theorem

A plane is missing, and it is presumed that it was equally likely to

have gone down in any of 3 possible regions. Let
1 − βi , i = 1, 2, 3, denote the probability that the plane will be
found upon a search of the ith region when the plane is, in fact, in
that region. (The constants βi are called overlook probabilities,
because they represent the probability of overlooking the plane;
they are generally attributable to the geographical and
environmental conditions of the regions.) What is the conditional
probability that the plane is in the ith region given that a search of
region 1 is unsuccessful, i = 1, 2, 3?

Sayantan Banerjee 10