0% found this document useful (0 votes)
244 views5 pages

Baye's Theorem

1) Bayes' theorem provides a way to calculate conditional probabilities based on known marginal probabilities. It is commonly used to solve probability problems involving events. 2) The document provides 6 examples of applying Bayes' theorem to solve probability problems involving events such as defective products from different machines, misfiling of reports by secretaries, defective components from different factories, medical diagnosis outcomes, and selecting pens from assorted packets. 3) In each example, the relevant events are defined, the probabilities of those events are calculated using known marginal probabilities, and Bayes' theorem is applied to find the conditional probability of an event given another event.

Uploaded by

Shubh Patiyat
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
244 views5 pages

Baye's Theorem

1) Bayes' theorem provides a way to calculate conditional probabilities based on known marginal probabilities. It is commonly used to solve probability problems involving events. 2) The document provides 6 examples of applying Bayes' theorem to solve probability problems involving events such as defective products from different machines, misfiling of reports by secretaries, defective components from different factories, medical diagnosis outcomes, and selecting pens from assorted packets. 3) In each example, the relevant events are defined, the probabilities of those events are calculated using known marginal probabilities, and Bayes' theorem is applied to find the conditional probability of an event given another event.

Uploaded by

Shubh Patiyat
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Baye’s theorem

If B1, B2, …, Bn are mutually disjoint events with 𝑃(𝐵𝑖) ≠ 0 (𝑖 = 1,2, … , 𝑛) then for any arbitrary
event A which is a subset of ⋃𝑛𝑖=1 𝐵𝑖 such that 𝑃(𝐴) > 0, then

𝑃(𝐵𝑖 )𝑃(𝐴|𝐵𝑖 )
𝑃(𝐵𝑖 |𝐴) = 𝑛 .
∑𝑖=1 𝑃(𝐵𝑖 )𝑃(𝐴|𝐵𝑖 )

Problems on Baye’s theorem:

1. In a certain assembly plant, three machines, B1, B2, and B3, make 30%, 45%, and 25%,
respectively, of the products. It is known from past experience that 2%, 3%, and 2% of the products
made by each machine, respectively, are defective. Now, suppose that a finished product is randomly
selected. What is the probability that it is defective? What is the probability that it was made by
machine B3?
Solution: Consider the following events:
A: the product is defective,
B1: the product is made by machine B1,
B2: the product is made by machine B2,
B3: the product is made by machine B3.

Applying the rule of elimination, we can write

𝑃(𝐴) = 𝑃(𝐵1)𝑃(𝐴|𝐵1) + 𝑃(𝐵2)𝑃(𝐴|𝐵2) + 𝑃(𝐵3)𝑃(𝐴|𝐵3).

𝑃(𝐵1)𝑃(𝐴|𝐵1) = (0.3)(0.02) = 0.006,


𝑃(𝐵2)𝑃(𝐴|𝐵2) = (0.45)(0.03) = 0.0135,
𝑃(𝐵3)𝑃(𝐴|𝐵3) = (0.25)(0.02) = 0.005,
∴ 𝑃(𝐴) = 0.006 + 0.0135 + 0.005 = 0.0245

Using Baye’s rule, the probability that the defective product was made by machine B3 is

𝑃(𝐵3)𝑃(𝐴|𝐵3)
𝑃(𝐵3|𝐴) =
𝑃(B1)P(A|B1) + P(B2)P(A|B2) + P(B3)P(A|B3)

0.005
= = 0.204
0.0245

2. An office has 4 secretaries handling respectively 20%, 60%, 15% and 5% of files of all government
reports. The probability that they misfile such reports are respectively 0.05, 0.1, 0.1 and 0.05. Find the
probability that the misfiled report can be blamed on the first secretary.

Solution: Let 𝐴1 , 𝐴2 , 𝐴3 and 𝐴4 be 4 secretaries of the office respectively handling 20%, 60%, 15%
and 5% of these files. Hence we have
𝑃(𝐴1 ) = 0.2, 𝑃(𝐴2 ) = 0.6, 𝑃(𝐴3 ) = 0.15 and 𝑃(𝐴4 ) = 0.05

Let E be the event of misfiling a report by the secretaries.

𝑃(𝐸|𝐴1 ) = 0.05, 𝑃(𝐸|𝐴2 ) = 0.1, 𝑃(𝐸|𝐴3 ) = 0.1 and 𝑃(𝐸|𝐴4 ) = 0.05

𝑃(𝐴1 )𝑃(𝐸|𝐴1 ) = 0.2 × 0.05 = 0.01


𝑃(𝐴2 )𝑃(𝐸|𝐴2 ) = 0.6 × 0.1 = 0.06
𝑃(𝐴3 )𝑃(𝐸|𝐴3 ) = 0.15 × 0.1 = 0.015
𝑃(𝐴4 )𝑃(𝐸|𝐴4 ) = 0.05 × 0.05 = 0.0025

𝑃(𝐸) = 𝑃(𝐴1 )𝑃(𝐸|𝐴1 ) + 𝑃(𝐴2 )𝑃(𝐸|𝐴2 ) + 𝑃(𝐴3 )𝑃(𝐸|𝐴3 ) + 𝑃(𝐴4 )𝑃(𝐸|𝐴4 )


𝑃(𝐸) = 0.01 + 0.06 + 0.015 + 0.0025 = 0.0875
Using Baye’s rule, probability that the misfiled report can be blamed on the first secretary is

𝑃(𝐴1 )𝑃(𝐸|𝐴1 )
𝑃(𝐴1 |𝐸) =
𝑃(𝐸)
0.01
𝑃(𝐴1 |𝐸) = = 0.1142
0.0875
3. One factory F1 produces 1000 articles of which 20 are defective, second factory F2 produces 4000
articles of which 40 are defective and the third factory F3 produces 5000 articles of which 50 are
defective. All these articles are put in one stock file. If one of them is chosen, what is the probability
that it is defective? If a chosen item is defective, what is the probability that it is from factory F1?

Solution: E be the article is defective.


F1: the article produced by F1
F2: the article produced by F2
F3: the article produced by F3

Since there are 10,000 articles in all (produced by F1, F2 and F3 taken together), we have
1000 4000 5000
𝑃(𝐹1 ) = 10000 = 0.1 , 𝑃(𝐹2 ) = 10000 = 0.4, 𝑃(𝐹3 ) = 10000 = 0.5

20 40 50
𝑃(𝐸|𝐹1 ) = 1000 = 0.02, 𝑃(𝐸|𝐹2 ) = 4000 = 0.01, 𝑃(𝐸|𝐹3 ) = 5000 = 0.01

𝑃(𝐹1 )𝑃(𝐸|𝐹1 ) = 0.002


𝑃(𝐹2 )𝑃(𝐸|𝐹2 ) = 0.004
𝑃(𝐹3 )𝑃(𝐸|𝐹3 ) = 0.005

Therefore, the probability of selecting a defective article from the lot is,
𝑃(𝐸) = 𝑃(𝐹1 )𝑃(𝐸|𝐹1 ) + 𝑃(𝐹2 )𝑃(𝐸|𝐹2 ) + 𝑃(𝐹3 )𝑃(𝐸|𝐹3 )
𝑃(𝐸) = 0.002 + 0.004 + 0.005
𝑃(𝐸) = 0.011

The probability that the chosen defective article is from F1 is


𝑃(𝐹1 )𝑃(𝐸|𝐹1 )
𝑃(𝐹1 |𝐸) =
𝑃(𝐸)
0.002
𝑃(𝐹1 |𝐸) = = 0.1818
0.011
4. The chance that a doctor will diagnose a disease correctly is 60%. The chance that a patient will die
after correct diagnose is 40% and the chance of death by wrong diagnosis is 70%. If a patient dies,
what is the chance that his disease was correctly diagnosed?
Solution:
Let A be the event of correct diagnosis and B be the event of wrong diagnosis by the doctor
𝑃(𝐴) = 0.6
𝑃(𝐴) + 𝑃(𝐵) = 1
𝑃(𝐵) = 1 − 𝑃(𝐴)
𝑃(𝐵) = 0.4
Let E be the event that patient dies
𝑃(𝐸|𝐴) = 0.4 and 𝑃(𝐸|𝐵) = 0.7

𝑃(𝐸) = 𝑃(𝐴)𝑃(𝐸|𝐴) + 𝑃(𝐵)𝑃(𝐸|𝐵) = (0.6 × 0.4) + (0.4 × 0.7) = 0.52

Using Baye’s rule, the probability that the disease was correctly diagnosed is

𝑃(𝐴)𝑃(𝐸|𝐴) 0.6 × 0.4


𝑃(𝐴|𝐸) = = = 0.4615
𝑃(𝐸) 0.52

5. A shipment of components consists of 3 identical boxes. The first box contains 200 components of
which 25% are defective, the second box has 5000 components of which 20% are defective and the
third box contains 2000 components of which 600 are defective. A box is selected at random and a
component is removed at random from this box. What is the probability that this component is
defective? If the component drawn is found to be defective, what is the probability that it came from
the first or second box?
Solution: Let A , B, C are the first second and third box respectively.
Let P(A), P(B) and P(C) be the probabilities of choosing the first, second and third boxes respectively.
1 1 1
𝑃(𝐴) = , 𝑃(𝐵) = , 𝑃(𝐶) =
3 3 3
E be the event of defective component

Let 𝑃(𝐸|𝐴), 𝑃(𝐸|𝐵) and 𝑃(𝐸|𝐶) denote the probabilities of choosing a defective item from the first,
second and third boxes respectively
600
𝑃(𝐸|𝐴) = 0.25, 𝑃(𝐸|𝐵) = 0.2 and 𝑃(𝐸|𝐶) = 2000 = 0.3

Therefore, the probability of drawing a defective component from an arbitrarily chosen box is
𝑃(𝐸) = 𝑃(𝐴)𝑃(𝐸|𝐴) + 𝑃(𝐵)𝑃(𝐸|𝐵) + 𝑃(𝐶)𝑃(𝐸|𝐶)
1
𝑃(𝐸) = 3 [0.25 + 0.2 + 0.3] = 0.25

The probability that a drawn component is defective and it is from the first box is
1
𝑃(𝐴)𝑃(𝐸|𝐴) 3 × 0.25 1
𝑃(𝐴|𝐸) = = =
𝑃(𝐸) 0.25 3
The probability that a drawn component is defective and it is from the second box is
1
𝑃(𝐵)𝑃(𝐸|𝐵) 3 × 0.2
𝑃(𝐵|𝐸) = = = 0.2667
𝑃(𝐸) 0.25

Consequently, the probability that a drawn component is defective and it is from the first or second
box is
𝑃(𝐴|𝐸) + 𝑃(𝐵|𝐸) = 0.3333 + 0.2667 = 0.6.

6. A company manufacturing ball pens in two writing colours blue and red make packets of 10 pens
with 5 pens of each colour. In a particular shop it was found that after sales, packet 1 contained 3 blue
and 2 red pens, packet 2 contained 2 blue and 3 red pens, packet 3 contained 3 blue and 5 red pens.
On the demand of a customer for a pen, packet was drawn at random and a pen was taken out. It was
found blue. Find the probability that packet 1 was selected.

Solution: Let 𝑃1 , 𝑃2 and 𝑃3 be the event of selecting packets 1, 2 and 3 respectively at random.
1
∴ 𝑃(𝑃1 ) = 𝑃(𝑃2 ) = 𝑃(𝑃3 ) = 3

Let E be the event of selecting a blue pen


Probability of selecting a blue pen from packet1, packet 2 and packet 3 is
3 2 3
𝑃(𝐸|𝑃1 ) = 5 , 𝑃(𝐸|𝑃2 ) = 5 and 𝑃(𝐸|𝑃3 ) = 8

𝑃(𝐸) = 𝑃(𝑃1 )𝑃(𝐸|𝑃1 ) + 𝑃(𝑃2 )𝑃(𝐸|𝑃2 ) + 𝑃(𝑃3 )𝑃(𝐸|𝑃3 )


1 3 2 3 11
𝑃(𝐸) = 3 [5 + 5 + 8] = 24 = 0.4583

Using Baye’s rule, we have


1 3
𝑃(𝑃1 )𝑃(𝐸|𝑃1 ) ×
𝑃(𝑃1 |𝐸) = = 3 5 = 0.4364
𝑃(𝐸) 0.4583

You might also like