Mathematics III Probability Concepts

Paper Name: Mathematics III 1 Paper Code: BS M301
Institute of Engineering & Management
Department of ELECTRONICS & COMMUNICATION

ENGINEERING
Work book
Paper Name with code: Mathematics III; BS M301

Name of the Teacher: Dr. Saktipada Nanda (SPN)
Name of the Student:

Year: Section:
Class Roll No.:
University Roll No.:
1|Page Study Material, IEM, ECE Department

“Mathematics is a more powerful instrument of knowledge than any other that has been
bequeathed to us by human agency” - Descartes’
Module - I
Basic Probability (8 L)
Paper name: Mathematics III
Code: BS M 301
Contacts: 3L Credits: 3
Pre-requisites: Probability and Statistics of High School Level, Mathematics I (BS M102),
Mathematics II (BS M202)
Module I:Basic Probability [8 L]
1.Detailed Syllabus:
Probability spaces, conditional probability, independence; Discrete random variables,
Independent random variables, the multinomial distribution, Poisson approximation to the
binomial distribution, infinite sequences of Bernoulli trials, sums of independent random
variables; Expectation of Discrete Random Variables, Moments, Variance of a sum,
Correlation coefficient, Chebyshev’s Inequality.
2.Recommended Books:
(i)Erwin Kreyszig, Advanced Engineering Mathematics, 9th Edition, John Wiley & Sons,
2006. (ii) P. G. Hoel, S. C. Port and C. J. Stone, Introduction to Probability Theory, Universal
Book Stall, 2003 (Reprint).
(iii)GATE Engineering Mathematics and General Aptitude by Dr Saktipada Nanda and
Sibashis Nanda (www. Flipkart.com/www.amazon.in)
(iv) Engineering Mathematics IV by G.P. Samanta
(v) A Course on Probability and Statistics by A. K. Mukhopadhyay and S. P. Nanda
(vi) Statistics by Sancheti and Kapoor
(vii) Statistical Methods by N.G.Das
3.Course Outcomes:
(i) Uncertainty computing is used in many fields to solve Real life problem - such as in
prediction, control theory, management, chaotic system etc.
(ii) The concept is quite useful in the field of Computer Science to study the average
performance of the designed model/algorithm, management -to manage man and
machine dynamics, medical science-to detect a disease , meteorology- to predict weather
phenomena, communication sciences- to measure information quality and quantity.
(iii)The concept and results may be applied in Data Structure (in the preparation of ‘hash
table’).

(iv)The concept and results may be applied in File Structure (in ‘Average seek time
computation’).
4. Course Information
PROGRAMME:Engineering DEGREE: B. Tech.
COURSE: ECE SEMESTER: 3 CREDITS: 3
COURSECODE: BS M 301 COURSE TYPE: Theory
CORRESPONDING LAB COURSE

CONTACT HOURS: 3L+1T
CODE (IF ANY): NO
5.Day-wise Lesson Plan:
LECTURE Topics/Sub- topics LECTURE Topics/Sub- topics

1 Some Basic terminology. 5 Binomial & Poisson Distribution
Event space, Axiomatic Expectation, Mean & Variance of
and Classical definition of Binomial and Poisson distributions
Probability.
2 Conditional probability, 6 Infinite sequences of Bernoulli trials
Independent events, Bayes’ Chebyshev’s Inequality
theorem and its application.
3 Random variables (Discrete & 7 Miscellaneous problems on the
Continuous), Probability probability, mean & variance of
Mass Function and related discrete random variable
problems
4 Discrete Random variable 8 Miscellaneous problems on
and concept of Expectation Discrete probability distributions
& variance of Discrete
Random variable

DAY 1
Course: B. Tech.
Relevant MAKAUT syllabus portion: Some Basic terminology,Event space, Axiomatic and
Classical definition of Probability,Conditional probability.
Lecture 1 (60 minutes)
Relevant MAKAUT syllabus portion: Some Basic terminology. Event space, Axiomatic and
Classical definition of Probability.
Objectives:
It gives the idea of numerical measurement of chance that helps to guess the future.
Class Notes:
(i) Event Space: The set of all sample points ( S) is Event space.
Class Notes: Definition of probability:Let P be a function from

(ii) Axiomatic  to the set of all real
numbers satisfying the following axioms:
Axiom I. P(A)  0 for every event A in  (class of all events)

Axiom II.P(S)=1, S being the sample space.
Axiom III. If A1,A2,---,An be a set of mutually exclusive events belonging to ,
then P  A1  A2      An   P  A1   P  A2       P  An 
(iii) Classical Definition of probability: If a random experiment has n (finite) mutually

exclusive, exhaustive and equally likely outcomes and out of them m are favourable to A,
m
then the probability of occurrence of A, denoted by P(A), is given by P ( A) 
n
(iv) Theorem of Total Probability: For any two events A and B,

P ( A  B )  P ( A)  P ( B )  P ( A  B )
(ii) For two mutually exclusive events A and B, P ( A  B )  P ( A)  P ( B )
(iii) If the n events A1 , A2 ,  , An are mutually exclusive, exhaustive and equally likely
1
events, then P ( A1 )  P ( A2 )      P ( An ) 
n
Let’s learn by doing:

1.If A and B are any two events suchthat
P ( A  B )  1 / 2, P ( A  B )  1 / 3, , P( A)  P(B)  p, then find the value of p.

2.If two fair coins are flipped and at least one of the outcomes is known to be a head, what
is the probability that both outcomes are heads?
3. Consider the following experiment:

Step 1. Flip a fair coin twice.
Step 2. If the outcomes are (Tails, Heads), then output Y and stop.
Step 3. If the outcomes are either (Heads, Heads) or (Heads, Tails), then output N and stop.
Step 4. If the outcomes are (Tails, Tails) then go to Step 1.
Find the probability that the output of the experiment is Y is (up to two decimal places).
4. The probability that at least one of the events A and B occurs is 0.6. If A and B occur
simultaneously with probability 0.2, then find the value of P ( A )  P ( B )
5.There are 25 calculators in a box. Two of them are defective. Suppose 5 calculators are
picked for inspection (i,e, each has the same chance of being selected), what is the
probability that only one of the defective calculators will be included in inspection?
DAY 2
Course: B. Tech.
Relevant MAKAUT syllabus portion: Conditional probability, Independent events,
Bayes’ theorem and its application.
Class Notes:
Conditional Probability: Probability of occurrence of the event B given that the event
A has actually occurred = P(B/A)
(ii) Theorem of Compound Probability: P(B/A) = P( AB) , P( A)  0 and
P( A)
P(A/B) = P ( AB ) , P ( B )  0
P( B)
(iii) Independent Events: If A and B are independent events,
P ( B / A)  P ( B )  P ( A  B )  P ( A). P ( B )
If A and B are independent events, then
a) A and B b) A and B c) A and B are also independent.
xii) Baye’s theorem:
P ( Bi ) P ( A / Bi )
P( Bi / A)  , i  1,2,  , n
P( B1 ) P( A / B1 )  ....  P( Bn ) P( A / Bn )
(i)
1. Two players, A and B , alternately keep rolling a fair dice. The person to get a six first wins the
game. Given that player A starts the game, find the probability that A wins the game.

2. A candidate is selected for interview for three posts. The number of candidates for the first,
second and third posts are 3, 4 and 2 respectively. Find the probability that he will get at least one
post.
3. A person moving through a tuberculosis prone zone has a 50% probability of becoming infected.
However, only 30% of infected people develop the disease. What percentage of people moving
through a tuberculosis prone zone remains infected but does not show symptoms of disease?
1
4.P and Q are considering to apply for a job. The probability that P applies for the job is , the
4
1
probability that P applies for the job given that Q applies for the job is , and the probability that Q
2
1
applies for the job given that P applies for the job is . Then find the probability that Q does not
3
apply for the job given that P does not apply for the job.
5.Three companies, X, Y and Z supply computers to a university. The percentage of computers
supplied by them and the probability of those being defective are tabulated below.
Company % of computers supplied Prob. of being defective

X 60% 0.01
Y 30% 0.02
Z 10% 0.03
Given that a computer is defective, the probability that it was supplied by Y.
DAY 3
Course: B. Tech.
Relevant MAKAUT syllabus portion: Condition Probability and Independent Events
Objectives: Random variables (Discrete & Continuous), Probability Mass Function and
related problems.
Class Notes:
(i)Discrete Random Variable X: Its p. m. f. (probability mass function) f(x) satisfies the

relations f ( x )  0 and  f ( x)  1

(ii)The probability that the X will assume the value x is given by P(X = x) = f(x)
Mean of X = x = E(X) =  f x where fi is the probability for X = xi
i i
2 2 2
(iii) Variance of X = VAR(X) =  2 = E(x - x )  E ( x )  x
s. d. of X     E ( x 2 )  x 2

1. If a random variable X takes the values 1, 2, 3 and 4 such that

2 P ( X  1)  3P ( X  2)  P ( X  3)  5 P ( x  4), then find the value of P ( X  1).
2. If f ( x )  kx, x  1,2,  , n be the p. m. f. of a random variable X , then the mean of X is

n 1 n 1 2n  1 2n  1
(A) (B) (C) (D)
2 3 2 3
3. A random variable X has the following probability distribution:
Values of X 0 1 2 3 4 5 6 7
P(X) 0 2k 3k K 2k K2 7K2 2K2+
k
Then find P(0< X < 5).
4.Let X be a random variable which is uniformly chosen from the set of positive odd numbers less
than 100. Obtain the expected value of X.
5.Consider a dice with the property that the probability of a face with n dots showing up is
proportional to n . Find the probability of the face with three dots showing up.
DAY 4
Course: B. Tech.
Relevant MAKAUT syllabus portion: Discrete Random variable and concept of
Expectation & variance of Discrete Random variable
Class Notes:
(i ) E ( X )   x.P ( X ), E (c)  c, E (cX  b)  cE ( X )  b, E (aX  bY )  aE ( X )  bE (Y )
(ii)If X and Y are independent events then E(XY) = E(X).E(Y)

 
(iii ) var( X )  E  X  X   E X 2  X 2 , var(a )  0, var(aX  b)  a 2 var( X )
2
(iv) If X and Y are independent events, var(aX  bY )  a 2 var( X )  b 2 var(Y )

iv) A.M.

1
1. Find the variance of the random variable X with probability density function f ( x )  | x | e | x |
2
2. Consider the following probability mass function (p.m.f.) of a random variable
q if X  0

X : p ( x, q )  1  q if X  1 . If q = 0.4,find the variance of X.
0, otherwise

3. For a random variable X, var (X) = 1, then var (2 X + 3) =
(A) 1 (B) 4 (C) 16 (D) 1/2
4.A and B toss in turn an ordinary die for a prize of D 55. The first to toss 6 wins. If A has the first
throw , what is his mathematical expectation?
5.If a person gets D(2x + 5) where x denotes the number when a balanced die is rolled once. How
much money can be expected in the long run per game?
DAY 5
Course: B. Tech.
Relevant MAKAUT syllabus portion:
Binomial & Poisson Distribution Expectation, Mean & Variance of Binomial and Poisson
distributions
Objectives: In this chapter, we shall deduce mathematically the expected frequency

distribution of certain population.
The concept of probability distribution is analogous to that of frequency distribution. The
frequency distribution tells us how the total frequency is distributed among different values
or classes of the variable. Similarly, a probability distribution tells us how the total
probability of 1 is distributed among the various values which the random variable can take.
Concept of Expectation is used to estimate the mean of a random variable and variance gives
the measure of spread about the mean value of the observations.

Class Notes:
1. Binomial Distribution: The probability of x successes in n independent trials P(X = x) = f(x)

= n C x p x q n  x , x = 0,1,2, ...,n; p is the probability of success, q is the probability of failure and p + q
=1 Parameters = n, p Mean = np Variance = npq
2. Poisson Distribution: The probability that the discrete random variable X assumes the value x is
e m m x
given by P(X = x) = f(x) = , x  0,1,2,......, 
x!
Parameter = m, Mean = Variance = m
3. Binomial to Poisson Distribution: If n is large and p is small, then the Binomial Distribution
converges to Poisson Distribution and the mean of the Binomial Distribution (np) converges to the
mean of the Poisson Distribution (m).
1. (v)Let’s
var(a)learn by doing:
= 0, var(ax + b) = a2var(x), var(ax + by) = a2var(x) + b2var(y)
1.For a Binomial (6, p ) distribution, P ( X  2)  9 P ( X  4). Then find the value

of P ( X  0).
2. A random variable follows Binomial Distribution with mean 4 and variance 2. Then find
the probability of assuming non-zero value of the variate.
3. A and B play a game in which their chances of winning are in the ratio 3:2. Out of five
games played find A’s chance of winning three games.
4. The probability of hitting a target by a bullet is 1/2.Two direct hits are required to destroy
the target. If 4 bullets are thrown independently, find the probability of destroying the target.
5. Suppose p is number of cars per minute passing through a certain road junction between 5
PM and 6PM, and p has a Poisson distribution with mean 3. What is the probability of
observing fewer than 3 cars during any given minute in this interval?
DAY 6
Course: B. Tech.
Infinite sequences of Bernoulli trials, Tchebyshev’s Inequality
Objectives: The distributions are frequently used in statistical data analysis. For example,
the customer arrival pattern in a service centre or a job arrival in a printer queue.

Class Notes:
i)Bernoulli’s Trials: Let Ai be the event corresponding to i successes (n-i failures) in
n independent trials, then P(Ai) =  in  p i (1  p ) n i , i  0,1,2,  , n.
ii)Tchebyshev’s Inequality: If X is a random variable having mean m and standard

2
deviation  , then for any   0, P  X  m     .
2
1. What is the probability of at least r successes in n Bernoulli’s Trials?

2. A dice is thrown three times in succession. Find the probability of getting two ones.
3. Find the probability of getting 11 three times in 100 tosses of two dice.
4. Let X be a random variable which follows Poisson distribution with parameter m. Prove
 m 4
that P X   
 2 m
5. A symmetric die is thrown n times and obtain a total score Sn. Determine the upper
S 
estimate of P n  3.5   ,   0 using Tchebyshev’s Inequality.
 n 
DAY 7
Course: B. Tech.
Miscellaneous problems on probability, mean & variance of discrete random variable
1. A nationalized bank has found that the daily balance available in its savings a/c follows a
normal distribution with mean Rs. 500 and s.d. Rs. 50. Find the percentage of savings a/c
holders who maintain an average daily balance more than Rs. 500.
17
2. The probability that a construction job will be finished in time is , the probability that there
20
3
will be no strike is and the probability that the construction job will be finished in time, assuming
4
14
that there will be no strike is . Find the probability that the construction job will be finished in time
15
and there will be no strike.
10 | P a g e Study Material, IEM, ECE Department

3. In a factory, two machines M 1 and M 2 manufacture 60% and 40% of the auto components
respectively. Out of the total production, 2% of M 1 and 3% of M 2 are found to be defective. If a
randomly drawn auto component from the combined lot is found defective, what is the probability
that it was manufactured by M 2 ?
4. An examination consists of two papers, Paper 1 and Paper 2. The probability of failing in Paper 1
is 0.3 and that in Paper 2 is 0.2. Given that a student has failed in Paper 2, the probability of failing in
Paper 1 is 0.6. Find the probability of a student failing in both the papers.
5.In a bolt factory, machines A, B, C manufacture respectively 20%, 30% and 50% of the
total output. Of the output, 3%, 4% and 5% are defective. One bolt is drawn at random from
the product and found defective. What is the probability that it is manufactured by A?3. If 3%
of the bolts manufactured by a company are defective, find the probability that in a sample of

200 bolts (a) 5 will be defective (b) none is defective. e 6  0.00248 . 
DAY 8
Course: B. Tech.
Miscellaneous problems on Discrete probability distributions
1. If 3% of the bolts manufactured by a company are defective, find the probability that in a

sample of 200 bolts (a) 5 will be defective (b) none is defective. e 6  0.00248 . 
2.A car hire farm has two cars which it hires out day by day. The number of demands for a
car on each day is distributed as a Poisson distribution with average number of demands per
day is 1.5. Calculate the number of days (approximately) in a year on which some demand is
refused and the number of days in a year (approximately) on which neither car is used.
e 1.5  0.2231 
3.Suppose p is number of cars per minute passing through a certain road junction between 5
PM and 6PM, and p has a Poisson distribution with mean 3. What is the probability of
observing fewer than 3 cars during any given minute in this interval?
4.The incidence of occupational disease in an industry is such that workers have a 10%
chance of suffering from it. What is the chance that out of 6 workers, at least 3 will suffer
from the disease?
5. A and B play a game in which their chances of winning are in the ratio 3:2. Find A’s
chance of winning at least three times out of the five games played.

Module - 2
Continuous Probability Distributions (4L)
Code: BS M 301
.1. Detailed Syllabus:
Continuous random varibales and their properties, distribution functions and densities,
normal, exponential and gamma densities.
3.Course Outcomes:
table’).
computation’).


1 Continuous random 3 PDF and CDF of Normal
variables and their distribution, Standard Normal
properties, PDF & CDF distribution
2 PDF and CDF of Exponential 4 Gamma distribution

distribution Miscellaneous problems
DAY 1
Course: B. Tech.
Continuous random variables and their properties, PDF & CDF
Objectives:
The concept is applied to study the average performance of the designed model /algorithm, to
manage man and machine dynamics, to detect a disease, to predict weather phenomena.
Class Notes:
1. Continuous Random Variable X: Its p. d. f. (probability density function) f(x) satisfies the

relations f ( x )  0 and  f ( x)dx  1

2. The probability that X will assume any value in the interval [a, b] is given by P(a ≤ x ≤ b)
b
=  f ( x)dx
a
3. The Cumulative Distribution Function (c.d.f.) or Distribution Function F(x) is given by

x
d P (c  x  d )  F ( d )  F (c )
F ( x)  P( X  x)   f (t )dt and

f ( x) 
dx
F ( x) ;

4. Mean of X = x = E(X) =  xf ( x)dx and


5. variance of x   2  E ( x 2 )  x 2  x
2
f ( x)dx  x 2

6. E(x - x ) = 0, E(a) = a, E(ax) = a E(x), E(ax + b) = a E(x) + b, where a and b are constants.
7. var(a) = 0, var(ax + b) = a var(x), var(ax + by) = a2var(x) + b2var(y)
2

x n x
1. The function f ( x )  e , x  0, n being a positive integer, is a p.d.f. of X . Find the variance
n!
of X .
2. A random variable X has probability density function f (x) as given below:

a  bx, 0  x  1 2
f (x)   . If the expected value E[ X ]  , then find Pr[X  0.5]
0, otherwise 3
3. The length of life of a tyre follows the continuous distribution:

k / x 3 , 1000  x  1500
f ( x)   Find k and the probability that a randomly selected tyre would
0, elsewhere
function for at least 1200 hours.
 x, 0  x 1

4.The function f (x ) defined by f ( x )  k  x, 1  x  2
0, is a p.d.f. of a random variable X for a
 elsewhere
suitable value of k. Find the probability that the random variable X lies between 1/2 & 3/2.
x 2
 4  x ,0  x  2
5. The probability density function of a random variable, X is f ( x )   4
 
0, otherwise
Find the mean  x of the random variable.
DAY 2
Course: B. Tech.
PDF and CDF of Exponential distribution.
Objectives:
This is a standard probability distribution and is used commonly in statistics.
Class Notes:
1. A random variable X assuming non-negative values will follow Exponential distribution with 1.The
1.The pdf of exponential distribution with parameter  ( 0) is given by f ( x )  e  x , x  0.
 
1 1
 xf ( x)dx  x
2
2.Mean  x  E ( x )  , 3. variance  f ( x)dx  x 2 

  2

1. If X is exponentially distributed, show that the probability that X exceeds its mean value
is less than 1/2.
2. Assume that the length of a phone call in minutes is an exponentially distributed random
1
variable with parameter . If A arrives immediately ahead of B at a public telephone booth,
10
find the probability that B will have to wait
i) more than 10 minutes ` ii) between 10 and 20 minutes.
3.Assume that the length of a phone call in minutes is an exponentially random variable
with parameter 1/10. If a arrives immediately ahead of B at a public telephone booth, find
the probability that B will have to wait i) more than 10 minutes ii) between 10 and 20
minutes.
4.A random variable X has the pdf given by
f ( x)  ke  b ( x  a ) , a  x  ,
where k,a,b are constants.
Prove that k=b=1 and a=m-s, where m = mean & s = s.d.
5.The radius of a circle has distribution given by the pdf
1, 1  x  2
f ( x)   .
0, elsewhere
Find the mean and variance of the area of the circle.
6.Suppose that during rainy season, on a tropical island, the length of shower has an
1
exponential distribution with average length of shower minute. What is the probability
2
that a shower will last more than 3 minutes? If a shower has already lasted for 2 minutes,
what is the probability that it will last for at least one more minute?
DAY 3
Course: B. Tech.
PDF and CDF of Normal distribution, Standard Normal distribution

Objectives:
This is a standard probability distribution and is used commonly in statistics.
Class Notes:
( x )2
1.Normal Distribution: Its p. d. f. is given by f ( x )  1 
,  x
e 2 2
 2
Parameter =  ,  , Mean =  and Variance =  2
2. Standard Normal Distribution: z  x   is called standard normal variate.

1
,  x
2
Its p. d. f. is given by  ( z )  e z /2
Mean = 0 and Variance = 1.
2
The standard normal variate z is unit free.
Area between z  1 is 68.27%, Area between z  2 is 95.45%
Area between z  3 is 99.73%
3.Diagram of the bell-shaped standard normal curve:
4.Some Results:
k
i) i ) P (   z  0)  P (0  z   )  0.5, ii )  ( k )    ( z )dz

iii )  (k )   ( k )  1
Iv) For positive value of P (  k  z  0)  P (0  z  k )

v) Points of inflexion    3 ,   3
1.If X be a normal variate with zero mean and unit variance, then find the expectation of X2.

2.Obtain mean and s.d. of the normal distribution.
3.If X is normally distributed with mean 3 and s.d. 2, find c such that P(X > c)=2P(X ≤ c).
 0.43



Given , 

 (t )dt  0.666

4.If X is normally distributed with mean 12 and variance 16, find P(X ≥ 20).
 1
2


2
Given , e t / 2 dt  0.977725
 2  
5.The weight of a student in a college is normally distributed with mean = 40 kg and s.d. =5
kg. Find the percentage of students that have weight between 38 kg and 52 kg.
 1
0 .4
1
2 .4

2  2 
t 2 / 2 t 2 / 2
Given, e dt  0 . 6554 & e dt  0 . 9918 
 
DAY 4
Course: B. Tech.
Gamma distribution Miscellaneous problems

Objectives:
The service time of a queueing model (in which inputs follow Poisson distribution) follows
gamma distribution.
In PERT (Program Evaluation and Review Technique), the completion time gives a skewed
distribution.
Class Notes:
I)The pdf of X following gamma distribution is given by

 1  x l 1
f ( x)   e x ,0  x . l  1 is the parameter of the distribution.
 (l )
ii) f (x) is maximum at x  l  1. 1 1l
iii) Maximum value of f (x) is M  e (l  1) l i .
(l )
1
1. If a normal variate X is N(0,1), then show that X2/2 is    variate.
2

2. The density function of a random variable X is f ( x)  e  x , x  0. Find the density function

1
of the random variable i ) U  X ii ) V  .
X
3. Let the p.d.f. of a random variable X is f ( x)  k ( x  1)(2  x),1  x  2.
5 3
Determine (i) the value of k, (ii) the distribution function (iii) P  X  .
4 2
4. The weekly wage of 10000 workers in a factory follows normal distribution with mean Rs. 70 and
standard deviation Rs. 5. Find the expected number of workers whose weekly wages are
(i) between Rs. 66 and Rs. 72 (ii) more than Rs. 72
 1
z

e
t 2 / 2
Given dt  0.1554 or 0.2881 according as z  0.4 or 0.8
 2 0 
1
x e | x |
5. Find the variance of the random variable X with probability density function f ( x) 
2
6. The mean weight of 500 male students in a college is 150 lbs and the standard deviation is
15 lbs. Assuming the weights are normally distributed, find how many students weigh
i) between 120 and 155 lbs ii) more than 155 lbs.
 (2)  0.9772,  (0.33)  0.6293
7. If X is an exponentially random variable with parameter  (> 0), find the value of k such
P( X  k )
that  l , k  0.
P( X  k )
8. The length of life of a tyre follows the continuous distribution:

k / x 3 , 1000  x  1500
f ( x)   Find k and the probability that a randomly selected tyre would
0, elsewhere
function for at least 1200 hours.
9. A random variable X has probability density function f (x) as given below:

a  bx, 0  x  1 2
f (x)   . If the expected value E[ X ]  , then find Pr[X  0.5]
0, otherwise 3
10. Three companies, X, Y and Z supply computers to a university. The percentage of computers
supplied by them and the probability of those being defective are tabulated below.
Company % of computers supplied Prob. of being defective

X 60% 0.01
Y 30% 0.02
Z 10% 0.03
Given that a computer is defective,find the probability that it was supplied by Y.

Module - 3
Bivariate Distributions (4L)
Code: BS M 301
.1. Detailed Syllabus: Bivariate Distributions: 4L

Bivariate distributions and their properties, distribution of sums and quotients, conditional
densities, Bayes’ rule.
3.Course Outcomes:
table’).
computation’).


1 Bivariate distributions and 3 Conditional densities
their properties
2 Distribution of sums and 4 Miscellaneous Problems
quotients
DAY 1
Course: B. Tech.
Bivariate distributions and their properties
Objectives: The objective of this course is to familiarize the students with statistical
techniques consisting of two random variables. It aims to equip the students with standard
concepts and tools at an intermediate to advanced level that will serve them well towards
tackling various problems in the discipline.
The students will learn:
The ideas of probability and random variables and various discrete and continuous
probability distributions and their properties.
Class Notes:
i) Definition: A random variable x assumes two values x1 , x2 corresponding to each of which

another random variable y assumes two possible values y1 , y 2 . There are then 4 pairs of values
xi , y i , i  1,2. Let pij  Pr ob( x  xi , y  y j ).
Joint Distribution of x and y:
Y/x y1 y2 Total The sum of the probabilities in all rows and
x1 p11 p12 p1 or  p
i j
ij  1.
x2 p 21 p 22 p2
Total p1 p2 1
iii) The bivariate distribution function of 2 random variables X & Y is defined as

F ( x, y )  P (  X  x,    Y  y ) ii) F (, )x  1y, F (, y )  0, xF ( xy, )  0

iii) Discrete: f ij  P X  xxi , Y
y  y 
j & F  x, y )    f ij , f ij  0,  f ij  1.
iv) Continuous: F ( x, y ) 
x y

f ( x, y )dxdy where if(x,j y) is the joint pdf
  
i  of ( x, y ) with property
j  
iv)   f ( x, y )dxdy  1
  

1.Show that the function f ( x, y ) defined by

sin x sin y, 0  x   / 2,0  y   / 2
f ( x, y )   is a possible two-dimensional pdf.
0, elsewhere
2.The jolnt pdf of the the random variables X & Y is

k (3 x  y ), 1  x  3,0  y  2
f ( x, y )   . Find the value of k.
0, elsewhere

k (3 x  y ), 1  x  3,0  y  2
f ( x, y )   . Find the value of P(X + Y < 2).
0, elsewhere

C ( x  y ), x  0, y  0, x  y  2
f ( x, y )   . Find the value of C.
0, elsewhere

C ( x  y ), x  0, y  0, x  y  2
f ( x, y )   . Find the value of P(X < 1, Y > 1/2).
0, elsewhere
DAY 2
Course: B. Tech.
Relevant MAKAUT syllabus portion: Distribution of sums and quotients
Objectives:
Class Notes:
Definition: A random variable x assumes two values corresponding to each of which another i)The
expectation of the sum of two jointly distributed random variablesx & y is given by
E(X + Y) = E(X) + E(Y).
ii) If X & Y are jointly distributed random variables,

var(X + y) = var(X) + var(Y) +2cov(X,Y) and var(X - y) = var(X) + var(Y) -2cov(X,Y)
iii) If X & Y are independent binomial variables with parameters (m,p) & (n,p), then X + Y has a
binomial distribution with parameters (m + n, p).
iv) If X & Y are independent poisson variables with parameters m & n, then X + Y has a poisson
distribution with parameter m + n.

1. The jolnt pdf of the the random variables X & Y is

6  x  y
 , 0  x  2,2  y  4
f ( x, y )   8 . Find the value of P(X + Y < 3).
0, elsewhere
6  x  y
 , 0  x  2,2  y  4
f ( x, y )   8 . Find the value of P(X < 1/Y = 3).
0, elsewhere
6  x  y
 , 0  x  2,2  y  4
f ( x, y )   8 . Find the value of P(X < 1, Y < 3).
0, elsewhere
DAY 3
Course: B. Tech.
Relevant MAKAUT syllabus portion: Conditional densities and independence
Objectives:
Class Notes:
Discrete case: P ( X  xi , Y  y j )  f ij , then the conditional pmf of X on the hypothesis Y  y j is

denoted by f i / j and is defined by f i / j  P ( X  xi / Y  y j ).
Again,
P ( X  xi , Y  y j ) fij f ij
I) f i j  P ( X  xi / Y  y j )    fi / j 
f ij P (Y  y j ) fj fj
Similarly, f j / i 
fi
If the random variables are independent, then f i / j  f i , f j / i  f j and f ij  f i  f j .

Class Notes (contd):
Continuous case: The conditional density function of X on the hypothesis Y = y, denoted by

f ( x, y )
f x ( x / y) 
f y ( y)
f ( x, y )
The conditional density function of Y on the hypothesis X = x, denoted by f y ( y / x ) 
f x ( x)
When the random variables are independent, then f ( x, y )  f x ( x )  f y ( y ).
1. If f ( x, y )  3 x 2  8 xy  6 y 2 0  x  1,0  y  1, find f x ( x / y ) & f y ( y / x ). Hence show

that X & Y are dependent.
2. The joint density function of the random variables X & Y is given by
f ( x, y )  2 (0  x  1, 0  y  x). Find the marginal functions.
3.The joint density function of the random variables X & Y is given by

f ( x, y )  2 (0  x  1, 0  y  x). Find the conditional density functions.
4.The joint density function of the random variables X & Y is given by

f ( x, y )  2 (0  x  1, 0  y  x). Find P 1 / 4  X  3 / 4 / Y  1 / 2 .
DAY 4
Course: B. Tech.
Relevant MAKAUT syllabus portion: Miscellaneous Problems

 x / 2, 0  x  1

1.A variable X has the pdf f ( x)  1 / 2, 1  x  2 . Find the mean and variance of X.
(3  x) / 2. 2  x  3

2.The pdf of a random variable X is f ( x)  k ( x  1)(2  x), 1  x  2

5 3
Determine (i) the value of k (ii) the distribution function (iii) P  X  .
4 2
8
3.The mean and s.d. of a binomial diostribution are respectively 4 & . Find P(X = 0).
3
4.A box contains 5 defective and 10 non-defective lamps. 8 lamps are drawn at random. In
succession without replacement. What is the probability that eigth lamp is the fifth defective?
2
5Find the mean and s.d. of a random variable whose pdf is given by f ( z )  kze  z , z  0.

Module - 4
Basic Statistics
Code: BS M 301
Mathematics II(BSM202) .1.
Measures of Central tendency: Moments, skewness and Kurtosis - Probability distributions:
Binomial, Poisson and Normal - evaluation of statistical parameters for these three
distributions, Correlation and regression - Rank correlation. (6L)
3.Course Outcomes:
Statistics is a statement of facts or simply data related to a field of enquiry and the scientific
methods for analysis and interpretation of such data.
i) Computer Science and Statistics are different disciplines. Statisticians are devising new
theories for using data for decisions and Computer Scientists are inventing efficient methods
for performing the calculations.
ii) Statistics is a form of data processing - a way of converting data into information useful in
decision making.
The subject is widely used in
a) to present facts in a proper form b) to indicate trend behaviour
b) to test a hypothesis d) to draw valid inferences
3. Course Information
PROGRAMME:Engineering DEGREE: B. Tech.
COURSE: ECE SEMESTER:3 CREDITS: 3
COURSECODE: BS- M301 COURSE TYPE: Theory
CORRESPONDING LAB COURSE

CONTACT HOURS: 3L
CODE (IF ANY): NO


1 Measures of Central 4 Moments, skewness & kurtosis
Tendency-Mean
2 Measures of Central 5 Correlation, Rank Correlation
Tendency- Median & mode
3 Measures of Dispersion 6 Regression
Day 1
Course: B. Tech.
Relevant MAKAUT syllabus portion: Measures of Central Tendency- Mean
Objectives: Study of the measures to determine a single value that describes the
characteristics of the entire data
Class Notes:
Mean: If a variate x assumes n values x1 , x2 ,..., xn then its

n
x i
ii) G.M. = G   x1.x2 .    .xn 
1/ n
i) A.M. = A  i 1
n
n
iii) H.M.= H 
1 / x1  1 / x2    1 / xn
If a variate x assumes n values x1 , x2 ,..., xn with corresponding frequencies
n
fx i i
f1 , f 2 ,, f n then its i) A.M. = A  i 1
ii) G.M. =
N
 f f
G  x1 1 .x2 2 .    .xn 
f n 1/ N
iii) H.M.=
N
H , N  f1  f 2     f n and A  G  H
f1 / x1  f 2 / x2     f n / xn
iv)For two distinct observations, A  H  G 2
v)If x be the mean of m observations and y be the mean of n observations then the
mx  n y
combined mean of the (m  n) observations is X 
mn
vi) A.M. depends upon both the change of origin and the change of scale.

1. Find the A.M. of n quantities 1, 3, 5, ---, (2 n -1).

2. The mean mark of 100 students was found to be 40. Later on it was discovered that a mark
3 was misread as 83. What is the corrected mean mark?
3. What is the A.M. of the data 5, 55, 555, ---upto n th term?
4. The AM of a group of n observations is 540 and that of a group of m observations is 460.
If the AM of the merged group is 520, then find the value of n: m
5. Find the AM of the first n natural numbers, the weight of each is equal to that number.
Day 2
Course: B. Tech.
Relevant MAKAUT syllabus portion: Measures of Central Tendency- Median & mode
and the empirical relation among Mean, Median and Mode.
Objectives: Study of the measures to determine a single value that describes the
characteristics of the entire data.
Class Notes:
i)Median (Me): It is the middlemost value of the series arranged in ascending or

descending order of magnitudes. It is the best measure of central tendency for
grouped frequency distribution with open end classes.
ii)Mode (Md): It is the value of the variate occurring most frequently in the data.
iii)Empirical relation among Mean, Median and Mode:
Mean - mode = 3(mean - median)

1. Find the median from the following data:
x 0 1 2 3 4 5 6
f 7 44 35 16 9 4 1
2.The median and the mode of the following frequency distribution are respectively known as
27 and 26.
Value 0-10 10-20 20-30 30-40 40-50
Frequency 3 a 20 12 b

Find the values of a and b.
3.Calculate the mean, median and mode:
Class 10-20 20-30 30-40 40-50 50-60 60-70
Frequency 5 10 14 8 5 2
4.A cyclist reaches his school from his house at a speed of 10 km/hr and back from his school
to his house at 15 km/hr. His average speed in km/hr is
(A) 12.5 (B) 10 (C) 6 (D) 12
5. In a moderately symmetrical distribution, mean = 21, mode = 24, the median would be
(A) 22 (B) 23 (C) 20 (D) 23.5 6.
Day 3
Course: B. Tech.
Relevant MAKAUT syllabus portion: Measures of Dispersion
Objectives: A measure of dispersion is one that calculates numerically the variability of the
observations around its central value.
Class Notes:
    (x  x) 2

x 2
 x2
n n
ii) S.D. does not depend on the change of origin but depends upon the change of scale.
iii) If two groups contain respectively m & n observations with means x & y , s.d.
 1 &  2 , the s.d.   of the combined group is given by
2 2 2 2
(m  n) 2  m 1  n 2  md1  nd 2 where d1  x  z , d 2  y  z and z is the
combined mean of the (m + n) observations.

iv) Coefficient of variation =  100%
x
1. If the s.d. of 1, 2, ---,k is 2, find k.

2. Find the s.d. of the first n natural numbers.
3. Two variables x and y are related by y = 10 - 3x. If the s.d. of x is 4, find the s.d. of y.
4.Calculate the s.d. from the following table:

Class 10-20 20-30 30-40 40-50 50-60 60-70
Frequency 5 10 14 8 5 2
5.The runs of two batsmen A & B in 5 consecutive innings are
A: 72 32 45 57 63
B: 50 80 42 34 70 Who is more consistent?
Day 4
Course: B. Tech.
Relevant MAKAUT syllabus portion: Moments, Skewness and Kurtosis
Objectives: The measures Moments, Skewness and Kurtosis describe the extent of
symmetry or asymmetry in a distribution.
Class Notes:
i) Moment;
1
r-th moment about A =  x  Ar , r  1,2,3,  
n
1
ii) r-th central moment =   x  x  , r  1,2,3,   [ x is the mean of x]
r
n
iii) For any distribution, the value of the first central moment = 0
iv) Skewness= (Mean - Mode)/(s.d.)
m
v) Coefficient of Kurtosis = 44 , m4 is the fourth central moment and  is the s.d. of

the distribution.
xviii) A.M.
1. If the first moment of a distribution is 2 about the value 2; find the mean.
2. Find the first and second central moments of 2, 4, 6, 8
3. If the second and third central moments of a distribution are 4 and 10, find the skewness of
the distribution.
4. The first three moments about the value 2 are 4, 65 and 325. Find its mean and s.d.
5.The first three moments about the value 2 are 4, 65 and 325. Find its moment measure of
skewness.

Day 5
Course: B. Tech.
Relevant MAKAUT syllabus portion: Correlation, Rank Correlation
Objectives: Correlation is a statistical technique that measures and analyses the nature and
the degree of relationship between two variables.
Class Notes:
Formulae:
i) Correlation coeff. between x and y is rxy  cov( x , y ) , cov( x , y )  1 ( x  x )( y  y ).
 x . y n
ii)  1  r  1.
iii) If r  0  x & y are uncorrelated.
r  1  a perfect positive correlation between x & y.
r  1  a perfect negative correlation between x & y.
iv) Rank Correlation coeff. between x and y is 6 D 2
R 1 2
,
N (N  1)
where D = difference of ranks in the two series and N = number of paired
observations.
x
y 
1. If r  1.2, r x  0.3, find r.
x y
2. If two variables are connected by the relation 6x - y =10, find the correlation coeff.
between x and y.
3. Calculate the correlation coeff. from the following:
x 10 12 13 16 17 20 25
y 19 22 24 27 29 33 37
4. Calculate the rank correlation coeff. from the following:
Class A 5 3 2 1 4 7 8 6
Class B 4 2 1 3 5 8 6 7

5.If X  x  x , Y  y  y & X 2
 10, Y 2
 24,  XY  12 then find the correlation
coefficient between x & y.
Day 6
Course: B. Tech.
Relevant MAKAUT syllabus portion: Regression
Objectives: Regression is a mathematical measure for estimation of the average value of one
variable for a given value of the other variable when the two variables are related.
Class Notes:
Formulae:
i)Regression equation of y on x: y  y  b yx  x  x , b yx  r  y
x
ii)Regression equation of x on y: x  x  b xy  y  y , b xy  r  x . b yx  b xy  r 2
y
iii)The regression lines intersect at means.
The regression lines are coincident if r = +1 or - 1
The regression lines are orthogonal if r = 0.
1. Given  x  9 , Regression equations are 8x - 10y + 66 = 0 and 40x - 18y =214. Find
(a) Means of x and y (b) Correlation coeff. between x and y ( c) S.D. of y.
2. If rxy  0.6,  y  4, byx  0.48, then find the value of  x .
3. From the following data, find the two regression equations:
x 1 2 3 4 5
y 2 2 5 4 6
4. Two regression lines are 5x + 12y = 7, 3x + 8y = 11. Identify the regression lines.
5. If x  6, y  7, b yx  0.45, b yx  0.65, find the equation of the two regression lines.

Module - 5: Applied Statistics (6 L)

Code: BS-M 301
Pre-requisites: Probability and Statistics of High School Level,
Detailed Syllabus: Applied Statistics:
Module 5
Curve fitting by the method of least squares- fitting of straight lines, second degree parabolas
and more general curves. Test of significance: Large sample test for single proportion,
difference proportions, single mean, difference of means and difference of standard
deviations. (6 L)
1. Recommended Books:
2. Course Outcomes:
The following questions help to classify the problem related to a statistical problem:
(i) What is the population related to data/problem that has to be described?
(ii) What are the sources of variation?
(iii) How should the data be reduced?
Outcomes:
The subject
(i) helps to answer some queries related to a given set of numerical data
(ii) has the capability to group and classify the given set of numerical date
(iii) can perform tasks related to different analyses such as factor analysis, principle
component analysis, independent component analysis etc.
(iv) can render different statistical methods that can measure the correctness of the results for
a query.
(v) can develop different statistical techniques that are used to design statistical models for
estimation and prediction. Using these models, statistical methods are used to collect, sample
data. The sample data is utilized for gathering knowledge by the method of learning or
parameter estimation.
(vi) can render techniques for choosing between alternatives known prior to the investigation.


1 Curve fitting by the 4 Test of significance: Large sample
method of least squares- test for single proportion and
fitting of straight lines difference of proportions
2 Curve fitting by the method 5 Large sample test for single mean
and difference of means
of least squares- second
degree parabolas and more

general curves
3 Test of significance. 6 Large sample test for difference of

standard deviations.
DAY 1
Course: B. Tech.
Relevant MAKAUT syllabus portion: Curve fitting by the method of least squares- fitting
of straight lines (fitting of straight lines having odd & even number of observations)
Objectives:
The method of least squares is applied to compute the best fitting values of the parameters in
the polynomial curves (straight line, parabola) and exponential curves (reducible to linear
form).
Class Notes:

Let the equation of the best fitting straight line fitted to n pairs of observations
(xi, yi), i = 1,2,---, n be y = a + bx
n 2
D    yi  a  bxi 
i 1
The parameters a & b are determined by solving the equations

 y  na  bx &  xy  a x  b x 2
Simplification of calculation:
Case I. when n is odd:

x  (mean value of x)
The mid-point is taken as the origin and take u 
common difference
so that u  0
Case II. when n is even:
The mid-point is taken as the origin and take
x  (mean value of x)
u so that  u  0
1
(common difference )
2
1. Fit a straight line by the method of least squares to the following data:
x 60 61 62 62 64
y 40 42 48 52 55
2. Fit a straight line by the method of least squares to the following data:
x 15 20 25 30 35
y 12 14 18 25 31
3. Find the equation of the best fitted straight line for the following bivariate data:
x 2 4 6 8
y 10 20 25 30
4. Fit a straight line by the method of least squares to the following data :
x 15 20 25 30 35 40
y 12 14 18 25 31 44

5. Fit a straight line by the method of least squares to the following data :
x 0 5 10 15 20 25 30
y 10 14 19 25 31 36 39
DAY 2
Course: B. Tech.
Relevant MAKAUT syllabus portion: Curve fitting by the method of least squares- (fitting
of second degree curves- parabolas)
Objectives:
The method of least squares is applied to compute the best fitting values of the parameters in
the polynomial curves (parabola) having three parameters a, b, c. It has applications in
estimation of production, population etc.
Class Notes:
Let the equation of the best fitting parabola fitted to n pairs of observations
(xi, yi), i = 1,2,---, n be y = a + bx + cx2.
2
 
n
D   yi  a  bxi  cxi
2
i 1
By choosing suitable origin and the scale similar in straight lines) ,

the parameters a, b and c are determined by solving the equations
 y  na  c u 2 ,  uy  b u 2 &  u 2 y  a u 2  c u 4
1. Fit a second degree parabola by the method of least squares to the following data:
x 0 1 2 3 4
y 1 5 10 22 38
2. Fit a a second degree parabola by the method of least squares to the following data and
estimate the value for 1979:
Year 1973 1974 1975 1976 1977
Production (in 10 12 13 10 8
‘000 units)
3.Fit a a second degree parabola y  a  bx  cx 2 by the method of least squares to the

following data:

x 0 1 2 3 4
y 1 5 10 22 38
4.The profit of a company in a year are given in the following table:

x (year) 1 2 3 4 5
y(profit in thousand D) 1250 1400 1650 1950 2300
Fit a a second degree parabola y  a  bx  cx 2 by the method of least squares to the

following data and estimate the profit in the sixth year.
5.Fit a a second degree parabola y  a  bx 2 by the method of least squares to the following
data:
x 0 1 2 3
y 1 6 20 48
DAY 3
Course: B. Tech.
Relevant MAKAUT syllabus portion: Test of significance

Objectives: In every branch of engineering and technology, assumptions (called hypothesis)
are made on the parameters of the population on the basis of the sample information
(statistic). It is impossible to make a decision with perfect certainty about the acceptance or
rejection of the hypothesis (decision). So, it is to be stated how much of confidence can be
achieved on such a decision that is how much the test is significant. So, the tests are called
Test of significance.
Class Notes:
Two types of Hypothesis:

1.Null hypothesis H 0  : Any hypothesis can be set as a Null hypothesis.
2.Alternative hypothesis H 1  : Any hypothesis against which a null hypothesis is
tested is Alternative hypothesis.
Level of significance: The max probability with which we are willing to risk the
Type I error. The commonly used the level of significance are 5% or 1%.
Critical region: For a given level of significance if the statistic computed to test the
hypothesis falls in this region W  , the hypothesis is rejected.
Acceptance region: The rest of the sample space W  is acceptance region.

Level of significance Accept Reject
5% -1.96 ≤ z ≤ 1.96 |z| > 1.96
1% -2.58 ≤ z ≤ 2.58 |z| > 2.58
1. In order to test whether a coin is perfect, the coin is tossed 5 times. The null hypothesis of
perfectness is rejected if more than 4 heads are obtained. The probability of Type I error is
(A) 1/8 (B) 1/16 (C) 1/32 (D) 1/64
perfectness is rejected if more than 4 heads are obtained. Find the probability of Type II error,
when the corresponding probability of head is 0.2
3. To test the unbiasedness of a die it is thrown 6 times and is accepted that unbiasedness if not
more than one six is obtained. Find the probability of Type I error.
4. Let P denotes the probability of getting a head when a given coin is tossed once. Suppose
that the hypothesis H0:P=0.5 is rejected in favour of H1:P=0.6, if 10 trials result in 7 or more
heads. Calculate the probability if Type I error.
5. Let P denotes the probability of getting a head when a given coin is tossed once. Suppose
that the hypothesis H0:P=0.5 is rejected in favour of H1:P=0.6, if 10 trials result in 7 or more
heads. Calculate the probability if Type II error.
DAY 4
Course: B. Tech.
Lecture 4 (60 minutes)Test of significance: Large sample test for single proportion and
difference of proportion

Class Notes:

At 95% level p p  1.96( S .E. of p )

At 959% level p p  2.58( S .E. of p )
pP
The test statistic z  , p  sample proportion , P  population proportion l
P (1  p )
n
Confidence limits for difference of population proportion (P)
At 95% level p p  1.96( S .E. of p )

At 99% level p p  2.58( S .E. of p )
The test statistic
X  np
z , p  sample proportion , P  population proportion l
np (1  p )
1. A coin is tossed 900 times and heads appear 490 times. Does the result support the
hypothesis that the coin is unbiased?
2. A whole seller in apples claim that 4% of the apples supplied by him is defective. A
random sample of 600 apples contained 36 defective apples. Test the claim of the wholesaler
at 95% level of significance.
3.The manager of the circulation department of a weekly magazine claimed that 90% of its
subscribers would renew their subscriptions. A sample of 100 subscribersshowed that 81
renewed their subscriptions. Is there sufficient evidence that the manager is wrong? Test at
1% significance level. Given P(0<z<2.58) = 0.495
perfectness is rejected if more than 4 heads are obtained. What is the probability of Type I
error? Find the probability of Type II error when the corresponding probability of head is 0.2.
5. A machine produced 50 defective units in a random sample of 1000 and after overoiling, it
produced 38 defectives in a random sample of 500. Using 1% significance level, test whether
the data can support the claim that the machine improved due to overoiling. Given P(Z>2.33)
= 0.01 where Z is a standard normal variate.

DAY 5
Course: B. Tech.
Relevant MAKAUT syllabus portion: Large sample test for single mean and difference of
means

Class Notes:
x1 , x 2 ,  , x n be a random sample of size n, mean m, s.d.  .

H0: m = m0, H1:m > m0, H2:m < m0,H3:m  m0 at preassigned level of significance.
x  m0
Test statistic u 
/ n
The critical value u  if alternative hypothesis is H 1 or H 2 & u  / 2 if H 3 .
Reject H 0 at level  if
(i) u  u  when alternative hypothesis is H 1
(ii) u  u  when alternative hypothesis is H 2
(iii) u  u  / 2 when alternative hypothesis is H 3 .
We can not reject H 0 otherwise.
 12  2 2
For 2 sample test, test statistic Z 0  ( x1  x 2 ) / 
n1 n2

1. A random sample with observations 65, 71, 64, 71, 70, 69, 64, 63, 67, 68 is drawn from a
normal population with variance 7.056. Test the hypothesis that the population mean is 69 at
1% level of significance. Given P(0 < Z < 2.58) = 0.495
2. From a random sample of size 100, mean 105, s.d. 20 test at 1% level whether the mean of
population can be less than 120. Given z 0.01  2.33
3. A machine part was designed to withstand an average pressure of 120 unit. A random
sample of size 100 from a large batch was tested and it was found that the average
pressurewhich these parts can withstand is 105 units with a s.d. of 20 units. Test at 5% level
whether the batch meets the specification. Assume the population has a normal distribution.
Given P(Z > 1.645) = 0.05, Z is a standard normal variate.
4. The means of two large samples of sizes 1000 and 2000 are 67.5 & 68.0 respectively. Test
the equality of means of the two normal population each with a s.d. 2.5 at 0.5% level.Given
the area under standard normal curve is 0.25 from z = 0 to z = 0.0987.
5. A college conducts both day and night classes intended to be identical.
Shift Sample size Sample mean Sample variance
Day 100 72.4 14.8
Night 200 73.9 17.9
Are the two means statistically equal at 10% level? Given P(0 < z < 1.645) = 0.05
DAY 6
Course: B. Tech.
Relevant MAKAUT syllabus portion: Large sample test for difference of standard
deviations.

Class Notes:
 x  x
2
i
2 nS 2
Test Statistic:   i 1
 H 0 is rejected if
 02  02
2
 2    ,   level of significan ce,   population mean,
S  sample s.d . and  0 is defined by H 0 (   0 ).
1. A random sample of size 31 drawn from a normal population gives a sample mean 42 and
a sample s.d. 5. Test at 5% level the hypothesis that the population s.d. is 7.
2.A sample 4, 5, 6, ---, 32, 33 of size 30 is drawn from a population with mean 4. It is
assumed that the s.d. of the population is 3. Test this assumption at 0.1% level of significance.
2
[Given  2 .001  59.703 with 30 d . f . and  .001  58.302 with 29 d . f .]

3.The s.d. of a random sample of size 12 drawn from a normal population is 5.5. Calculate
the 95% confidence limits for the s.d.  in the population.
2
[Given  2 .975  3.82 and  .025  21.92 with 11 d . f .]
4.A sample of size 8 from a normal population yields as the unbiased estimate of population
variance the value 4.4. Obtain the 99% confidence limits for the population variance  2 .
2
[Given  2 .975  0.99 and  .025  20.3 with 7 d . f .]
5.In a random sample of 1000 persons from city I, 500 are found to be consumers of wheat.
In another random sample of 900 from city II, 400 are consumers of wheat. Do these data
reveal a significant difference between these two cities with respect to wheat consumers?
Test at 1% significant level. [Given P(Z>2.58) = 0.005, Z is a standard normal variate.]
Module - 5: Small Samples (4 L)

Code: BS-M 301
Pre-requisites: Probability and Statistics of High School Level,
Module 6: Small samples: (4L)
Test for single mean, difference of means and correlation coefficients, test for ratio of
variances - Chi-square test for goodness of fit and independence of attributes.
2. Recommended Books:
3. Course Outcomes:
The following questions help to classify the problem related to a statistical problem:
(iv) What is the population related to data/problem that has to be described?
(v) What are the sources of variation?
(vi) How should the data be reduced?
Outcomes:
The subject
(vii) helps to answer some queries related to a given set of numerical data
(viii) has the capability to group and classify the given set of numerical date
(ix) can perform tasks related to different analyses such as factor analysis, principle
component analysis, independent component analysis etc.
(x) can render different statistical methods that can measure the correctness of the results for
a query.
(xi) can develop different statistical techniques that are used to design statistical models for
estimation and prediction. Using these models, statistical methods are used to collect, sample
data. The sample data is utilized for gathering knowledge by the method of learning or
parameter estimation.
(xii) can render techniques for choosing between alternatives known prior to the investigation.

1 Test for single mean 3 Test for ratio of variances and
correlation coefficients
2 Test for difference of means 4 Chi-square test for goodness of fit

and independent attributes
DAY 1
Course: B. Tech.
Relevant MAKAUT syllabus portion: Test for single mean
Objectives: In this chapter, the test of significance/hypothesis will be conducted by drawing

samples of smaller size (size < 30). As samples of large size may not be always available ,
these tests are sometimes convenient.
Class Notes:
x 
1. Test for single mean: Test stastistic z  , S .E .  . If z falls in the critical
S .E . n
region, shown below H 0 is rejected.
Rejection rules for H 0 :
H1 5% level 1% level
  0 | z | 1.96 | z | 2.58
  0 z  1.645 | z  2.33
Let’s
   0learn by
z doing:
1.645 z  2.33

1. A tyre manufacturing claims that the average life of their product is 69 thousand miles. A
car manufacturing company planning to purchase tyre collect a sample of 10 tyre’s life from
the population of life of tyres which are 65,71,64,71,70,69,64,63,67 and 68 thousands of
miles. It is known that the population is normal and the variance of the population is 7.056.
Test at 5% level of significance that the average life of tyre of the company is lower than they
claim. [Given z .05  1.65]
2. A random sample of size 10 was taken from a normal population, whose variance is 7.056
sq. Inches. If the observations in inches are 65,71,64,71,70,69,64,63,67 and 68, test the
hypothesis that the population mean is 69 inches at 99% confidence limit.
3. A man buys 50 electric bulbs of brand A and 50 electric bulbs of brand B.He finds that A
brand bulbs gave an average life of 1500 hours with a s.d. of 60 hours while B brand bulbs
gave an average life of 1512 hours with a s.d. of 80 hours. Is there a significant difference in
the mean life of the two brands at 1% level of significance?
4. A manufacturer of video display unit is testing two micro circuit designs to find whether
they produce equivalent current flow. The following data was recorded:
Type Sample size Sample mean Sample variance
Design 1 25 22.1 18
Design 2 20 24.2 19
Using 5% signifance level, determine whether there is any difference in mean current
flowbetween two designs. It is assumed that both the populations to be normal with unknown,
unequal variances. Given P(t > 2.021) = 0.025 for 40 d.f.
5. Nine patients to whom a certain drug was administered, registered the following rise in
blood pressure: 3, 7, 4, -1, -1,6,-4, 1, 5.
Test the hypothesis that the drug does not raise BP at 10% level of significance.
Assume that the sample is from a normal population. Given P(z>1.86)=0.05 for 8 degrees of
freedom.
DAY 2
Course: B. Tech.
Relevant MAKAUT syllabus portion: Test for difference of means

Class Notes:

1. Test for equality of means: H 0 : 1   2 and H 1 : 1   2
Test statistic
n1 n 2 n1  n 2  2  x1  x 2
t . which is a t var iate with n1  n 2  2 d . f .
n1  n 2 2
n1 S1  n 2 S 2
2

1. Two types of batteries are tested for their length of life distributed normally and the
following data is obtained.
No. of batteries Mean life (hours) variance
Type A 9 600 121
Type B 8 640 144

Is there a significant difference in the life time of the two types of batteries? Value of t for 15
d.f. at 5% level is 2.131.
2. A group of 5 patients treated with medicine A weigh 42, 39, 48, 60, 41 kg. A second group
of 7 patients from the same hospital treated with medicine B weigh 38, 42, 56, 64, 68,69,62
kg. Do you agree with the claim that medicine B increases the weight significantly?
[The value of t at 5% level of significance for 10 d.f. is 2.2281]
3. A manufacturer of video display units is testing two micro-circuit designs to find whether
they produce equivalent current flow. The following data was recorded:
Sample size Sample mean Samplev ariance
Design 1 25 22.1 18
Design 2 20 24.2 19
Using 5% significance level, determine wether there is any difference in mean current flow
between two designs. It is assumed that both the populations to be normal and with unknown,
unequal variances. [Given P(t>2.021) = 0.025 for 40 d.f.
4. A drug is given to 10 patients and the increase in their blood pressure were recorded as
3, 6, -2, 4, -3, 4, 6, 0, 0, 2. Is it reasonable to believe that the drug has no effect on change of
blood pressure? [5% value of t for 9 d.f. is 2.26]
5.A certain diet newly introduced to each of the pigs resulted in the following increase in
body weight: 6, 3, 8, -2, 3, 0, -1, 1, 6, 0, 5 and 4. Can we conclude that the diet is effective in
increasing the weight of the pigs? [Given t .05,11  2.20] [Take H 0 (   0), H 1 (   0)]

DAY 3
Course: B. Tech.
Test for ratio of variances and correlation coefficients

Class Notes:
1. Test for Ratio of Variances: H 0 : 1   2 and H 1 : 1   2
Test statistic:
2
s1 2 n1 2 2 n2 2
F where s1  S1 & s 2  S 2 which is Snedecor ' s
s2
2
n1  1 n2  1
F var iate with n1  1, n 2  1 d . f .
2. Test for difference of correlation coefficient:
z1  z 2 1 1  r1 1 1  r2
Test statistic: z  , Z1  log , Z 2  log
1 1 2 1  r2 2 1  r2

n1  3 n 2  3
2
n n2 s
S 2 and F  1 2 with n1  1, n 2  1 d . f .
2 2 2 2
3. s1  1 S1 , s 2 
n1  1 n2  1 s2
1. Two random samples of sizes 9 and 13 are drawn from two normal population. It is
observed that the s.d. of the two samples are 2.1 and 1.8 respectively. May we suppose that
the s.d. of the second population is greater than that of the first population. Test at 5% level.
[Given P(F>3.28) = 0.05 for d.f. 12,8]
2. In a sample of 8 observations, the sum of the squared deviations of the items from the
mean was 94.5. In another sample of 10 observations, the value was found to be 101.7. Test
whether the difference is significant at 5% level. [Given area under the F curve enclosed
between the ordinates at 3.29 and  is 0.05 with (7,9) d.f. and 3.07 with (8,10) d.f.

3.The following results were obtained from two independent random samples:
Sample size Mean S.D.
Sample I: 6 29 4.0
Sample II: 5 25 2.1

Test at 5% level whether the two samples may be regarded from the same normal population.
[Given t .025  1.82 for 9 d . f . and F.05  6.26 for (5,4) d . f .
4.Two independent samples of sizes 16 and 18 are drawn from a normal bivariate population.
It is observed that the correlation coefficient between the variables in the two samples are
0.40 & 0.68 respectively. Test at 5% level of significance whether the correlation coefficient
of the variates in the two population is same.
[Given area under normal curves between the ordinates z = -1.96 and z = 1.96 is 0.95]
5.To compare the caffeine content of two brands of coffee, the caffeine contents of 100 gm
jars of both the brands are measured. A random sample of 30 jars of brand I and another
random of 33 jars of brand II are taken. The mean caffeine content obtained from 30 jars of
brand I is found to be 17.61 mg per 100 gm jar with a s.d. of 0.41 mg. The mean caffeine
content obtained from 33 jars of brand II is found to be 17.64 mg per 100 gm jar with a s.d. of
0.51 mg. Assuming that the population of caffeine contents of coffee of two brands are
normally distributed with unequal variances, test at 5% significant level whether the caffeine
contents are equal for the two brands.
[Given P(t > 2) = 0.025 with 60 d.f.]
DAY 4
Course: B. Tech.
Chi-square test for goodness of fit and independent attributes
Objectives: Several types of surveys and experiments result in qualitative or categorical data
where quality or characteristic is recorded for each unit and the no. of units are counted
having same characteristic.Our objective is to see how will the expected cell count match
with the observed count.

Class Notes:
1.Test statistic:
 f 0  f e 2
2   , f 0  observed frequency , f e  exp ected frequency , the
fe
summation is taken over all classes. It has  2 distribution with k-1 d.f.

1. The following table gives the number of aircraft accidents that occurred during various
days of the week.Test whether the accidents are uniformly distributed over the week.
Day Sun Mon Tues Wed Thurs Fri Sat
No. of accidents 13 14 19 12` 11 15 14
2
[Given  0.05 (v  6)  12.59 ]
2. A die is thrown 150 times with the following results:

No. turned up 1 2 3 4 5 6
Frequency 19 23 28 17 32 31
Test the hypothesis that the die is unbiased.
[Given  2 0.05 (v  6)  12.59 ]
3. The number of road accidents per week in a certain area were as follows:
12, 8, 20, 2, 14, 10, 15, 6, 9, 4
Are these frequencies in agreement with the belief that accident conditions were same during
10-week period.
[Given  2 0.05 (v  9)  16.919 ]
4. Among 80 offspring of a certain cross between guinea pigs, 25 were white, 48 were red
and 7 were black. As per the genetic model, these numbers should be in the ratio 4:9:3. Are
the data consistent with the model at 5% significance level?
[Given P  2  5.991  0..05 for 2 d . f . ]
5. To observe the colour preference of a 2-year old child three balls of different colours, viz,
red, blue, green are placed together in front of the child to choose one. This repeated for 105
times and the choices are recorded as follows:
Colour Red Blue Green
Observed count 48 20 37
Does the child have a preference for one of the three colours? Test at 1% significance level?
[Given P  2  9.210   0..01 for 2 d . f . ].

Mathematics III Probability Concepts

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Mathematics III Probability Concepts

Uploaded by

Copyright:

Available Formats

Paper Name: Mathematics III 1 Paper Code: BS M301

Institute of Engineering & Management

Department of ELECTRONICS & COMMUNICATION

Paper Name with code: Mathematics III; BS M301

Name of the Student:

1|Page Study Material, IEM, ECE Department

Module I:Basic Probability [8 L]

2|Page Study Material, IEM, ECE Department

PROGRAMME:Engineering DEGREE: B. Tech.

COURSE: ECE SEMESTER: 3 CREDITS: 3

COURSECODE: BS M 301 COURSE TYPE: Theory

CORRESPONDING LAB COURSE

5.Day-wise Lesson Plan:

LECTURE Topics/Sub- topics LECTURE Topics/Sub- topics

3|Page Study Material, IEM, ECE Department

Lecture 1 (60 minutes)

Class Notes: Definition of probability:Let P be a function from

Axiom I. P(A)  0 for every event A in  (class of all events)

(iii) Classical Definition of probability: If a random experiment has n (finite) mutually

(iv) Theorem of Total Probability: For any two events A and B,

Let’s learn by doing:

4|Page Study Material, IEM, ECE Department

3. Consider the following experiment:

Let’s learn by doing:

5|Page Study Material, IEM, ECE Department

Company % of computers supplied Prob. of being defective

Given that a computer is defective, the probability that it was supplied by Y.

Lecture 3 (60 minutes)

6|Page Study Material, IEM, ECE Department

Let’s learn by doing:

1. If a random variable X takes the values 1, 2, 3 and 4 such that

2. If f ( x )  kx, x  1,2,  , n be the p. m. f. of a random variable X , then the mean of X is

3. A random variable X has the following probability distribution:

Then find P(0< X < 5).

Lecture 4 (60 minutes)

(i ) E ( X )   x.P ( X ), E (c)  c, E (cX  b)  cE ( X )  b, E (aX  bY )  aE ( X )  bE (Y )

(ii)If X and Y are independent events then E(XY) = E(X).E(Y)

(iv) If X and Y are independent events, var(aX  bY )  a 2 var( X )  b 2 var(Y )

7|Page Study Material, IEM, ECE Department

Let’s learn by doing:

Lecture 5 (60 minutes)

Objectives: In this chapter, we shall deduce mathematically the expected frequency

8|Page Study Material, IEM, ECE Department

1. Binomial Distribution: The probability of x successes in n independent trials P(X = x) = f(x)

1.For a Binomial (6, p ) distribution, P ( X  2)  9 P ( X  4). Then find the value

9|Page Study Material, IEM, ECE Department

ii)Tchebyshev’s Inequality: If X is a random variable having mean m and standard

Let’s learn by doing:

1. What is the probability of at least r successes in n Bernoulli’s Trials?

Miscellaneous problems on probability, mean & variance of discrete random variable

Lecture 7 (60 minutes)

Let’s learn by doing:

10 | P a g e Study Material, IEM, ECE Department

Miscellaneous problems on Discrete probability distributions

Lecture 8 (60 minutes)

Let’s learn by doing:

11 | P a g e Study Material, IEM, ECE Department

.1. Detailed Syllabus:

12 | P a g e Study Material, IEM, ECE Department

4.Day-wise Lesson Plan:

LECTURE Topics/Sub- topics LECTURE Topics/Sub- topics

2 PDF and CDF of Exponential 4 Gamma distribution

Continuous random variables and their properties, PDF & CDF