Study Material

Subject Name: Mathematics III `Subject Code: BTH---BSC301

Module 1: Random Variables & Probability Distributions

Discrete Random Variable; Discrete Probability Distribution, Expectation and Variance of
random variables; Binomial and Poisson Distributions; Mean, Variance and Moment Generating
Functions of Binomial and Poisson Variates; Convergence of Binomial to Poisson Variate.
Continuous Random Variable; Continuous Probability Distributions, Expectation and Variance of
random variables, Exponential, Normal and Gamma Distributions; Mean, Variance and Moment
Generating Functions of the corresponding variates.
Tchebycheff’s Inequality and Weak Law of Large Numbers (Statement only).

If each value of a variable is associated with a definite probability of occurrence then the
variable is termed as random variable. The array of the various values of a random variable
in a random experiment with the corresponding probability associated with each value of the
variable is called probability distribution of the random variable.
1.BINOMIAL DISTRIBUTION :
A Binomial Distribution is applied when a Bernoulli’s Trial is repeated n times with the
following conditions
• Each trial results in two possible outcomes (Success or Failure)
• Probability of a success, denoted by p, remains constant
• Trials are independent

Probability of having r (r=0,1,2,….,n) successes in those n trials is calculated by BINOMIAL

DISTRIBUTION.
The PMF of this distribution is
� � = � = ��� �� (1 − �)�−� , r = 0,1,2,…,n.

2.POISSON DISTRIBUTION :
A discrete random variable X is said to have a Poisson distribution with parameter µ>0 if its
p.m.f is given by
�−� ��
� �=� = , � = 1,2,3, ….
�!
• Poisson distribution is applied when probability of ‘r’ times occurrence of an event is
to be calculated and average number of occurrence of that event is known in an
interval.
3.NORMAL (GAUSSIAN) DISTRIBUTION �(�, �� ) :
X is a continuous random variable
Range of X (all possible values) : −∞ �� ∞
PDF of Normal distribution :
−(�− � )2
1
� � =
� 2�
� 2�2 for −∞ ≤ � ≤ ∞ where � ��� � are mean and standard
deviation of X.
The curve of the normal pdf is bell shaped , symmetric about mean �. The total area under the
curve is 1.

Standard Normal Distribution N(0,1)

Random variable Z has standard normal distribution if it is normally distributed with mean 0
and s.d. 1.
−(� )2
1
PDF of N(0,1) is � � = 2�
� 2�2 for −∞ ≤ � ≤ ∞

−(� )2
� 1
CDF of N(0,1) is commonly denoted by � � , � � = � � ≤ � = −∞ 2�
� 2�2 ��

The value of � � is widely tabulated.

Probability Calculation Procedure :
�−�
Use the transformation � = �
, to convert the �(�, �2 ) variate to N(0,1) variate. Then get
the value of corresponding � �
4.Exponential Distribution :
X is a continuous random variable
Range of X (all possible values) : 0 �� ∞
PDF of X is � � = ��−�� , � ≥ 0

The curve of this PDF is

QUESTIONS
MODULE I

Sl. No. Question M BL

ar
ks
1 Find the Harmonic mean of the random variable X, the p.d.f. being 5 BL 4
6( x  x 2 ), 0  x  1
f ( x)   .
0, elsewhere

The H.M. H is given by 1/H = E(1/x)

2 Find the Geometric mean of the random variable X, the p.d.f. being 5 BL 4
6(2  x)( x  1), 1  x  2
f ( x)   .
0, elsewhere

The G.M. G is given by log G = E(log X)

3 A manufacturing unit producing CFL bulbs, finds that 0.1% of the 5 BL 4
products are defective. The bulbs are placed in boxes containing 500
CFLs. A retailer buys 100 boxes from the manufacturer. Using
Poisson Distribution, find how many boxes will contain (i) no
defective (ii) at least 2 defective (iii) at most 2 defective.
[e 0.5  0.6065]
Hints : Use Poisson Distribution to solve the above question
4 Geysers manufactured by a manufacturer have an average end of 10 BL 5
life of 5 years. The life span of each geyser follows an exponential
distribution. (a) Write the probability density function and graph it
(b) What is the probability that a geyser will last less than 3 years
(c) What is the probability that a geyser will last more than 10
years? (d) What is the probability that a geyser will last between 4
and 7 years? Answer Key: a) Exponential distribution and its graph
b) 0.4512 c) 0.1353 d) 0.20273

5 A test is conducted for the issue of driving licence. The scores of 10 BL 6

this test are normally distributed with a mean of 500 and a standard
deviation of 100. Avon wants to take the test and he has to score
better than at least 70% of the applicants who took the test. Avon
took the the test and scores 585. Analyze the situation and predict
whether Avon will be issued a licence?
Hints : Use Normal Distribution to solve the question
6 Fit a binomial distribution to following data, when tossing 5 coins. 10 BL 6
X 0 1 2 3
F(x) 2 14 20 34

Hints : Find mean from the given table. Hence find p & q. Thus
construct the Binomial Distribution table.
7 There are 600 business students in the post-graduate department of a
university. The probability for any student to need a particular copy
of a text book from the university library on any day is 0.05. How
many copies of the text book should be kept in the library so that the
probability may be greater than 0.90 that none of the students
needing a copy from the library has to come back disappointed.
Hints: Binomial distribution fitted to Normal distribution.
8 A target is made is made of three concentric circles of radii 10 6
1 / 3 ,1, 3 feet. Shots within the inner circles give 4 points, within
the next ring 3 points and within the third ring 2 points. Shots
outside the circles give 0.
Let X be the distance of the hit from the centre (in ft.) and let the
 2
 ,x 0
p.d.f. of X be f ( x)    (1  x 2 ) . What is
0, elsewhere

the expected value of the score in a single shot?

Module II: Method of Least Squares and Curve Fitting

Principle of Least Squares, Curve fitting by the method of Least Squares - fitting of straight lines,
second degree parabolas and exponential curves.

When we fit a regression line to set of points, we assume that there is some unknown linear
relationship between Y and X, and that for every one-unit increase in X, Y increases by some
set amount on average. Our fitted regression line enables us to predict the response, Y, for a
given value of X.

But for any specific observation, the actual value of Y can deviate from the predicted value.
The deviations between the actual and predicted values are called errors, or residuals.
The better the line fits the data, the smaller the residuals (on average). How do we find the
line that best fits the data? In other words, how do we determine values of the intercept and
slope for our regression line? Intuitively, if we were to manually fit a line to our data, we
would try to find a line that minimizes the model errors, overall. But, when we fit a line
through data, some of the errors will be positive and some will be negative. In other words,
some of the actual values will be larger than their predicted value (they will fall above the
line), and some of the actual values will be less than their predicted values (they'll fall below
the line).
If we add up all of the errors, the sum will be zero. So how do we measure overall error? We
use a little trick: we square the errors and find a line that minimizes this sum of the squared
errors.

This method, the method of least squares, finds values of the intercept and slope coefficient
that minimize the sum of the squared errors in case of a straight line fitting. The equation that
gives the picture of the relationship between the data points is found in the line of best fit. It
is calculated by the method of least squares.
Sl. No. Question Marks BL No.
1 As the number of units manufactured increases from 5,000 to 5 BL 4
7,000, the total cost of production increases from Rs 26,000 to
Rs 34,000. When number of units increases from 7,000 to
8,000, production increases from Rs 34,000 to Rs 38,000.
When number of units increases from 8,000 to 10,000,
production increases from Rs 38,000 to Rs 46,000 and so on.
Find the relationship between the cost (y) and the number of
units made (x), if the relationship is linear and the number of
units manufactured now a day is 19,000.
2 A firm invested Rs. 10 million in a new factory that has a net 5 BL 5
return of Rs. 5,00,000 per year. An investment of Rs. 20
million would yield net income of Rs. 2 million per year. An
investment of Rs. 30 million would yield net income of Rs. 4
million per year. An investment of Rs. 40 million would yield
net income of Rs. 5 million per year. An investment of Rs. 50
million would yield net income of Rs. 7.5 million per year. An
investment of Rs. 60 million would yield net income of Rs. 10
million per year. What is the linear relationship between
investment and annual income? What would be the annual
return on an investment of Rs. 15 million?
3 The amount demanded of a commodity is zero units when the 10 BL 5
price is Rs. 100 and 1,000 units when the price is zero, 5 units
when the price is Rs. 2,000 and 2,000 units when the price is
Rs. 200. If the demand curve is assumed to be a parabola, find
its equation.
4 A firm produces 200 units of a product for a total cost of Rs. 10 BL 5
730, 500 units of the product for a total cost of Rs. 970, 700
units of the product for a total cost of Rs. 1060, 950 units of the
product for a total cost of Rs. 1250, 1100 units of the product
for a total cost of Rs. 1370, 1400 units of the product for a total
cost of Rs. 1680 and 1500 units of the product for a total cost of
Rs. 1975. Assuming the cost curve to be exponential of type
y=axb, derive the equation of this curve and use it to estimate
the cost of producing 400 units, 600 units and 1000 units of the
product.

Module III: Sampling and Sampling Distributions

Population and Sample, Sampling With and Without Replacement (SRSWR and SRSWOR);
Random Samples, Population Parameters, Sample Statistics, Sampling Distributions, Standard
Error and Probable Error; Sample Mean, Sampling Distribution of Means; Sample Proportion,
Sampling Distribution of Proportions, Sample Variances, Sampling Distribution of Variances;
Case where Population Variance is unknown; Central Limit Theorem (Statement only); Degrees
of freedom, Chi-square distribution, Mean & Variance of Chi-square variate.

Sl. No. Question Marks BL

1 The frequency of color blindness (dyschromatopsia) in the 5 5
Caucasian American male population is estimated to be
about 8%. We take a random sample of size 25 from this
population. What is the probability that five individuals or
fewer in the sample are color blind?
2 Distribution of marks scored in an examination is normal. 10 5
Samples of marks of four students are drawn and it is seen
that the probability of the sample mean to be less than 61 is
0.44, to be more than 80 is 0.04. Find the mean and
standard deviation of the distribution.