Downloaded From www.castudynotes.

com

statistics
CA FOUNDATION - PAPER 3 - BUSINESS MATHEMATICS,
LOGICAL REASONING AND STATISTICS

This capsule on Foundation - Paper 3 - Business Mathematics, Logical Reasoning and Statistics , will enable the students
to understand and apply the techniques of developing discrete and continuous probability distributions.

Chapter 17 : Theoretical Distributions

In this chapter we will discuss the probability theory by Binomial Distribution

considering a concept and analogous to the idea of frequency One of the most important and frequently used discrete probability
distribution. In frequency distribution where to the total distribution is Binomial Distribution. It is derived from a particular
frequency to different class intervals, the total probability type of random experiment known as Bernoulli process named
(i.e. one) is distributed to different mass points is known as after the famous mathematician Bernoulli. Noting that a 'trial' is an
theoretical probability distributions. attempt to produce a particular outcome which is neither certain
• Discrete Random variable. nor impossible, the characteristics of Bernoulli trials are stated
• Continues Random variable. below:
(i) Each trial is associated with two mutually exclusive and
exhaustive outcomes, the occurrence of one of which is known
as a 'success' and as such its non occurrence as a 'failure'. As an
Importance of theoretical probability distribution.:
example, when a coin is tossed, usually occurrence of a head is
(a) An observed frequency distribution, in many a case, may
known as a success and its non–occurrence i.e. occurrence of a
be regarded as a sample i.e. a representative part of a large,
tail is known as a failure.
unknown, boundless universe or population and we may be
(ii) The trials are independent.
interested to know the form of such a distribution.
For Example: By fitting a theoretical probability distribution.
• Length of life of the lamps produced by manufacturer
up to a reasonable degree of accuracy. We may note the following important points in connection with
• The effect of a particular type of missiles, it may be binomial distribution:
possible for our scientist to suggest the number of such (a) As n >0, p, q ≥ 0, it follows that f(x) ≥ 0 for every x
missiles necessary to destroy an army position. Also ∑ f(x) = f(0) + f(1) + f(2) + …..+ f(n) = 1
• By knowing the distribution of smokers, a social activist (b) Binomial distribution is known as biparametric distribution as
may warn the people of a locality about the nuisance of it is characterised by two parameters n and p. This means that if
active and passive smoking and so on. the values of n and p are known, then the distribution is known
x
completely.
(b) Theoretical probability distribution may be profitably
employed to make short term projections for the future. (c) The mean of the binomial distribution is given by µ = np
(c) Statistical analysis is possible only on the basis of theoretical (d) Depending on the values of the two parameters, binomial
probability distribution. distribution may be unimodal or bi- modal., the mode of
A probability distribution also possesses all the characteristics binomial distribution, is given by µ0 = the largest integer
of an observed distribution. We define population mean, contained in (n+1)p
population median, population mode, population standard if (n+1)p is a non-integer (n+1)p and (n+1)p - 1 if (n+1)p is an
deviation etc. exactly same way we have done earlier. These integer
characteristics are known as population parameters. (e) The variance of the binomial distribution is given by
σ2 = npq
Since p and q are numerically less than or equal to 1, npq < np
A probability distribution may be either a discrete probability variance of a binomial variable is always less than its mean.
distribution or a Continuous probability distribution depending Also variance of X attains its maximum value at p = q = 0.5 and
on the random variable under study. this maximum value is n/4.
(f ) Additive property of binomial distribution.
If X and Y are two independent variables such that
X~ β (n1, P)
Two important discrete probability distributions
and Y ~ β (n2, P)
(a) Binomial Distribution Then (X+Y) ~ (n1 + n2 , P)
(b) Poisson distribution.

Applications of Binomial Distribution

Important continuous probability distribution Binomial distribution is applicable when the trials are independent
and each trial has just two outcomes success and failure. It is
Normal Distribution applied in coin tossing experiments, sampling inspection plan,
genetic experiments and so on.

The Chartered Accountant Student November 2021 31

28
Join Us on Telegram http://t.me/canotes_foundation
 Downloaded From www.castudynotes.com

statistics
Poisson Distribution (vii) Additive property of Poisson distribution
Poisson distribution is a theoretical discrete probability distribution If X and y are two independent variables following Poisson
which can describe many processes. Simon Denis Poisson of France distribution with parameters m1 and m2 respectively, then Z =
introduced this distribution way back in the year 1837. X + Y also follows Poisson distribution with parameter (m1 +
m2).
Poisson Model
i.e. if X ~ P (m1)
Let us think of a random experiment under the following
and Y ~ P (m2)
conditions:
and X and Y are independent, then
I. The probability of finding success in a very small time
Z = X + Y ~ P (m1 + m2)
interval ( t, t + dt ) is kt, where k (>0) is a constant.
II. The probability of having more than one success in this
time interval is very low.
III. The probability of having success in this time interval is Application of Poisson distribution
independent of t as well as earlier successes. Poisson distribution is applied when the total number of events is
pretty large but the probability of occurrence is very small. Thus we
The above model is known as Poisson Model. The probability of
can apply Poisson distribution, rather profitably, for the following
getting x successes in a relatively long time interval T containing m
cases:
small time intervals t i.e. T = mt. is given by
a) The distribution of the no. of printing mistakes per page of a
for x = 0, 1, 2, ......……… large book.
b) The distribution of the no. of road accidents on a busy road per
Taking kT = m, the above form is reduced to
minute.
for x = 0, 1, 2, ......…..... c) The distribution of the no. of radio-active elements per minute
in a fusion process.
d)
Definition of Poisson Distribution
A random variable X is defined to follow Poisson distribution with
parameter λ, to be denoted by X ~ P (m) if the probability mass
function of x is given by Normal or Gaussian distribution
The two distributions discussed so far, namely binomial and
f (x) = P (X = x) = for x = 0, 1, 2, ... Poisson, are applicable when the random variable is discrete. In
case of a continuous random variable like height or weight, it is
= 0 otherwise impossible to distribute the total probability among different mass
Here e is a transcendental quantity with an approximate value as points because between any two unequal values, there remains an
2.71828. infinite number of values. Thus a continuous random variable is
defined in term of its probability density function f (x), provided,
Important points in connection with Poisson distribution: of course, such a function really exists, f (x) satisfies the following
(i) Since e–m = 1/em >0, whatever may be the value of m, m > 0, condition:
it follows that f (x)≥ 0 for every x. f(x) ≥ 0 for x(-∞,∞) and =
Also it can be established that ∑ f(x) = 1 i.e. f(0) + f(1) + f(2)
+....... = 1 x The most important and universally accepted continuous
(ii) Poisson distribution is known as a uniparametric probability distribution is known as normal distribution. Though
distribution as it is characterised by only one parameter m. many mathematicians like De-Moivre, Laplace etc. contributed
(iii) The mean of Poisson distribution is given by m i,e µ = m towards the development of normal distribution, Karl Gauss was
(iv) The variance of Poisson distribution is given by σ2 = m instrumental for deriving normal distribution and as such normal
(v) Like binomial distribution, Poisson distribution could be distribution is also referred to as Gaussian Distribution.
also unimodal or bimodal depending upon the value of the A continuous random variable x is defined to follow normal
parameter m. distribution with parameters µ and σ2, to be denoted by
We have µ0 = The largest integer contained in m if m is a non- X ~ N (µ, σ2)
integer If the probability density function of the random variable x is given
= m and m–1 if m is an integer by
(vi) Poisson approximation to Binomial distribution f(x) = for -∞<x<∞
If n, the number of independent trials of a binomial
distribution, tends to infinity and p, the probability of a success, where µ and σ are constants, and > 0
tends to zero, so that m = np remains finite, then a binomial
distribution with parameters n and p can be approximated by a
Poisson distribution with parameter m (= np).
In other words when n is rather large and p is rather small so
that m = np is moderate then β(n, p) ≅ P (m)

32 November 2021 The Chartered Accountant Student

29
Join Us on Telegram http://t.me/canotes_foundation
 Downloaded From www.castudynotes.com

statistics
CA FOUNDATION - PAPER 3: BUSINESS MATHEMATICS,
LOGICAL REASONING AND STATISTICS

This capsule is in continuation to the previous edition featured in November 2021. Further here presented properties
of Normal Distribution and their applications. Here an attempt is made to the enable the students to understand the
concepts Binomial, Poisson and Normal distribution with the help of examples.

Chapter 17 : Theoretical Distributions

Some important points relating to normal distribution are listed (d) The normal distribution is known as biparametric
below: distribution as it is characterised by two parameters µ
(a) The name Normal Distribution has its origin some two hundred and σ2. Once the two parameters are known, the normal
years back as the then mathematician were in search for a distribution is completely specified.
normal model that can describe the probability distribution of
most of the continuous random variables.
(b) If we plot the probability function y = f (x), then the curve, Properties of Normal Distribution
known as probability curve, takes the following shape: 1. Since π = 22/7 , e–θ = 1 / eθ > 0, whatever θ may be,
it follows that f (x) 0 for every x.
It can be shown that
2. The mean of the normal distribution is given by µ. Further, since
the distribution is symmetrical about x = µ, it follows that the
mean, median and mode of a normal distribution coincide, all
being equal to µ.
3. The standard deviation of the normal distribution is given by
Mean deviation of normal distribution is
The first and third quartiles are Q1 = μ– 0.675 σ and Q3 = μ+
0.675 σ
-∞ x=µ ∞ so that, quartile deviation = 0.675 σ
4. The normal distribution is symmetrical about x =μ. As such,
Mean = Median = Mode its skewness is zero i.e. the normal curve is neither inclined
move towards the right (negatively skewed) nor towards the
Showing Normal Probability Curve. A quick look at figure reveals left (positively skewed).
that the normal curve is bell shaped and has one peak, which 5. The normal curve y = f (x) has two points of inflexion to be
implies that the normal distribution has one unique mode. The given by x = μ – σ and
line drawn through x = µ has divided the normal curve into two x = μ + σ i.e. at these two points, the normal curve changes its
parts which are equal in all respect. Such a curve is known as curvature from concave to convex and from convex to concave.
symmetrical curve and the corresponding distribution is known 6. If x ~ N (μ, σ2 ) then z = x – µ/σ ~ N (0, 1), z is known as
as symmetrical distribution. Thus, we find that the normal standardised normal variate or normal deviate.
distribution is symmetrical about x = µ. It may also be noted that We also have P (z ≤ k ) = φ (k) The values of φ(k) for different k
the binomial distribution is also symmetrical about p = 0.5. We next are given in a table known as “Biometrika.”
note that the two tails of the normal curve extend indefinitely on 7. Area under the normal curve is shown in the following figure:
both sides of the curve and both the left and right tails never touch
the horizontal axis. The total area of the normal curve or for that
any probability curve is taken to be unity i.e. one. Since the vertical
line drawn through x = µ divides the curve into two equal halves, it
automatically follows that,
The area between – ∞ to µ= the area between μ to ∞ = 0.5
When the mean is zero, we have
the area between – ∞ to 0 = the area between 0 to ∞ = 0.5

(c) If we take μ = 0 and σ = 1 , we have

f(x) = for –∞< z <∞
The random variable z is known as standard normal variate
(or variable) or standard normal deviate. The probability that a (z=3) (z=-2) (z=-1) (z=0) (z=1) (z=2) (z=3)
standard normal variate X would take a value less than or equal
to a particular value say X = x is given by
φ(x) = p ( X ≤ x )
(x) is known as the cumulative distribution function.
We also have (0) = P ( X ≤ 0 ) = Area of the standard normal
curve between –∞ and 0 = 0.5

The Chartered Accountant Student February 2022 29

30
Join Us on Telegram http://t.me/canotes_foundation
 Downloaded From www.castudynotes.com

statistics
Area Under Normal Curve => 4p = 6 - np
From the figure , we have => 4p = 6 - 10/3
P (µ – σ < x < µ + σ ) = 0.6828 => 4p = 8/3
=> P (–1 < z < 1 ) = 0.6828 => p = 2/3
P ( µ – 2 σ < x < µ + 2σ ) = 0.9546 np = 10/3 => n = 5
=> P (– 2 < z < 2 ) = 0.9546 probability that X assumes at most the value 2 = P(0) + P(1) + P(2)
and P ( µ – 3 σ < x < µ + 3σ ) = 0.9973 = ⁵C₀(2/3)⁰(1/3)⁵ + ⁵C₁(2/3)¹(1/3)⁴ + ⁵C₂(2/3)²(1/3)³
=> P (– 3 < z < 3 ) = 0.9973. = 1/243 + 10/243 + 40/243 = 51/243= 17/81
We note that 99.73 per cent of the values of a normal variable lies
between (µ – 3 σ) and (µ + 3 σ). Thus the probability that a value of
3. Assuming that one-third of the population is tea drinkers and
x lies outside that limit is as low as 0.0027.
each of 1000 enumerators takes a sample of 8 individuals to find
8. If x and y are independent normal variables with means and
out whether they are tea drinkers or not, how many enumerators
standard deviations as µ1 and µ2 and σ1, and σ2 respectively,
are expected to report that five or more people are tea drinkers?
then z = x + y also follows normal distribution with mean (µ1 +
Solution: Assume that being a tea drinker is like taking a flip of
µ2) and SD = respectively.
coin.(i.e. either the person drinks tea or not) with the probability of
i.e. If x ~ N (µ1, σ12) and y ~ N (µ2, σ22) and x and y are heads being 1/3 and tails being 2/3
independent, now P(X≥5) =P(X=5)+P(X=6)+P(X=7)+P(X=8) = (56*8+28*4+8*2+1)
then z = x + y ~ N ( µ1 + µ2, σ12 + σ22) /6561 = 577/6561 =0.087943 so for 1000 trials the number of trials
which report greater than or equal to 5 is 1000*P(X>=5) = 87.94 =88

Applications of Normal Distribution

4. If a random variable x follows binomial distribution with mean as
Most of the continuous variables like height, weight, wage, profit
5 and satisfying the condition 10. P (x= 0) = P(x= 1) , what is the value
etc. follow normal distribution. If the variable under study does
of P( X≥1/X>1) ?
not follow normal distribution, a simple transformation of the
Solution:
variable, in many a case, would lead to the normal distribution of
the changed variable.
When n, the number of trials of a binomial distribution, is large
and p, the probability of a success, is moderate i.e. neither too
large nor too small then the binomial distribution, also, tends to
normal distribution. Poisson distribution, also for large value of
m approaches normal distribution. Such transformations become
necessary as it is easier to compute probabilities under the
assumption of a normal distribution.

Some Important Problems

1. What is the probability that out of 10 missiles fired, atleast 2 will
hit the target
Solution: Probability of atleast 2 will hit the target is given as,
P(X ≥ 2) = 1 − P(X < 2)
The probability of a missile hitting a target is 1 /8
P(X ≥ 2) = 1 − [P(X = 0) + P(X = 1)] 5. Out of 128 families with four children each, how many are
= 1 − [¹⁰C₀ × (1/8)^0 × (7/8)^10 + ¹⁰C₁ × (1/8)^1 × (7/8)^9] expected to have atleast have one boy and one girl?
= 1 − [7^10/8^10 + (10 × 7^9)/8^10] Solution: 4 children in a family can be in
= 1 − [7^10 + 10 × 7^9] / 8^10 2 * 2 * 2 * 2 = 16 ways
= 1 − (17 × 7^9) / 8^10 at least one boy and one girl = Total cases - all boys - all girs
P(X ≥ 2) ≈ 0.3611 = 36.11% All boys = 1 case, All girls = 1 case
Therefore, the probability that out of 10 missiles fired, atleast 2 will => at least one boy and one girl = 16 - 1 - 1 = 14
hit the target is 0.3611. Probability of at least one boy and one girl = 14/16
out of 128 families expected to have = 128 * 14/16 = 8 * 14 = 112
2. Given X is a binomial variable such that 2 P(X = 2) = P(X = 3) and 112 Families expected to have at least one boy and one girl
mean of X is known to be 10/3. What would be the probability that
X assumes at most the value 2 6. In 10 independent rollings of a biased die, the probability that
Solution: an even number will appear 5 times is twice the probability that
mean = 10/3 , Mean = np = 10/3 an even number will appear 4 times. What is the probability that
P(X) = ⁿCxpx(1-p)ⁿ-x an even number will appear twice when the die is rolled 8 times?
=> P(2) = ⁿC₂p²(1-p)ⁿ-2 Solution: Probability of even number p = p
P(3) = ⁿC₃p³(1-p)ⁿ-3 Then probability of odd number (or not even number) = q = 1 - p
P(3) = 2 P(2) Probability Appearing 5 times
=> ⁿC₃p³(1-p)ⁿ-3 = 2 ⁿC₂p²(1-p)ⁿ-2 ¹⁰C₅ * p⁵ * q¹⁰-⁵
=> p/3!(n-3)! = (2 /2!(n-2)! )(1 - p) = ¹⁰C₅ * p⁵ * q⁵
=> p/6 = (1-p)/(n - 2)
=> np - 2p = 6 - 6p

30 February 2022 The Chartered Accountant Student

31
Join Us on Telegram http://t.me/canotes_foundation
 Downloaded From www.castudynotes.com

statistics
Probability Appearing 5 times 11. What is the probability of getting 3 head if 6 unbiased coins are
¹⁰C₄ * p⁴ * q¹⁰-⁴ tossed simultaneously?
= ¹⁰C₄ * p⁴ * q⁶ Solution: if x denotes the number of heads, then x follows binomial
¹⁰C₅ * p⁵ * q⁵ = 2 * ¹⁰C₄ * p⁴ * q⁶ distribution with parameters n = 6 and p = probability of success
=>p * 10!/5!5! = 2q * 10!/6!4! =½
=> p * 6 = 2q * 5 q= probability of failure = 1-1/2 = ½ , being given the coins are
=> 3p = 5q => 3p = 5(1 - p) unbiased
=> 8p = 5 The probability mass function of x is given by
=> p = 5/8 & q = 1 - 5/8 = 3/8
probability that an even number will appear twice when the die is f(x) = 6C3 . = 20 = 0.3125
rolled 8 times
= ⁸C₂ * p²q⁸-²
= 28 * (5/8)² (3/8)⁶ 12. In Binomial Distribution n = 9 and p = 1/3 , What is the value
= 28 * 25 * 3⁶ / 8⁸ of variance .
= 700 * 3⁶ / 8⁸ Solution: In Binomial Distribution variance = npq , here n= 9 , p
= 5,10,300/1,67,77,216 = 0.0304 = 1/3 and q= 2/3
Therefore variance = 9*1/3*2/3 = 2

7. What is the probability of making 3 correct guesses in 5 true-

13. For a Binomial Distribution E(x) = 2 , V(X)= 4/3 . Find the value
False answer type questions?
of n
Solution: Here P = 0.5 and q = 0.5 ( Since answer can be either True
Solution: Here E(X) = np = 2
or False ) n= 5, r = 3
V(x)= npq = 4/3 then substituting the value of np
P(x=r) = nCr px.qn-x
2×q = 4/3
P(x=3) = 5C3 (0.5) 5.(0.5)5-3 =0.3125
2q = 4/3
q= 2/3 then p = 1-2/3 = 1/3
8. Suppose that weather records show that on an average 5 out of 31 np = 2, n×1/3 = 2 , n= 6
days in October are rainy days. Assuming a binomial distribution
which each day of October as an independent trail, then the
probability that the next October will have at most three rainy days 14. The mode of Binomial Distribution for which the mean is 4 and
is: variance 3 is equal to?
Solution: p = Probability of a rainy day in October :p = 5/31, q = Solution: In Binomial Distribution Mean = np = 4 and Variance
probability of a non-rainy day in October q = 1- p = 1-5/31 = 26/31 = npq = 3
n = 31 (number of days in October) Then 4q = 3 q = ¾ , p = 1-q = 1-3/4 = ¼
n×1/4 = 4 therefore n = 16
P(x) = 31Cr. (n+1) p = (16+1) ×1/4 = 4.25 which is no longer integer.
So mode = 4
Required Probability = P (0) + P (1) +P(2) +P(3)

= 31C0. + 31C1. + 15. In a Binomial Distribution with 5 independent trials, probability

of 2 and 3 successes are 0.4362 and 0.2181 respectively. Parameter
‘p ‘of the Binomial Distribution is
31C2. + 31C3. Solution: Given n = 5 , P(x=2) = 0.4362
P(x=3) =0.2181
= 0.2403 P(x=3) = 5C3 . =10
0.2181 = 10.P3.q2
And P(X=2) =5C2 . =10
0.4362 = 10
By dividing
9. If 5 days are selected at random, then the probability of getting 0.2181/0.4362 =
two Sundays is:
Solution: Let P = Probability of getting a Sunday in a week (P) = 1/7 ½= q/p
Therefore P = 1/7 and q= 1-p = 1-1/7 = 6/7 q= 2p; 2p+p = 1
3p = 1, then p = 1/3
Required probability = 15C2 . = 0.288 = 0.29

16. What is the first quartile of X having the following probability

density function?
10. An experiment of succeeds twice as often as it falls. What is the
f(x) = for – ∝ < × < ∝
probability that in next five trials there will at least three successes?
Solution: According to the given statement p = 2q Solution: First Quartile Deviation (Q1) = μ- 0.675σ here
We know that p = 2/3 q= 1/3 By comparing probability density function of Normal Distribution,
Required probability P( X≥3) = P(3) +P(4) +P(5) Mean = 10 and σ = 4
Q1 = 10-0.675(6) =10-4.05 = 5.95
= 5C3 . + 5C4 . + 5C5 .

The Chartered Accountant Student February 2022 31

32
Join Us on Telegram http://t.me/canotes_foundation