Theoretical Distributions: Bernoulli's Distribution Binomial Distributions

Bernoulli’s distribution
Binomial distributions
THEORETICAL DISTRIBUTIONS
Introduction
▪ Frequency distributions are broadly classified

under two heads:
1. Observed frequency distributions and
2. Theoretical frequency distributions.
Probability distributions
1. Bernoulli’s distribution.
2. Binomial distributions
3. Poisson distributions
4. Hyper-geometric distributions
5. Normal distributions
6. Chi-Square distributions
7. Student’s t-distributions
Bernoulli distribution
▪ Bernoulli distribution was discovered by

Swiss mathematician James Bernoulli’s(1654-
1705).
▪ This is a discrete probability distribution.
Definition: If ‘X’ is a discrete random variable
with probability mass function p(X=x)=pxq1-
x,where x=0,1;0<p<1;q=1-p, then, ‘X’ is a
Bernoulli distribution.
Example of Bernoulli’s
distribution
▪ Number of heads obtained in the toss of a
coin
▪ Winning a game
▪ Number of male children when a baby born.
▪ Number of bombs hitting the bridge when a
bomb is dropped from aero plane.
Note: Bernoulli distribution with parameter p
can be written as follows:
x 0 1 Total
p(x) q p 1
Features of Bernoulli
distribution
1. Bernoulli distribution has one constant,
namely p, which is the parameter of
Bernoulli distribution.
2. x=0,1 is the range of Bernoulli distribution.
3. For a Bernoulli distribution p.m.f. is
p(X=x)=pxq1-x,where x=0,1;0<p<1;q=1-p
4. For a Bernoulli’s distribution mean=p,
variance=pq
Bernoulli trial
▪ If a trial results either in success or failure with

the probability of success ‘p’ remains same,
when the trial is repeated any number of
times, such a trial is known as Bernoulli trial.
Example of Bernoulli trial:
▪ The tossing of a fair coin once can be

considered as a Bernoulli trial.
▪ Because, the toss may result in a success (say
H) or a failure (say T) and the probability of
success remains same ( ½) for any trial.
Binomial distributions
▪ Binomial distribution is also discovered by

James Bernoulli.
▪ This method is a discrete probability
distributions.
▪ Definition: If ‘X’ is a discrete random variable
with probability mass function
p(X=x)=nCxpxqn-x,where x=0,1,…,n;0<p<1;q=1-
p, then, ‘X’ is a Binomial distribution.
▪ p(x)=5Cx(0.3)x(0.7)5-x x=0,1,2,3,4,5.
Binomial distribution
▪ The Binomial distribution with parameter n

and p can be written as follows
▪ Note: A binomial distribution with parameter
n and p is denoted as B(x; n,p) or B(n,p)
X 0 1 2 ------ n
p(x) nC p0qn-0 nC p1qn-1 nC p2qn-2 ------- nC pnqn-n

0 1 2 n
=qn =npqn-1 =pn
Examples of Binomial
distributions
▪ Number of heads obtained in 6 tosses of coin
▪ Number female children out of 6 children
born.
▪ Number of bombs hitting a target in among 3
bombs which are aimed at it.
▪ Number of defective items in a random
sample of 6 articles drawn from a
manufactured lot
▪ Number of matches won out of 7 played
Features of Binomial
distributions
▪ n and p are the parameters of Binomial
distributions.
▪ X=0,1,2,…….,n is the range of Binomial
distributions.
▪ For a Binomial distributions p.m.f is
p(X=x)=nCxpxqn-x,where x=0,1,…,n;0<p<1;q=1-p.
▪ For a Binomial distributions
mean=np,variance=npq.
distributions
▪ Mean>variance for a binomial distributions.
Here , np>npq because 0<p<1 and 0<q<1
▪ The mean and mode are equal if np is an
integer.
▪ The mode of the Binomial distributions is
equal to the value of x which has the largest
probability.
▪ If p=q=1/2, the Binomial distribution is
symmetrical.
distributions
▪ If p< ½ or q>1/2 then binomial distribution is
positively skewed.
▪ If p>1/2 or q<1/2 the binomial distribution is
negatively skewed.
▪ The binomial distribution tends to poisson
distribution if n-> ∞ and p->0 and np=λ, a
constant(fixed).
▪ The binomial distribution tends to Normal
distribution when n-> ∞ and p,q are almost
equal.
POISSON DISTRIBUTION
▪ Definition:
If X is a discrete random variable with
probability mass function p(x)=e-λ λx/x!
,where x=0,1,2,3,4,……….∞; λ>0.
Then is a Poisson variate and the distribution of
X is called Poisson distribution.
Note:e=2.7183 is the base of natural logarithm
POISSON DISTRIBUTION
▪ P.D with parameter λ can be written as

follows:
x 0 1 2 3 4 …….
p(x) e-λ λ0/0! e-λ λ1/1! e-λ λ2/2! e-λ λ3/3! e-λ λ4/4! ……
=e-λ =e-λ λ =e-λ λ2/2 =e-λ λ3/6 =e-λ
λ4/24
▪ Sum of all probabilities is equal to 1.

▪ The Poisson distribution with parameter λ is
denoted by P(x; λ) or p(λ)
Example of Poisson variate
▪ Number of deaths occuring in a city

▪ Number of accidents in a city
▪ Number of phone calls
▪ Number of printing mistake per page
▪ Number of vehicles crossing a junction in a
minute
▪ Number of radio active particles
Features of Poisson
distribution
▪ P.D has only one parameter λ.
▪ For a poisson distribution the p.m.f is
p(x)=e-λ λx/x!, where x=0,1,2,3,4,……….∞; λ>0.
▪ x=0,1,2,3,4,…………..,∞ is the large range of
Poisson distribution.
▪ For a Poisson distribution mean=λ,variance=λ
▪ The mean and variance are equal for a
Poisson distribution.
Features of Poisson
distribution
▪ When λ is not an integer, Poisson distribution
is unimodal and the integral part of λ is the
unique modal value.
▪ When λ is an integer, Poisson distribution is
bimodal and two modes are at (λ-1) and λ.
▪ Poisson distribution is positively
skewed(β1>0)
▪ Poisson distribution is leptokurtosis(β2>3)
Features of Poisson
distribution
▪ When λ is large, Poisson distribution can be
considered to be normal distribution.
HYPER GEOMETRIC DISTRIBUTION
▪ The result of each draw can be classified into

one of the two categories.
▪ The probability of success changes on each
draw
▪ Successive draws are dependent as they are
made without replacement.
▪ The draw is repeated a fixed number of times
from a finite population
Definition.
▪ If ‘X’ is a discrete random random variable with

probability mass function p(x)=aCxbCn-x/a+bCn,
▪
,where x=0,1,2,3…………….min(a,n);a,b and n>0,then
‘X’ is a hyper-geometric distribution. Here, a, b and n
are positive integers and n≤a+b. Hyper-geometric
distribution is a discrete probability distribution. The
hyper-geometric distribution with a=2, b=5 and n=4
is as follows.
Here , min(a,n)=min(2,4)=2.
So range is x=0,1,2.
Features of hyper geometric
distribution
▪ a , b , n are the three parameters of hyper
geometric distribution.
▪ Range of hyper geometric distribution is
x=0,1,2,3…..min(a,n)
▪ The probability mass function of hyper
geometric distribution is
p(x)=aCxbCn-x/a+bCn, x=0,1,2,3…..min(a,n) and
n>0.
Features of hyper geometric
distribution
▪ For hyper geometric distribution
mean=na/a+b,
Variance= nab(a+b-n)/(a+b)2(a+b-1)
▪ Hyper geometric distribution tends to
binomial distribution when a+b->∞ and
a/a+b=p. So binomial distribution is a limiting
form of hyper-geometric distribution with
parameters n and p=a/a+b.
Examples on hyper geometric
distribution
▪ Number of boys in a committee when 5 boys are
selected from 30 boys and 20 girls.
▪ Number of vegetarians in a sample of 8 selected
from a hostel in which there are 12 vegetarians
and 18 non vegetarians.
▪ Number of white balls in a selection of 4 when
there are 5 white and 6 black balls in an urn.
▪ Note: A hyper geometric distribution with
parameters a, b, n is denoted by H(x:a,b,n) or
H(a,b,n).
Normal distributions
▪ Definition:
If X is continuous distribution with probability
1 𝑥−𝜇
1 −
density function . 𝑓 𝑥 = 𝑒 2 𝜎
𝜎 2𝜋
; where -∞<x<+ ∞, σ>0
Then ‘X’ is a normal distribution.
Example
▪ Heights of students
▪ Weights of apples grown in orchads
▪ Life time of electric bulbs manufactured by a
firm
▪ Intelligence Quotients of a large group of
children.
▪ Income of the persons working in an
organizations.
Properties
▪ The normal curve is bell shaped.

▪ The curve is symmetrical about mean(𝛽1 = 0)
Here, mean=median=mode=μ
▪ The normal distribution has only one mode.
That is, it is unimodal.
▪ The distribution is mesokurtic(𝛽2 = 3).
▪ For a normal distribution,
standard deviation=σ
Properties
2
Quartile deviation= 𝜎
3
4
Mean deviation= 𝜎
5
▪ The curve is asymptotic to X-Axis. That is, the
curve touches the X-axis only at -∞ and + ∞.In
other words it approaches neared and nearer
to x-axis but never touches it.
▪ The curve has points of inflexion at μ-σ and
μ+σ.
Properties
▪ For normal distribution, the odd order

moments are 0, and even order moments are
given by
𝜇2𝑟 = 1 × 3 × 5 × ⋯ . 2𝑟 − 1 𝜎 2𝑟 ,
𝑟 = 1,2,3, … …
▪ The quartiles 𝑄1 𝑎𝑛𝑑 𝑄3 are equidistant from
the median and are given by
𝑄1 = 𝜇 − 0.6745𝜎 𝑎𝑛𝑑 𝑄3 = 𝜇 + 0.6745𝜎
Properties
▪ The total area under normal curve is equal to

one. So the area to the right of the ordinate
at the mean well as to the left of the ordinate
at the mean is 0.5.
Standard Normal Distribution
𝑥−𝜇
▪ If Z = is a normal variate with mean μ=0 and
𝜎
S.D σ=1, then Z is called a standard normal
variate and the distribution of Z is called a
standard normal distribution. The probability
density function of a standard normal
distribution. The probability function of a
standard normal distribution is
1 𝑥−𝜇 2
1 −
▪ .𝑓 𝑥 = 𝑒 2 σ
𝜎 2𝜋
1 −𝑍 2
𝑓 𝑍 = 𝑒 2 ; 𝑊ℎ𝑒𝑟𝑒 − ∞ < 𝑧 < +∞
2𝜋
Properties
▪ For a standard normal distribution mean=0,

variance=1 and S.D=1.
▪ The standard Normal Curve is symmetrical
about Z=0.
Here, Mean=Median=Mode=0
▪ Total area under the standard Normal curve is
equal to one.
▪ Standard Normal Curve is asymptotic to the
X-axis.
Note
▪ If X is a normal variate with mean=μ and

𝑥−𝜇
S.D=σ, then 𝑍 = is SNV.
𝜎
2
That is X~N(μ,𝜎 ) then Z~N(0,1)
So find the probability regarding X, the SNV
Z can be made use of The graph of standard
normal distribution is as follows:
Note

Theoretical Distributions: Bernoulli's Distribution Binomial Distributions

Uploaded by

Copyright:

Available Formats

Theoretical Distributions: Bernoulli's Distribution Binomial Distributions

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

Theoretical Distributions: Bernoulli's Distribution Binomial Distributions

Uploaded by

Copyright:

Available Formats

Bernoulli’s distribution

▪ Frequency distributions are broadly classified

▪ Bernoulli distribution was discovered by

▪ If a trial results either in success or failure with

▪ The tossing of a fair coin once can be

▪ Binomial distribution is also discovered by

▪ The Binomial distribution with parameter n

p(x) nC p0qn-0 nC p1qn-1 nC p2qn-2 ------- nC pnqn-n

▪ P.D with parameter λ can be written as

▪ Sum of all probabilities is equal to 1.

▪ Number of deaths occuring in a city

▪ The result of each draw can be classified into

▪ If ‘X’ is a discrete random random variable with

▪ The normal curve is bell shaped.

▪ For normal distribution, the odd order

▪ The total area under normal curve is equal to

▪ For a standard normal distribution mean=0,

▪ If X is a normal variate with mean=μ and

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.