Scribd
Upload
316 views

Statistical Distributions

This document discusses different types of statistical distributions. It defines a distribution as a mathematical model of how a variable behaves and the probabilities associated with different values. Distributions can be discrete, taking on separate values, or continuous, varying over a range of values. Common discrete distributions include binomial and Poisson, while common continuous distributions include uniform and normal. Examples are provided to illustrate calculating probabilities for different distributions based on their properties like mean and standard deviation.

Uploaded by

spectrum_48
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
316 views

Statistical Distributions

This document discusses different types of statistical distributions. It defines a distribution as a mathematical model of how a variable behaves and the probabilities associated with different values. Distributions can be discrete, taking on separate values, or continuous, varying over a range of values. Common discrete distributions include binomial and Poisson, while common continuous distributions include uniform and normal. Examples are provided to illustrate calculating probabilities for different distributions based on their properties like mean and standard deviation.

Uploaded by

spectrum_48
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 35

Statistical distributions

What is a distribution?
A statistical distribution refers to the way a particular variable of interest
behaves.
A distribution tries to mathematically model the behaviour so that
decision making can be done based on it.
For example, in the study of queuing in service industries the arrival of
customers is modelled as Poisson distribution and the service time is
modelled as exponential distribution.
A distribution tells us the values the variable can take and the probabilities
associated with those values.

4/30/2016

Types of Distributions
Discrete Distribution - When the variable is a discrete variable. e.g.
number of passengers sitting in a car
Continuous Distribution - When the variable is a continuous variable e.g.
rainfall in a place
The important distributions in statistics are as follows.
Bernoulli Distribution
Binomial Distribution
Uniform Distribution
Poisson Distribution
Geometric Distribution
Normal Distribution

4/30/2016

F Distribution

Exponential Distribution

Binomial Distribution

The probability that India wins a match against Sri Lanka is 0.6. If India and
Sri Lanka play a 3-match series. Assume that no match of tied or drawn.
Find the probability that

India wins all 3 matches


India wins exactly 2 matches
Binomial
India wins exactly 1 matches
India wins no match

Distribution

There are only 2 possible outcomes of an event. e.g. pass or fail, lose or
win, head or tail
Each trial is independent of any other trial
The probability of success is constant for all trials

Binomial Distribution

Mean = np
Variance = npq
Standard Deviation = npq

Binomial Distribution

The overall percentage of defaulters of personal loans in a bank is 20. What


is the probability, that out of a group of 6 borrowers, sanctioned loans on a
particular day,

Exactly one is a defaulter?


Upto 2 are defaulters?
Binomial Distribution
Less than 5 are defaulters?
Find the average number of defaulters.

The probability that a machine produces a defective part is 0.05. If a


machine produces 40 parts, find the probability that
Exactly 2 parts are defective
At the most 1 part is defective
Find the average number of defective parts

Example 1

10

The mean for a binomial distribution is 7.5. The variance for the same is
1.875. Find the probability that exactly 3 successes are achieved.

Example 2

The number of trials for a binomial distribution is 12. The variance for the
same is 3. Find the probability that at the most 2 successes are achieved.

Example 3

Poisson Distribution

Poisson distribution is used when


The occurrences are random and rare
The average number of occurrences is fixed

Poisson
distribution
where m = average number
of occurrences

The number of vehicles passing a junction is 2 per minutes. Find the


probability that in a given minutes
No vehicle passes
Exactly 1 vehicle passes
More than 2 vehiclesPoisson
pass

Distribution

15

Mean = xi f(xi) / f(xi) = m


Variance = (xi m)2f(xi) / f(xi) = m
Std. Deviation = m

Poisson distribution

The average number of mistakes per 10 pages in a book is 10. Find the
probability that on a given page
i) There is no mistake
ii) There are more than 3 mistakes

Poisson Distribution Practice Example

17

The variance for a Poisson distribution is 0.5. Find the mean of the
distribution. Find the probability of P(x < 3).

Example 4

18

For a Poisson distribution, P(0) = 0.01831. Find the probability of P(x


3).

Example 5

Discrete distribution
x can take only discrete values
the value of P(x) is defined for every value of x

Continuous distribution
x can takeDiscrete
any value vs. Continuous distribution
P(x) = 0 at a particular value of x. P(x) is defined only for a range of x.

Uniform Distribution

Uniform distribution

Uniform Distribution Parameters


Probability Density f(x) = 1 / (b - a)
Mean = (a + b) / 2
Variance = (b - a)2 / 12

4/30/2016

Example - Uniform Distribution


x varies uniformly over 5 to 17. Find
The probability density
P(6 < x < 12)
P(x < 12)
Mean and Standard Deviation

4/30/2016

Normal Distribution

Continuous Distribution
Probability Density

Normal Distribution

Normal Distribution

It is symmetric in nature
The total area under the curve is 1, the area under the left half and the right half is
0.5 each
The shape of the curve depends upon mean () and standard deviation ().
The more the , the more dispersed the curve is, the lesser the , the more peaked
the curve is. Properties of Normal Distribution
The probability is defined only for a range and not at a particular value of x. i.e. P(x1
x x2)
The probability is defined as the area under the normal curve and depends only on
the value of (x )/

Normal Distribution

The life of bulbs, manufactured by a company, has mean of 1,600 hr and std
deviation 30 hr.
i) What is the probability that the life of a bulb selected at random will be
less than or equal to 1,650 hr?
ii) What is the probability that the life of a bulb selected at random will be
Normal distribution
less than or equal to 1,550 hr?
iii) What is the proportion of bulbs having life between 1,550 and 1,580 hr?

A Tea Company packs tea in bags marked 250 g. Some packs of tea
were weighed and the mean and standard deviation were calculated
as 255 g and 2.5 g respectively. Assuming this data is normally
distributed, what percentage of packs are underweight?

Example 6

Percentage of underweight packs = 2.28%

To pass a test students need to score 50% or more. The marks of a


large number of students were sampled and the mean and standard
deviation were calculated. The standard deviation was 8%. If 70% of
the students passed the test, what is the mean of the score?
Assume this data is normally
distributed.
Example
7

Mean = 54.16%

A company makes spare parts for a machine. The lengths of the


parts should confirm to certain limits or they will be rejected. A
large number of parts were measured and the mean and standard
deviation were calculated as 3.1 m and 0.005 m respectively.
Assuming this data is normally
distributed
Example
8 and 99.7% of the parts
were accepted, what are the limits? The limits are on either side of
the mean and equidistant from the mean.

Upper Limit = 3.1148 m


Lower Limit = 3.0852 m

You might also like