Scribd
Upload
54 views

Probability Distribution

Uploaded by

2002rohanjha
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
54 views

Probability Distribution

Uploaded by

2002rohanjha
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 33

BUSINESS STATISTICS:

Text and Problems


With Introduction to Business Analytics

Dr. N. D. VOHRA
Chapter 7

Probability distributions
OBSERVED DISTRIBUTIONS AND
PROBABILITY DISTRIBUTIONS

• Observed frequency distributions depict how the


outcomes of an experiment have been observed.
• A probability distribution describes how the
outcomes of an experiment are expected to vary.
Such distributions are also termed as theoretical
distributions.
AN EXAMPLE OF PROBABILITY DISTRIBUTION:
PROBABILITY DISTRIBUTION OF SUM OF DIGITS
ON TWO DICE
Outcome Probability Expected
x p frequency
2 (1,1) 1/36 2
3 (1,2); (2,1) 2/36 4
4 (1,3); (2,2); (3,1) 3/36 6
5 (1,4); (2,3); (3,2); (4,1) 4/36 8
6 (1,5); (2,4); (3,3); (4,2); (5,1) 5/36 10
7 (1,6); (2,5); (3,4); (4,3); (5,2); (6,1) 6/36 12
8 (2,6); (3,5); (4,4); (5,3); (6,2) 5/36 10
9 (3,6); (4,5); (5,4); (6,3) 4/36 8
10 (4,6); (5,5); (6,4) 3/36 6
11 (5,6); (6,5) 2/36 4
12 (6,6) 1/36 2
Total 1 72
AN EXAMPLE

The owner of a bakery is considering how many one-kg cakes


he can sell in a day. He has kept a record of the sale of this type
of cake made over last 100 days as given below. Based on these
historical data, develop probability distribution of demand for
the cake in question.
No. of Cakes Sold (x ) 0 1 2 3 4 5 Total

No of Days (f ) 10 20 20 35 10 5 100
SOLUTION
No. of Cakes (x) No of Days (f ) Probability (p )
0 10 0.10
1 20 0.20
2 20 0.20
3 35 0.35
4 10 0.10
5 5 0.05
100

❑ Each of the probabilities is obtained by dividing the given frequency by the


total frequency ( =100).
❑ From this probability distribution it can be said that, based on past
experience, there is a 10 percent chance that no cake will be sold, a 20
percent chance that 1 cake will be sold in a day, … and so on.
DISCRETE AND CONTINUOUS
RANDOM VARIABLES
Random variable: The variable involved in a
probability distribution

Discrete Continuous

Assume only discrete Assumes any value in a


values given range
DISCRETE AND CONTINUOUS
PROBABILITY DISTRIBUTIONS

A probability distribution Discrete


involving a discrete random probability
variable distribution

A probability distribution Continuous


involving a continuous probability
random variable
distribution
EXPECTED VALUE AND
STANDARD DEVIATION OF A
RANDOM VARIABLE

•
AN EXAMPLE

The owner of a bakery is considering how many one-kg cakes


he can sell in a day. He has kept a record of the sale of this type
of cake made over last 100 days as given below. Obtain the
probability distribution and calculate expected value, variance
and standard deviation.
No. of Cakes Sold (x ) 0 1 2 3 4 5 Total

No of Days (f ) 10 20 20 35 10 5 100
SOLUTION

No. of Cakes Probability


px p (x − μ)2
x p
0 0.10 0 0.5290
1 0.20 0.20 0.3380
2 0.20 0.40 0.0180
3 0.35 1.05 0.1715
4 0.10 0.40 0.2890
5 0.05 0.25 0.3645
Total 1.00 2.30 1.7100
SOLUTION

•
SOME STANDARD
PROBABILITY DISTRIBUTIONS

Discrete Continuous
Binomial distribution Uniform Distribution*
Hypergeometric distribution Exponential Distribution
Multinomial Distribution Normal Distribution
Poisson Distribution
* Uniform distribution can be discrete as well.
BINOMIAL DISTRIBUTION

❑ An experiment consisting of n trials is made.

❑ Each trial results in either of two dichotomous alternatives (hence the name
binomial), arbitrarily termed as success and failure.

❑ The trials are independent of each other so that the probability of success p
remains unchanged from trial to trial.

❑ In the experiment, the discrete random variable, or phenomenon of interest


that follows is the number of successes obtained together with probabilities of
their occurrence.
BINOMIAL DISTRIBUTION

•
BINOMIAL DISTRIBUTION: n AND p
VALUES AND ITS SHAPE
POISSON DISTRIBUTION

•
POISSON DISTRIBUTION

• It is positively skewed. However, the degree of


skewness decreases with an increase in the value of λ.
• It has a single parameter, defined by the average
number of random events in a trial, λ (with λ > 0)
• The expected value (mean) and variance of a Poisson
distribution are both numerically equal to λ
POISSON DISTRIBUTION:
λ VALUES AND SKEWNESS
POISSON DISTRIBUTION AS
APPROXIMATION TO BINOMIAL
DISTRIBUTION

• The Poisson distribution may be used as an


approximation to the binomial distribution under the
following condition:
When n is large and p is small
• To use this approximation we set np = λ and calculate
probabilities using the Poisson probability distribution
formula.
NORMAL DISTRIBUTION

•
PROPERTIES OF NORMAL CURVE

• It is a uni-modal, bell-shaped and symmetrical curve. Its mean,


median, mode, mid-hinge and mid-range are all equal.
• The normal curve is asymptotic to the x-axis so that it
approaches the horizontal axis on both ends, but never touches
it.
• A normal distribution is defined by two parameters – its mean, μ,
and standard deviation, σ. Corresponding to every pair of these
measures, a distinct normal curve exists.
• A change in μ displaces the normal curve while a change in σ
causes a change in its relative position.
NORMAL CURVES: UNEQUAL MEANS,
EQUAL STANDARD DEVIATIONS
NORMAL CURVES: EQUAL MEANS,
UNEQUAL STANDARD DEVIATIONS
PROPERTIES OF NORMAL CURVE

• A normal curve has two points of inflection, where the curve changes
its curvature. They are situated at one-sigma (1σ) distance from mean
on either side of it.
• A normal curve being symmetrical about μ, it follows that area under
it to the left of μ is equal to the area under it to the right of μ. Also, for
every normal curve, μ ± 1σ covers 68.27 per cent of the area under the
curve; μ ± 2σ covers 95.45 percent of it, while μ ± 3σ covers 99.73
percent area.
• The inter-quartile range is contained within an interval of the
two-thirds of a standard deviation below the mean to two-thirds of a
standard deviation above the mean.
NORMAL CURVE
RELATIONSHIP BETWEEN
SD, MD AND QD FOR A
NORMAL DISTRIBUTION
Percentage of area included within a Size of
Measure of given range of mean measure
variation ± one ± two ± three standard
deviation deviations deviations deviation
Quartile
Deviation 50.0 82.3 95.7 0.6748
Mean
Deviation 57.5 88.9 98.3 0.7979
Standard
Deviation 68.3 95.5 99.7 1.0000
STANDARD NORMAL DISTRIBUTION

•
CALCULATION OF PROBABILITIES

•
AN EXAMPLE

A machine fills coffee powder in pouches, with an


average of 200 gm and a standard deviation of 4 gm.
Assuming that the coffee weight is normally
distributed, find the probability that a coffee pouch
selected at random will contain the following quantity
of coffee.
a) At least 200 gm
b) Between 200 and 206 gm,
SOLUTION

200 206
NORMAL DISTRIBUTION AS
APPROXIMATION TO DISCRETE
PROBABILITY DISTRIBUTIONS

• The normal distribution can used as approximation to the


binomial and Poisson distributions
• However, while a normal distribution uses a continuous
variable, the binomial and Poisson all involve discrete
variables
• As such, continuity correction factor (CCF) is required to be
introduced to make probability calculations.
END OF CHAPTER 7

You might also like

pFad - Phonifier reborn

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

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy