Scribd
Upload
10 views7 pages

UNIT VI - Probability

The document provides an overview of three probability distributions: Poisson, Binomial, and Normal. It outlines their definitions, assumptions, applications across various fields, and limitations. Each distribution serves specific purposes in modeling events and outcomes, with the Poisson distribution focusing on event occurrence, the Binomial on success in trials, and the Normal on data clustering around a mean.

Uploaded by

todepiyush88
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views7 pages

UNIT VI - Probability

The document provides an overview of three probability distributions: Poisson, Binomial, and Normal. It outlines their definitions, assumptions, applications across various fields, and limitations. Each distribution serves specific purposes in modeling events and outcomes, with the Poisson distribution focusing on event occurrence, the Binomial on success in trials, and the Normal on data clustering around a mean.

Uploaded by

todepiyush88
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

Poisson distribution

Definition

The Poisson distribution is a discrete probability distribution that expresses the likelihood of a
given number of events occurring in a fixed interval of time or space, provided the events occur:

 Independently of each other,


 At a constant average rate,
 With no two events happening simultaneously.

Assumptions of the Poisson distribution

1. Events occur one at a time and are independent.


2. The probability of more than one event in an infinitesimally small interval is negligible.
3. The average rate (lambda, λ) of occurrence is constant over time or space.

Applications of Poisson Distribution

1. Business and Operations:


o Predicting the number of customer arrivals in a queue.
o Modeling the number of defective items in a batch.
2. Healthcare:
o Estimating the number of patients arriving at a hospital emergency room.
3. Telecommunications:
o Modeling call arrivals in a call center or network traffic.
4. Insurance and Risk:
o Predicting the number of claims in a given period.
5. Biology and Ecology:
o Counting the number of mutations in a DNA sequence over time.
6. Transportation:
o Estimating the number of cars passing through a toll booth per hour.

Limitations

1. Assumes independence of events, which may not always hold in real-world scenarios.
2. Assumes a constant rate (lambda λ), which might vary over time in some processes.
3. Not suitable for data with over dispersion (variance greater than the mean).
Binomial distribution

Definition

The binomial distribution is a discrete probability distribution that describes the number of
successes in a fixed number of independent trials, each with the same probability of success. The
binomial distribution is used when there are exactly two mutually exclusive outcomes (success
or failure) for each trial.

Assumptions of the Binomial Distribution

1. Fixed number of trials: The number of trials (nnn) is fixed.


2. Two possible outcomes: Each trial has two outcomes: success or failure.
3. Independence: The trials are independent; the outcome of one trial does not affect the
others.
4. Constant probability of success: The probability of success (ppp) is the same for each
trial.

Applications of Binomial Distribution

1. Business and Economics:


o Estimating the number of successful sales in a fixed number of attempts.
o Calculating the probability of a certain number of defective items in a batch.
2. Healthcare:
o Predicting the number of patients who will respond positively to a new treatment
in a clinical trial.
3. Quality Control:
o Determining the probability of having a certain number of defective products in a
production process.
4. Marketing:
o Analyzing customer responses to a promotional campaign (e.g., the number of
customers who will purchase a product after a marketing email is sent).
5. Polling and Surveys:
o Estimating the probability of a certain number of people supporting a political
candidate out of a random sample.

Limitations of Binomial Distribution

1. Independence: Requires that trials are independent. If trials are dependent (e.g., selecting
items without replacement), the binomial distribution may not be appropriate.
2. Fixed Number of Trials: If the number of trials is not fixed, the binomial distribution
may not apply.
3. Constant Probability: The probability of success must remain constant across all trials,
which may not hold in some scenarios.
Normal distribution

Definition

The normal distribution, also known as the Gaussian distribution, is a continuous probability
distribution that is symmetric and describes data that clusters around a mean. It is widely used in
statistics and natural sciences due to its tendency to model the distribution of many types of real-
world data.

The normal distribution is defined by the bell-shaped curve where the majority of data points lie
near the mean, and the probability of extreme values decreases exponentially as you move away
from the mean.

Characteristics of the Normal Distribution

1. Shape:
o
Symmetric about the mean.
o
Bell-shaped, with the highest point at the mean.
o
The tails of the distribution approach, but never touch, the horizontal axis
(asymptotic behavior).
2. Mean, Median, and Mode:
o For a perfect normal distribution, the mean (μ\muμ), median, and mode all
coincide at the center of the distribution.

Applications of Normal Distribution

1. Natural and Social Sciences:


o Heights, weights, and IQ scores of humans.
o Measurement errors in experiments.
o Blood pressure and cholesterol levels.
2. Finance:
o Stock prices and returns are often modeled using normal distribution (though real
financial data may exhibit fat tails or skewness).
3. Quality Control:
o Monitoring the production of manufactured goods (e.g., measurement of product
dimensions).
o Statistical process control charts, where a process is assumed to be normally
distributed.
4. Psychology:
o Many psychological measurements and scores are assumed to follow a normal
distribution (e.g., intelligence test scores).
5. Engineering and Manufacturing:
o Predicting the distribution of strength or failure rates of materials.
Limitations of the Normal Distribution

1. Not Always a Good Fit:


o Real-world data may not always be perfectly normal, especially in cases with
skewness or outliers.
2. Assumption of Homogeneity:
o Assumes that data is homogeneous and doesn't account for heteroscedasticity
(when variability changes across levels of an independent variable).
3. Outliers:
o The normal distribution does not model extreme outliers well.

You might also like