Scribd
Upload
48 views21 pages

Discriminant Analysis Presentation

Discriminant analysis is a statistical technique used to classify data by determining variables that discriminate between two or more groups. It maximizes variance between groups while minimizing variance within groups. There are two main types: linear discriminant analysis, which finds a linear combination of features to best separate classes assuming equal covariance matrices; and quadratic discriminant analysis, which uses non-linear boundaries and assumes different covariance matrices for each class. Discriminant analysis has applications in medical diagnosis, finance, quality control, and biology. The process involves data collection, preprocessing, model building using linear or quadratic discriminant analysis, and evaluating the model with cross-validation.

Uploaded by

gugugaga
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
48 views21 pages

Discriminant Analysis Presentation

Discriminant analysis is a statistical technique used to classify data by determining variables that discriminate between two or more groups. It maximizes variance between groups while minimizing variance within groups. There are two main types: linear discriminant analysis, which finds a linear combination of features to best separate classes assuming equal covariance matrices; and quadratic discriminant analysis, which uses non-linear boundaries and assumes different covariance matrices for each class. Discriminant analysis has applications in medical diagnosis, finance, quality control, and biology. The process involves data collection, preprocessing, model building using linear or quadratic discriminant analysis, and evaluating the model with cross-validation.

Uploaded by

gugugaga
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 21

Discriminant

Analysis
Daniel Damunza & Mark
Bilahi
What is Discriminant Analysis?
 Discriminant analysis is a statistical analysis
technique used for data classification and
dimension reduction.
 It can be used to group data along specified x-
tics / features. It is also used to determine
variables that discriminate between two or
more groups of objects / events.
 Primary goal – Maximize variance between
groups while minimizing variance within
groups.
What are it’s Applications?
 Medical Diagnosis - used to distinguish between different diseases & to identify
new conditions. E.g., differentiating Covid-19 from other SARS viruses.
What are it’s Applications?
 Finance – determine customers’ credit qualification for a loan based on previous
financial statements & credit history. E.g., grouping clients based on the ‘credit rating’
to determine who qualifies for what loan types / amounts.
What are it’s Applications?
 Quality Control – anomaly detection in high quantity production factories. E.g.,
detecting defective cups in a plastic cup factory.
What are it’s Applications?
 Botany & Zoology – group species based on physical x-tics.
What are the types of Discriminant Analysis?
Linear Discriminant Analysis Quadratic Discriminant Analysis
- Finds linear combination of features that - Utilizes non-linear classification
best separates the different classes. boundaries to split data.(more accurate).

- Assumes the predetermined classes share - Assumes each class has it’s own covariance
the same covariance matrix. matrix.

- Assumes the data follows a normal - Can handle data with complex
distribution. distributions.

How do you know which to use?


- Having done your exploratory analysis of your data, compute & consider the covariance
matrixes of the classes.
- Use Cross Validation to determine which method is better for your data set.

An alternative is to partition the sample data into a training (or model-building) set, which we can
use to develop the model, and a validation (or prediction) set, which is used to evaluate the predictive
ability of the model. This is called cross-validation .
What are the types of Discriminant Analysis?
Linear Discriminant Analysis Quadratic Discriminant Analysis
Mathematical Principles
 Covariance Matrix – A specific type of matrix that describes the covariance
between two items in a random vector space.
Formula:
Here’s some Example Analyses!
Before Discriminant Analysis
Resultant Dataset Visualized:
Here’s some Example Analyses!
Linear Discriminant Analysis
Source Data Visualization Linear DA Results Visualization
Here’s some Example Analyses!
Quadratic Discriminant Analysis
Source Data Visualization Quadratic DA Results Visualization
Process of Discriminant Analysis

1. 2. 3.
Data Collection Data Preprocessing Model Building
Gather the variables you wish to Cleaning & normalization of Deciding between Linear DA &
classify your data. Quadratic DA
This step includes feature
selection.
Example of Using Discriminant Analysis
Example of Using Discriminant Analysis
Example of Using Discriminant Analysis
Example of Using Discriminant Analysis
References
- 10.6 - Cross-validation | STAT 501. (n.d.). Online.stat.psu.edu. Retrieved November 6, 2023, from
https://online.stat.psu.edu/stat501/lesson/10/10.6#:~:text=An%20alternative%20is%20to%20partition

Covariance Matrix - Definition, Formula, Examples, Properties and FAQs. (2022, October 27). GeeksforGeeks.
https://www.geeksforgeeks.org/covariance-matrix/

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