Regression
Regression is a supervised learning technique used to predict a dependent variable
based on one or more independent variables by estimating a relationship between
them.
Regression is applicable when we want to know the answer to one thing, but we
have clues coming from multiple sources.
Types of Regression Models
1. Simple Linear Regression
2. Multiple Regression
3. Polynomial Regression
4. Logistic Regression
Syllabus Includes only Simple Linear Regression.
Regression Modelling is a process of determining a relationship between one or
more independent variables and one dependent variable.
Examples. 1. Predicting the height of a person given the age of the person.
2. Predicting the price of the car given the car model, year of manufacturing,
mileage, engine capacity etc.
1. Simple Linear Regression :
Assume that there is only one independent variable x. if the relationship between
x and y ( dependent variable ) is modeled by the relation,
y= a + bx, then the regression model is called a linear regression model.
Solved Example
We can also solve the problem of various regression models using
Matrix Method
-------------------------------------------------------------------------------------------------------------
Find Linear Regression of the data
of week and product sales ( in
thousands ) given in table.
Use Linear Regression In Matrix
Form
Predict the 5th Week Sales
The regression is given as follows
ao = -1.5 and a1 is 2.2
y = a 0 + a1 * x
The predicted 5th week sale when x = 5 is
Y = -1.5 + 2.2 * 5 = 9.5