Linear Regression


Linear Regression

Linear Regression


Linear regression attempts to model the relationship between two variables by fitting a linear equation to observed data. One variable is said to be independent and the other one is said to be dependent.

y=mx + c

The core concept is to model using a straight line

Linear Regression is usually used for Continuous Variable or Value, or in a simple term to predict some quantity


The dependent variable is plotted on Y-axis and the Independent variable on X-axis.


Now, Lets us Understand Linear Regression with an Example

Let us consider some points for an Independent Variable

X = { 1 , 2 , 3 , 4 , 5 }

Y = { 3 , 4, 2 , 4 , 5 }


(1,3) , (2,4) , (3,2) , (4,4) , (5,5)

Now to find the slope we need to first get x – x_mean and y – y_mean

LR Table

Now to calculate the slope we use the formula

Slope formula

Now solving the above equation with the values fetched from the table we get the slope (m) value

Slope value

Now we can use the slope value and x mean and y mean value and find the constant from the equation, y = mx + c

Equation, y = mx + c

where y = y mean value , x = x mean value, m = slope calculated above

We substitute all the values to get cCOPYCOPYCOPYCOPYCOPYCOPYCOPY

m = 0.4
x = 3
y = 3.6
y = mx + c
3.6 = 0.4*3 + c
c = 2.4

Now that we have all the values, the final equation will beCOPYCOPYCOPYCOPYCOPYCOPYCOPY

y = m.x + c

y = 0.4.x + 2.4         -----> final equation

Finally, substituting all x values in the final equation we get yhat

Now we can plot a straight line with (x,yhat) this line is known as the regression line


y = m.x +c


y = m1.x1 + m2.x2 + m3.x3 + ..... + mi.xi  +  c

Linear Regression Evaluation Metrics

  • Mean Absolute Error (MAE):- MAE is the mean of absolute error value i.e. it is the mean of the difference between the actual value and predicted value
Screenshot 2021-01-12 at 4.10.58 PM.png


Actual ValuePredicted ValueError
  • Mean Squared Error (MSE):- MSE is the measures the average of the squares of the errors

MSE is always positive and a value closer to 0 or lower is better

A model with lower MSE will be deemed better

Screenshot 2021-01-12 at 4.13.50 PM.png


Actual ValuePredicted ValueErrorSquare
  • Root Mean Squared Error (RMSE):- RMSE is the Standard Deviation of the Error and root of MSE

RMSE indicates the spread of the residual error. It is always positive and a lower value indicated better performance

Screenshot 2021-01-12 at 4.17.28 PM.png
  • R Square:- R squared value is a statistical measure of how close the data are fitted regression line

It is also known as the coefficient of Determination, or the coefficient of multiple determination

Screenshot 2021-01-12 at 4.20.08 PM.png

Leave your thought here

Your email address will not be published. Required fields are marked *

Select the fields to be shown. Others will be hidden. Drag and drop to rearrange the order.
  • Image
  • SKU
  • Rating
  • Price
  • Stock
  • Availability
  • Add to cart
  • Description
  • Content
  • Weight
  • Dimensions
  • Additional information
  • Attributes
  • Custom attributes
  • Custom fields
Click outside to hide the comparison bar