Linear Regression in Python using Statsmodels 2021 [New🔴]

In this tutorial video, we learned Linear Regression in Python using statsmodels. To do the analysis, we used least square method for linear regression analysis. Click "Show more" to learn more 👇:-

Statsmodels python package is used to compute regression with multiple predictors.

Topics covered:
• How to do linear regression in Python?
• statsmodel for linear regression in Python
• Interpretation of the linear regression results in Python
• Making predictions based on the regression results
• Introduction (0:00)
• Data for Linear regression in Python (2:00)
• Using statsmodels for linear regression (4:00)
• Making Predictions based on the Regression Results (6:25)
• Ploting linear regression curve in python (9:30)
• Analysis of linear regression equation (12:42)

𝐆𝐞𝐭 𝐢𝐧𝐬𝐭𝐚𝐧𝐭 𝐮𝐩𝐝𝐚𝐭𝐞𝐬 𝐚𝐛𝐨𝐮𝐭 𝐭𝐡𝐞 𝐥𝐚𝐭𝐞𝐬𝐭 𝐯𝐢𝐝𝐞𝐨𝐬:

Linear regression is used as a predictive model that assumes a linear relationship between the dependent variable (which is the variable we are trying to predict/estimate) and the independent variable/s (input variable/s used in the prediction).

Under Simple Linear Regression, only one independent/input variable is used to predict the dependent variable. It has the following structure:

Y = C + M*X

Y = Dependent variable (output/outcome/prediction/estimation)
C = Constant (Y-Intercept)
M = Slope of the regression line (the effect that X has on Y)
X = Independent variable (input variable used in the prediction of Y)

𝐌𝐚𝐤𝐞 𝐬𝐮𝐫𝐞 𝐭𝐨 𝐬𝐮𝐛𝐬𝐜𝐫𝐢𝐛𝐞 𝐬𝐨 𝐲𝐨𝐮 𝐝𝐨𝐧'𝐭 𝐦𝐢𝐬𝐬 𝐨𝐮𝐭 𝐨𝐧 𝐦𝐲 𝐟𝐮𝐭𝐮𝐫𝐞 𝐯𝐢𝐝𝐞𝐨𝐬:

After subscribing, 𝐠𝐞𝐭 𝐟𝐫𝐞𝐞 𝐚𝐜𝐜𝐞𝐬𝐬 𝐭𝐨 𝐦𝐲 𝐆𝐨𝐨𝐠𝐥𝐞 𝐃𝐫𝐢𝐯𝐞: Follow steps on my YouTube Channel.

I used Anaconda jupyterlab for this code. It is an amazing platform for beginners. #fpritvik #regression

[tonycardinal]

thank you. How would you predict the value for a single point? In other words how can I predict the value of the dependent variable from one indepedent variable?

[faltumaintimepass]

Thanks for showing polynomial regression. Need clarification, when you are using x1^2 as a different variable (thus, making the quadratic equation as a multi-linear regression, we will have issue of multicolleniarity, between x1 and x1^2 variables. And one of the assumptions for linear regression model is :


No Multicollenearity - i.e., two and more variables shouldn't have high correlation b/w each other


Considering that this assumption is getting violated, so our result in your example can't be right. Please correct my understanding, if wrong.

[deekshitashamchavan]

Thank you! This is very helpful. Will be using it for my project

[alfazbaig]

Bro LinearRegression from sklearn is different method and StatsModel is different??

[amolkabugade]

why did't you used train test split