# Linear Regression Analysis

## Introduction to Linear Regression Analysis

Linear regression is a widely used supervised learning algorithm for various applications. The advantage of using linear regression is its implementation simplicity. A Linear regression algorithm is widely used in the cases where there is need to predict numerical values using the historical data.

Suppose we have 20 years of population data and we are interested in predicting the population for the next 5 years or we have product purchase data and we are interested to find the best selling price by changing the product related features, linear regression will be the right choice to tackle this kind of interesting problems.Even though we have a bunch of regression algorithms to predict numerical values. Such as : Polynomial Regression, Stepwise Lasso Regression andElasticNet Regression.

Linear regression mostly used method for solving linear regression kind of problems, because linear regression needs less computational power compared to other regression methods and it’s the best approach to find the relation between different attributes. Suppose finding the relation between increase in temperature leads to increase in cool drinks or not.

Linear Regression means predicting scores of one variable from the scores of the second variable. The variable we are predicting is called the criterion variable and is referred to as Y. The variable we are basing our predictions is known as the predictor variable and is referred to as X. When there is only one predictor variable, the prediction method is called simple regression.The aim of linear regression is to find the best-fitting straight line through the points. The best-fitting line is called a regression line. The above equation is hypothesis equation

where:

hθ(x) is nothing but the value Y(which we are going to predicate )  for particular x ( means Y is a linear function of x)

θ0 is a constant

θ1 is  the regression coefficient

X is value of the independent variable

## Properties of the Linear Regression Line

Linear Regression line has the following properties:

1. The line minimizes the sum of squared differences between observed values (the y values) and predicted values (the hθ(x) values computed from the regression equation).
2. The regression line passes through the mean of the X values (x) and through the mean of the Y values ( hθ(x) ).
3. The regression constant (θ0) is equal to the y-intercept of the regression line.
4. The regression coefficient (θ1) is the average change in the dependent variable (Y) for a 1-unit change in the independent variable (X). It is the slope of the regression line.

The least squares regression line is the only straight line that has all of these properties.

## Goal of  Hypothesis Function

The goal of Hypothesis is to choose θ0 and θ1 so that hθ(x) is close to Y for our training data while choosing θ0 and θ1 we have to consider the cost function( J(θ) ) where we are getting low value for cost function( J(θ) ).

The below function is called as a cost function, the cost function ( J(θ) ) is nothing but just a Squared error function. ## Let’s Understand Linear Regression with Example

Before going to explain linear Regression let me summarize  the things we learn  ## Suppose we have data some thing look’s like this

No. Year Population
1 2000 1,014,004,000
2 2001 1,029,991,000
3 2002 1,045,845,000
4 2003 1,049,700,000
5 2004 1,065,071,000
6 2005 1,080,264,000
7 2006 1,095,352,000
8 2007 1,129,866,000
9 2008 1,147,996,000
10 2009 1,166,079,000
11 2010 1,173,108,000
12 2011 1,189,173,000
13 2012 1,205,074,000

No. Year Population
1 2014 ?
2 ?  2,205,074,000

## Let me draw a graph for our data ## Python Code for graph • Now what we will do is we will find the most suitable value for our  θ0 and θ1 using hypotheses equation.
• Where x is nothing but the years, and the hθ(X) is the prediction value for our hypotheses.
• Once we were done finding θ0 and θ1 we can find any value.
• Keep in mind we first find the θ0 and θ1 for our training data.
• Later we will use these θ0 and θ1 values to do the prediction for test data.

Don’t think too much about how to  find  θ0 and θ1 values, in linear regression implementation in python, I have explained how we can find θ0 and θ1 values with nice example and the coding part too.

I hope you like this post. If you have any questions, then feel free to comment below.  If you want me to write on one particular topic, then do tell it to me in the comments below.

### Related Courses:

Do check out unlimited data science courses

 Title & links Details What You Will Learn Machine Learning A-Z: Hands-On Python & R In Data Science      Students Enrolled:: 19,359 Course Overall Rating:: 4.6 Master Machine Learning on Python & R Make robust Machine Learning models. Handle specific topics like Reinforcement Learning, NLP and Deep Learning. Build an army of powerful Machine Learning models and know how to combine them to solve any problem. Machine Learning: Classification      Course Overall Rating:: 4.7 Describe the input and output of a classification model. Build a classification model to predict sentiment in a product review dataset. Analyze financial data to predict loan defaults. Evaluate your models using precision-recall metrics. Implement these techniques in Python (or in the language of your choice, though Python is highly recommended). Practical Machine Learning      Course Overall Rating:: 4.4 This course will cover the basic components of building and applying prediction functions with an emphasis on practical applications. Will provide the basic grounding in concepts such as training and tests sets, overfitting, and error rates and introduce a range of model-based and algorithmic machine learning methods These methods including regression, classification trees, Naive Bayes, and random forests. The course will cover the complete process of building prediction functions including data collection, feature creation, algorithms, and evaluation.

• […] the packages in this post  python packages for datamining. It would better once your go through Linear Regression […]

• […] With linear regression, we know that we have to find a linearity within the data so we can get θ0 and θ1 […]

• […] Linear regression […]

• […] and regression will  helpful in understanding different classification algorithms and regression analysis algorithms. The idea of this post is to give a clear picture to differentiate classification and regression […]

• […] for training our model with various machine learning algorithms like Knn, SVM, decision tree, linear regression, […]

• […] we were so interested to write about Svm as it is one of the powerful technique for Classification, Regression  & Outlier detection with an intuitive […]

• […] for training our model with various machine learning algorithms like Knn, SVM, decision tree, linear regression, […]

• […] Understanding simple linear regression is so comfortable than linear regression. […]

• […] regression classifier is more like a linear classifier which uses the calculated logits (score ) to predict the target class. If you are not familiar with […]

• […] logistic regression model is a supervised classification model. Which use the techniques of the linear regression model in the initial stages to calculate the logits (Score). So technically we can call the logistic […]

• […] this the regression course you will get the chance to learn in details about the regression techniques. You will learn the concepts of bias and variance. Estimate the model parameters using the […]

• […] you are working with a model which assumes the linear relationship between the dependent variables, correlation can help you come up with an initial list of […]