Application of Basic Regression Analysis Models: A Statistical Approach

Regression analysis is one of the well-liked statistical methods which is used for prediction analysis. In statistical data analysis, one usually needs to begin an association between the various parameters in a data set. This association is crucial for prediction and analysis. So, regression is one of the techniques for prediction analysis and data mining tasks. Each one has its own sense. To construct future predictions, Regression analysis comprises fitting the right model relating to the inclined data set. These techniques vary in terms of the type of response variable, explanatory variable and distribution. This work is mainly focused on the dissimilar types of regression techniques premeditated for various types of analysis and which types of regression are used in the context of different data sets. The study discussed the four types of regression models such as Linear Regression, Polynomial Regression, Partial Least Square Regression and Principal Component Regression, and Support Vector Regression in detail. Although the polynomial regression model agrees on a non-linear association between the response variable and explanatory variable, still it is observed as linear regression since its regression coefficients a0,a1,a2,........an are linear.