Liner regression
Liner regression fall under the category of supervised learning model. This model is subdivided in to two, which is simple liner regression and multiple liner regression.
In simple linear regression only one dependent and one independent variable is used to make the model hence the name simple linear. In the multiple liner regression, there are usually more than one independent variable (Watson, 1964). Multiple linear model explores the correlation of numerous different variables with one dependent variable. When each of the independent variables is defined to predict the dependent variable, the multiple variableness information can be used to produce an exact estimate of the level of impact on the result variable (Fox, 1997). The model establishes a best liner relationship between the variables. The central task of the multiple linear regression analysis is to fit a single line via a scatter plot. To be precise, a line through a multi-dimensional data space is fitted in the MLR to achieve a line of best fit. One dependent and two regressor variables are the MLR simplest form
Model1 (SLR)
Y –hat = βx + e
Model2 (MLR)
yi=βx1 + βx2 + βx3 + e
Where y-hat is the y estimates and the variable β is the independent variable, while e is the error term. When fitting liner regression model, the model tries to find the least square errors as much as possible.
Though linear regression cannot be considered a flexible model, it’s the one mostly used in statistical analysis since it is easy to interpret and its degree of accuracy for continuous variables is high. Regression analysis is important because it provides a powerful statistical method for a business to analyze the relationship between two or more interest variables (Draper & Smith, 1998). Essentially, regression analysis is an interesting statistical issue, it is important to understand. Businesses incorporated many ideas from statistics because they can show volubility to help a company recognize a range of fundamental things and then take informed well-studied decisions based on different data aspects.
References
Draper, N. R., & Smith, H. (1998). Applied regression analysis (Vol. 326). John Wiley & Sons.
Fox, J. (1997). Applied regression analysis, linear models, and related methods. Sage Publications, Inc.
Watson, G. S. (1964). Smooth regression analysis. Sankhyā: The Indian Journal of Statistics, Series A, 359-372.