Linear Regression is important tools which are mostly used in Machine learning and AI tools .it is technique used to estimates a relationship between variables. Predict the value of one variable (dependent variables) on the basis of another variable commonly known as independent variable. A straight line fit to the data and confirming having good model.

Y=Bo+B1 x+a here y is a dependent variable, whereas Bo,B1,x,a are independent variables.

This is easily determined in SAS by using the proc reg. Dependent variables always used to write along with model statement in left side and right side should write independent variable. Even this linear regression also easily determines in R by using the LM function. Regression analysis used in several situations like analyse the relation between the size of a house and its selling price for a real state agent/also finding the exact reason what influencing the most.in example 2 predict the exam score of students who study 7.1 hours, actually that is not available in your data set.

Study Hours | Exam score |

6 | 56 |

8 | 76 |

7.4 | 69 |

Multiple linear regression having also relation between two or more variables. Multiple linear regression might be linear or nonlinear, here so many techniques are available which I am going to list down below.

Linear (Multiple regression Model)

- Simple linear
- Method of least square
- Coefficient of multiple determination
- Standard error of estimate
- Dummy Variable

Non-Linear (Multiple regression Model)

- Polynomial
- Logarithm
- Square root
- Reciprocal
- Exponential

there is a relationship between two or more variables. For instance, is there a relationship between the grade on the third French exam A student takes in the grade on the final exam. If yes, then how is it related and how strongly regression can be used here to arrive at a conclusion? This is an example of bivariate data. That is two variables. However, statisticians are mostly interested in multivariate data. Regression analysis is used to predict the value of 1 variable, the dependent variable, on the basis of other variables, the independent variables. In the simplest form of regression, linear regression, you work with one independent variable. In example one, Using the data given on the screen, you have to analyse the relation between the size of a house and its selling price for realtor. Let’s look at the two main types of regression analysis, simple linear regression and multiple linear regression. Both of these statistical methods use a linear equation to model the relationship between two or more variables. Simple linear regression considers one quantitative and independent variable X to predict the other quantitative. But dependent variable, why multiple linear regression considers more than one quantitative and qualitative variable in simple linear regression, the predictions of the explained variable why, when plotted as a function of the explanatory variable X from a straight line, the best fitting line is called the regression line. The output of this model is a function to predict the dependent variable on the basis of the values of the independent variable. The dependent variable is continuous and the independent variable can be continuous or discrete. Let’s look at the different kinds of linear and nonlinear analysis. List of linear techniques are simple method of least squares, coefficient of multiple determination, standard error of the estimate, dummy variable and interaction. Similarly, there are many non-linear techniques available such as polynomial, log, rhythmic, square root, reciprocal and exponential. To understand, this model will first look at a few assumptions. The simple linear regression model depicts the relationship between one dependent and two or more independent variables. The assumptions which justify the use of this model are as follows. Linear and additive relationship between the dependent and independent variables. Multivariate normality, Little or no Co linearity in the data. The little or no autocorrelation in the data. Homoscedasticity, that is variance of errors, same across all values of X.

**SAS Analytics Free Course with Certificate**

**SAS** is the data analysis software of the future. Discover how SAS can assist you with data management, predictive analytics, and business analytics. Join **Durga Online Trainer** today and become an** SAS** expert.