MULTIPLE REGRESSION EQUATION
Multiple regression equation is a formula that analyzes the relationship between two or more independent variables and the dependent variable. The technique makes an accurate prediction of the dependent variable by the use of a relevant dependent variable. The equation is represented by Y=a + b1X1 + b2X2 + b3X3. ….. The equation is simplified as follows
- Y is the dependent variable
- a represents the constant value
- b1, b2, b3 represent regression slope
- X1 X2, X3 represents independent variables
The equation predicts the dependent variable with the help of many chosen independent variables. This method is used by researchers when linear regression fails to provide solutions. Multiple regression equation is used with the purpose to predict and determine the most reliable predictor. The more the number of variables, the more the ability multiple regression equation to provide solutions to many questions. Multiple regression analysis shows the relationship between a set of information given. When drawing the regression line, we can see the connection from the set data.
Advantages of multiple regression equation
- Multiple regression equations detect any deviation from the expected data.
- Multiple regression equation detects the strength of the effect of the independent variables on the dependent variable.
- The multiple regression equation allows the researchers to account for all factors in a model.
- The multiple regression equation is highly accurate and gives a better understanding of the variables involved.
- R -Squared
R- squared is a statistical method that represents a part of the dependent variable that has been explained by the independent variable. The R-Squared shows the goodness of the regression model. The higher R-Squared valued, the better the fit, and the lower the value, the worse the fit.
- Adjusted R-Squared
Adjusted R-Squared is an improvement on R squared that considers several variables. The method explains the ability of regression models that entail different variables to explain. If the predictor improves the model more than the expected chance adjusted R-Squared increases and decreases if the predictor improves the model less than the scheduled chance.
- The standard error of the estimate
The method measures the accuracy of forecasts. It measures the deviations of actual values from the estimated costs on the regression line. The standard error of an estimate is calculated by finding the square root of the standard deviation. The smaller the value of the standard error estimates, the better the calculation based on the regression line.
- Prediction of future months
Prediction of the coming months is the forecast of the events in the forthcoming months.
- Confidence in the prediction
Confidence in prediction is a range that entails the mean value of the dependent variable given specific values of the independent variables.