Regression analysis in research helps analyze the relationship between independent and dependent variables. For example, in the marketing application, the independent variable refers to the instruments that are changed to help in the achievement of the best outcome (dependent variable). Regression analysis is necessary for research, as it indicates whether there is a significant relationship between the independent and dependent variables (Anderson et al., 2017, pp. 602). It also shows the relative strength of various independent variables' effects on the dependent variable. Nonetheless, regression analysis helps to make predictions.
The simple form of regression analysis involves one dependent and a single independent variable. For example, the managers of a pizza outlet near campus outlets believe that their sales (denoted as y) are positively related to the population size of the student (denoted as x) (Anderson et al., 2017, pp.602). Therefore, the hotel managers believe that the pizza outlets that are close to the college outlets generate higher sales than those far away from the college. The equation describing the relationship between x and y and the error term refers to the regression model. Therefore, the simple linear regression model is
Delegate your assignment to our experts and they will do the rest.
The P 0 and the P 1 refers to the model parameters
(Greek letter epsilon), which is a random variable depicts the error term (Anderson et al., 2017, pp. 602).
Error term explains variability in the y variable, which is unexplainable by the relationship between x and y. On the other hand, regression equation refers to the equation, which describes how the outcome value y, expressed as E (y), relates to the x variable (Anderson et al., 2017, pp. 603).
Simple Linear Regression Equation
Model building refers to the process of developing an estimated regression equation that shows the relationship of a dependent variable and one or more independent variables (Anderson et al., 2017, pp.757). The model building major issues are related to finding the best functional form of the correlation as well as choosing the independent variables necessary in a particular model.
Reference
Anderson, D., Sweeney, D., Williams, T., Camm, J., & Cochran, J. (2017). Statistics for Business and Economics (13th ed.).
