Using of ANOVA and Multiple Regression in Analyzing the Impact of Independent Variables

Using of ANOVA and Multiple Regression in Analyzing the Impact of Independent Variables Interpret the multiple regression results below: 1) Model Summaryb Description: • R = 0.805 means that the relationship (relation) between Role, Family, Price, Location, Product, Group, Promotion is 80.5%. This means that the relationship is very close. The bigger R means the closer the relationship. To ensure the type of relationship between variables can be seen in the following table. Relationship Table between Variables Value 0.0 - 0.19 0.2 - 0.39 0.4 - 0.59 0.6 - 0.79 0.8 - 0.99 Interpretation Not Very Tight Not Tight Close Enough Erat Very Tight • R square of 0.648 means that 64.8% of the decision can be explained by Role, Family, Price, Location, Product, Group, Promotion while the remaining 35.2% can be explained by other factors not examined bythis study. • Adjusted R Square of 0.622 means 62.2% % of decisions can be made. explained by Role, Family, Price, Location, Product, Group, Promotion while the remaining 37.8% can be explained by other factors not examined by this study. There are two choices here, whether to use R Square or Adjusted R Square. If there are more than two variables, the Adjusted R Square is used. • Standard Error of Estimated means that it measures the variation of the value that is predicted Standard Error of Estimated can also be called standard deviation. In the example, the Standard Error of Estimated is 2.65391. 2) ANOVAa Description: • The table above reveals that the calculated F value is 24.229 with a significance level of 0.000. While the F table at the 95% confidence level (α = 0.05) is 2.6. Because in both calculations, namely F count> F table and the level of significance (0.000) <0.05, it shows that the influence of the independent variables Role, Family, Price, Location, Product, Group, Promotion simultaneously is positive and significant on decisions. Additional Information: • The table shows that Regression df = 7 means that the number of independent variables is 7, namely Role, Family, Price, Location, Product, Group, Promotion. • Total df = 99 means the number of respondents/data is 99 (where df = n-1) while Regression df = 92 comes from 99-7. • Residual: the difference between the actual decision and the predicted decision. Residual = Total - regression. • Mean Square: Sum of Square/ df. In the example mean square regression (170,647) = 1194,531/7 • SSE (sum of squares for error) shows the sum of squares for error meaning that if a regression equation is obtained from substituting the values of a and b that minimize the SSE, the least squares prediction regression line equation will result. 3) Coefficientsa Description • The product variable has a positive and significant effect on the decision, this can be seen from the significant value (0.000) below (smaller than) 0.05 and the calculated t value(6,571) > ttabel means that if the product variable is increased by one unit (unit), the decision will increase by 0.320 units (unit). • The promotion variable has a positive and significant effect (0.863) below (smaller than) 0.05 and the calculated t value(0.173) > ttabel means that if the promotion variable is increased by one unit (unit), the decision will increase by 0.020 one unit (unit). • The price variable has a positive and significant effect (0.304) below (smaller than) 0.05 and the calculated t value(1,033) > ttabel means that if the price variable is increased by one unit (unit), the decision will increase by 0.121 units (unit). • The location variable has a positive and significant effect (0.014) below (smaller than) 0.05 and the value of t count (2.497) > ttabel means that if the location variable is increased by one unit (unit), the decision will increase by 0.358 units (unit). • Group variables have a positive and significant effect (0.723) below (smaller than) 0.05 and the value of t count(0,356) > ttabel means that if the group variable is increased by one unit (unit), the decision will increase by 0.034 units (unit). • Family variables have a positive and significant effect (0.029) below (smaller than) 0.05 and the calculated t value(2,214) > ttabel means that if the group variable is increased by one unit (unit), the decision will increase by 0.220 units (unit). • Variable Role has a positive and significant effect (0.077) below (smaller than) 0.05 and the value of t count(1,788) > ttabel means that if the group variable is increased by one unit (unit), the decision will increase by 0.372 units (unit). • Based on the output results, the formula for the regression equation is: Y = β0 + x1 + β3 x3 + β x44 + β5 x5 + β6 x6 + β7 x7 + ei Y = - 6,830 + 0.320 Product + 0.020 Promotion + 0.121 Price + 0.358 Location + 0.034 Group + 0.220 Family + 0.372 Role