Hello, appreciate if anyone could help me on Multiple Regression analysis. Thanks!
i)
Multicollinearity of the predictor variables are defined by Variance Inflation Factors(VIF) statistic. If the measures VIF statistic value is between 1 to 10, then there is no sign of multicollinearity.
From the regression model summary,
Model | Predictor variable | VIF | Multicollinearity |
1 | Age | 1.032 | no |
Gender | 1.032 | no | |
2 | Age | 1.047 | no |
Gender | 1.051 | no | |
Perceived Usefulness | 1.295 | no | |
Complementary | 1.314 | no | |
Convenience | 1.251 | no | |
3 | Age | 1.051 | no |
Gender | 1.055 | no | |
Perceived Usefulness | 1.392 | no | |
Complementary | 1.456 | no | |
Convenience | 1.338 | no | |
Entertainment | 1.418 | no |
ii)
The significance of predictor variables, age and gender determine by significance p-value of the respective coefficient value.
From the regression model summary,
Model | Predictor variable | Coefficient | Sig. | ||
1 | Age | 0.047 | 0.376 | >0.05 | Not Significant |
Gender | -0.071 | 0.317 | >0.05 | Not Significant | |
2 | Age | 0.064 | 0.159 | >0.05 | Not Significant |
Gender | 0.02 | 0.747 | >0.05 | Not Significant | |
3 | Age | 0.043 | 0.275 | >0.05 | Not Significant |
Gender | 0.038 | 0.465 | >0.05 | Not Significant |
In each of the three model both the predictor variable Age and Gender are not significant at 5% significance level.
iii)
Model | Predictor variable | Significance P-value | |
1 | Age | 0.376 | Not Significant |
Gender | 0.317 | Not Significant | |
2 | Age | 0.159 | Not Significant |
Gender | 0.747 | Not Significant | |
Perceived Usefulness | 0 | Significant | |
Complementary | 0 | Significant | |
Convenience | 0 | Significant | |
3 | Age | 0.275 | Not Significant |
Gender | 0.465 | Not Significant | |
Perceived Usefulness | 0.016 | Significant | |
Complementary | 0.051 | Significant | |
Convenience | 0.004 | Significant | |
Entertainment | 0 | Significant |
All the other predictor variable except Age and Gender are significant hence only these two variable need to be removed from the model.
iv)
The R-square value and adjusted R-square value both increased by adding the predictor variables Perceived Usefulness, Complementary and Convenience in model 2 and further increase by adding Entertainment in model 3. These variables significantly explains the model while the variables Age and Gender need to be remove to improve the model further.
Hello, appreciate if anyone could help me on Multiple Regression analysis. Thanks! Question 4 Use the...