1. From the ANOVA table, we can see that the F statistic computed is 30.753 which has p-value as significant (<0.001). Hence, the regression model can be used to explain and predict X20 - Likely to recommend.
2. The accuracy of the regression model can be told by the adjusted R-square statistic:
Adjusted R-square value = 0.511
Hence, 51.1% variation can be explained by the model.
3. The variables which have a significant impact on X20 will have significant p-value. We can see from the table that the following variables are significant (at 95% confidence level) or having p-value<0.05 which is given in the last column under Sig.
X6 - Product Quality
X8 - Technical Support
X10 - Advertising
X11 - Product Line
X12 - Salesforce Image
X14 - Warranty and Claims
X17: Price flexibility
4. The advertising variable, X10 is significant and has a negative standardised coefficient = -0.131
This means that it is negatively related to the response variable - likely to recommend. Hence, if we increase the advertising capabilities, the response variable will decrease. Hence, the company should not increase its advertising capabilities.
5. Let's check out the coefficients of both the variables:
Price flexibility, X17 = 0.298
Product quality, X6 = 0.455
Hence, as the coefficient of product quality is more than the coefficient of price flexibility, we can say that there is a greater effect of product quality on the customers. Hence, they value product quality more than the price flexibility.
Question #1 Consider the following model that predicts X20 (Likely to recommend) Model Summaryb M...