Using Standard Error of Estimated in Regression Model Evaluation Determination Test • R = 0.295 means that the relationship (relation) between BI1, BI2, BI3, BI4, CS1, CS2, CS3, CS4 and SB1 (Y) is 29.5%, meaning that the relationship is not tight. The bigger R means the closer the relationship. Value 0.0 - 0.19 0.2 - 0.39 0.4 - 0.59 0.6 - 0.79 0.8 - 0.99 Interpretation Very heavy Not heavy Quite heavy Erat Sangaterat • R Square of 0.087 means that 0.87% of Loyalty can be explained by BI1, BI2, BI3, BI4, CS1, CS2, CS3, CS4 while the remaining 99.13% can be explained by other factors. other factors not examined by this research. • Adjusted R Square of 0.003 means that 0.03% of Loyalty can be explained by BI1, BI2, BI3, BI4, CS1, CS2, CS3, CS4 while the remaining 99.97% can be explained by other factors not examined by this research. • Standard Error of Estimated means measuring the variation of the predicted value. Standard Error of Estimated can also be called standard deviation. In the table, the Standard Error of Estimated is 0.96385. the smaller the standard deviation, the better the model and vice versa, if the standard deviation gets bigger, the worse the model. ANOVA (F TEST) • The table above reveals that the calculated F value is 9.62 with a significant level of 0.000. while the F table at the 95% confidence level (0.05). therefore the calculation of F count> F table and a significant level of 0.000 <0.05, indicating that the effect of independent variables BI1, BI2, BI3, BI4, CS1, CS2, CS3, CS4 as a whole is positive and significant on loyalty (Y). • The table shows that regression df = 8 means that the number of independent variables is 8, namely BI1, BI2, BI3, BI4, CS1, CS2, CS3, CS4. • Total df = 89 means the number of respondents/data is 89 (where df = n-1) while the residual df = 81 comes from 89-8. • Mean Square: Sum of Square/df. In the table mean square regression (89.4) = 7.150/8.