|
Strength of association
|
ω2
|
≈ 0.01
|
small association
|
| | |
≈ 0.06
|
medium association
|
| | |
≈ 0.14
|
large association
|
| |
φc
|
< 0.3
|
little or no association
|
| | |
0.3 to 0.7
|
weak association
|
| | |
0.7 to 1.0
|
strong association
|
|
Regression model evaluation
|
deviance statistic
|
-
|
significance of unexplained (residual) variance in the dependent variable; thus is desired to be non-significant
|
| |
Nagelkerke's R2
|
-
|
the association between predictor variables and the outcome variable. Statistic ranges from 0 to 1 with higher scores indicating stronger associations.
|
| |
% of correctly classified cases
|
-
|
calculated at the start of the procedure and at the end of the analysis using the cut-off point of 0.5 for the estimated probability of the outcome variable
|
| |
sensitivity
|
-
|
the proportion of true positives or the proportion of cases correctly identified by the test as meeting the response category
|
| |
specificity
|
-
|
the proportion of true negatives or the proportion of cases correctly identified by the test as meeting the reference category
|
| |
c statistic
|
-
|
varies from 0.5 (the models predictions are no better than chance) to 1 (the model always assigns the higher probabilities to correct cases than incorrect ones)
|
