### Table 4: Half-Life of Top k Search Results Type Top

2007

"... In PAGE 7: ...5. The observed and predicted half-lives for each search en- gine is presented in Table4 . For top 100 results, the pre- dicted half-lives for both interfaces lie close to each other.... ..."

Cited by 2

### Table 5 Predictions of the Model

"... In PAGE 7: ... All other variables, including equity returns, can be determined in a nonlinear way once we have values for the capital stocks and the stochastic shocks. ( Table5 dis- plays the predictions of all the versions of the model.) Shocks Only to Technology.... In PAGE 7: ...s 4.10; and the return on debt is 4.07. (See Table5 .) The equity risk premium in this economy is small, only 0.... In PAGE 7: ...5, as in the data. In Table5 , we report the results of this experiment. No- tice that little has changed from the economy with only technology shocks.... ..."

### Table 1 shows the results of the study. For each model, the optimal parameters and a measure of the model apos;s average error are presented. Average error provides a single measure of performance that can be used to compare models, it is defined below.

"... In PAGE 3: ... error: 32.62% Table1 : User model parameter estimation results DISCUSSION The average errors of models 2-4 is significantly less than that for model 1, with the most sophisticated (model 4) yielding an improvement of 9.85 and 15.... ..."

### Table 5 Comparison of predictive models

"... In PAGE 12: ...05 we must accept the null hypothesis of no association between predicted risk and real risk. Table5 shows the results of comparing the predictive models to each other with respect to the remaining criteria. All the data are represented as percentages.... ..."

### Table 4 Assessment of predictive models

"... In PAGE 12: ... Results We applied the evaluation criteria on the testing set and analyzed the resulting data. Table4 shows the associations of the predictions and the real behavior of the components. The rightmost two columns show the chi-square values and the probabilities of incorrectly rejecting the null hypothesis, that is incorrectly saying that there is a significant association.... ..."

### Table 4 Assessment of predictive models

"... In PAGE 12: ... Results We applied the evaluation criteria on the testing set and analyzed the resulting data. Table4 shows the associations of the predictions and the real behavior of the components. The rightmost two columns show the chi-square values and the probabilities of incorrectly rejecting the null hypothesis, that is incorrectly saying that there is a significant association.... ..."

### Table 4 Assessment of predictive models

"... In PAGE 12: ... Results We applied the evaluation criteria on the testing set and analyzed the resulting data. Table4 shows the associations of the predictions and the real behavior of the components. The rightmost two columns show the chi-square values and the probabilities of incorrectly rejecting the null hypothesis, that is incorrectly saying that there is a significant association.... ..."

### Table 17: Evaluation of prediction model

"... In PAGE 24: ...d probability pi gt;0.66 were classified fault-prone. The threshold 0.66 was selected to balance the actual and pre- dicted number of fault-prone classes. From Table17 we see that 54 classes were predicted fault-prone. These 54 classes contained 220 out of the 232 faults in the system (95% completeness).... ..."