### Table 5. Results of analyses comparing alternative multiple regression models prediction of controller activity.

2006

"... In PAGE 9: ... We used a method that allowed us to compare specific regression models instead of an analysis such as stepwise linear regression because we wanted to assess the relative contribution of specific variables to the model rather than simply those variables that made statistically significant contributions, such as would result when conducting a multiple regression analysis. Table5 shows the results of these analyses. Row 1 shows the multiple correlation of the full model containing all three predictor variables (Number of Aircraft, Complexity Rating, and Complexity Value) with the criterion variable (number of R and RA controller data entries).... ..."

### Table 5: Regression of Model Prediction Errors on Firm and Bond Characteristics

"... In PAGE 24: ... We use the actual spread prediction error, rather than the absolute value of the error, because we believe the factors that lead to underprediction of spreads are typically not the same as those that lead to overprediction of spreads, which is the assumption when both positive and negative errors are treated equally.19 Table5 shows five sets of regressions, two for each of the structural models. Each regression is estimated with 182 bonds whose prices are observed in a variety of different interest rate settings.... In PAGE 24: ... The last is the residual from a regression of aggregate corporate bond issuance against a time trend. The columns in Table5 show regressions of spread prediction errors under two specifications. The first specification includes all of the variables representing parameters in the five models as well as our control variables related to the interest rate environment.... In PAGE 25: ... Perhaps this problem arises from the lack of precision in Vasicek model estimates. A second feature of structural models that has often been thought in the literature of causing major pricing errors is maturity, but the regression estimates in Table5 contradict this view. To the extent that short-term bonds have a spread underprediction problem, as has been emphasized in the literature, the only evidence is in the M and G models.... In PAGE 25: ... The LT model instead relies on coupon and leverage to define risk. In the second specification shown in Table5 the coefficient on coupon is not significant, although it is still positive. The reason is that the indicator variable for old bonds, which we included to capture liquidity, is highly 20We also estimated regressions with an indicator variable for bonds with less than 5 years to maturity.... In PAGE 26: ...15 in magnitude. The second set of regression specifications reported in Table5 includes the other variables that were significant in the t-tests. Likely most of these were significant because they were related to volatility or coupon, as few are consistently significant once other factors are considered.... In PAGE 45: ... Table5 reports regression coefficients and their t-values (in parentheses) where the dependent variable is the (signed) spread prediction error (in percentage terms) based on the 150-day historical volatility. Debt issuance is the residual from a regression of aggregate debt issuance against a time trend.... ..."

### Table 4 Performance of the learning-based disambiguator on the locally disambiguated dataset.

"... In PAGE 6: ...,217 (10.62%) were author-disambiguated. The context window size3 is fixed at 8. In Table4 we summarize the results of the classification using the learning-based disambiguator. The table shows that retaining phrases improves performance greatly.... ..."

### Table 1. Variable mapping for model predictive control (MPC) controllers Process Demand

2003

"... In PAGE 3: ... p and m represent the controller prediction and move hori- zons, respectively, while k represents time. r represents the setpoint trajectory, u is the control signal/manipulated variable, and y is the estimated output; the relationship of these variables to demand network information is summa- rized in Table1 and further discussed in Section 3. The three terms in the MPC cost function penalize predicted setpoint tracking error, excess movement of the manipu- lated variable, and deviation of the manipulated variable from a target value, respectively.... In PAGE 4: ... Single-Product, Two-Echelon, Two-Node Problem Analysis Inthissection,asingle-product,two-nodedemandnetwork representing a factory and a retailer is used to establish the linkages between the inventory management problem and the process control one. The assignment of demand net- work variables to process control variables is summarized in Table1 . Figure 2 illustrates the material flows from the factory to the retailer and on to the customer.... ..."

Cited by 2

### 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. Regression model predicting Problematic Use

"... In PAGE 6: ... This is the pool of participants which we are able to use to make longitudinal models, since we have at least two waves of data from them. Table5 shows a longitudinal regression model of change in problematic use over time. This model accounts for roughly 53% of the variance in Problematic use (adjusted R2 (372) =0.... In PAGE 7: ... This result has been replicated in the current study. The final model presented in Table5 reflects the removal of five of the seven personality factor from the model due to their lack of contribution to the model fit. DISCUSSION The significant interaction of Self-Regulation and Depression, indicating that depressive affect dampens the effectiveness of the self-regulatory processes, offers strong and explicit support for Hypothesis III.... ..."

### Table 4: Mission Space Model Predictive Validation

"... In PAGE 5: ... The percent difference between predicted responses (using RSEs) and actual responses (using analysis code) for the random cases is used as a measure of the RSE accuracy. Table 3: Ranges for Mission Space Model Mission Parameter Units Minimum Maximum Payload lbs 30000 50000 Altitude feet 0 4000 Temperature F 90 95 Hover 1 Time min 1 5 Cruise 1 Combat Radius nm 50 540 Payload Dropped % 50 100 Cruise 3 Comabt Radius nm 50 530 Cruis 3 Altitude feet 0 8000 Cruise 3 Temperature ISA + C 0 30 Hover 2 Time min 2 5 Vertical ROC fpm 0 500 Flat Plate Drag Area sq feet 0 45 The results of this confirmation test are given in Table4 . This table shows the maximum, mean and standard deviation for the percent difference between the predicted response and the actual response (per analysis code) for the random cases.... ..."

Cited by 1

### Table 3. Results for rule-based, learning-based, and hybrid methods

"... In PAGE 8: ...As expected, we obtained better results progressively as we combined the rule-based and learning- based methods. As in Table3 , it is clear that the hybrid method (.6478) outperforms the conventional method of using rule alone (.... ..."

### Table 4: Parameter estimates and standard errors of age and age-squared in OLS regression models predicting the logarithm of annual earnings (men and women combined).

2006

"... In PAGE 16: ... In sum, thinking in terms of status as well as of class does not appear to add a great deal to our understanding of differences in age-earnings curves. To check on this impression more formally, we show in Table4 results from analyses, based on the same data as used in Figure 1, in which we regress earnings on age and age-squared. It is evident from the first panel of Table 4 that, as would be expected, the coefficients for both age terms are significantly larger for Classes I and II than for Class V+VI+VII.... In PAGE 16: ... To check on this impression more formally, we show in Table 4 results from analyses, based on the same data as used in Figure 1, in which we regress earnings on age and age-squared. It is evident from the first panel of Table4 that, as would be expected, the coefficients for both age terms are significantly larger for Classes I and II than for Class V+VI+VII. But, from the second panel, it can be seen that, while the coefficients for status band 1 are larger than those for status bands 2, 3 and 4, there is far less differentiation among the latter.... ..."

Cited by 2