### Table 2 shows and parameters of each zone obtained by linear regression

1997

"... In PAGE 7: ....72 0.107 0.998 180.46 0.170 0.997 201.43 0.138 0.999 Table2 . Linear regression coe cients and correlation coe cient for main layers.... ..."

Cited by 10

### Table 3. Coefficients of the Linear Regression

2003

"... In PAGE 6: ... 5.2 Coefficients of the Linear Regression Table3 shows the coefficients of the learned regression model. The most important feature was the a priori distribution of the examples in the training data followed by the precision of the rule.... ..."

### Table 1 shows the R2 value, a measure for determining how well the linear regression

### Table 1 shows the estimated expected cross-validation error for linear regression, as a function of the level of noise . For instance-based learning:

1994

"... In PAGE 36: ...1491 + 6 0.0000 8 8 Table1 . Estimated cross-validation error for linear regression.... In PAGE 47: ...1491 + 6 0.0000 8 8 Table1 . Estimated cross-validation error for linear regression.... ..."

Cited by 4

### Table 1 shows the estimated expected cross-validation error for linear regression, as a function of the level of noise . For instance-based learning:

1

"... In PAGE 36: ...1491 + 6 0.0000 8 8 Table1 . Estimated cross-validation error for linear regression.... In PAGE 47: ...1491 + 6 0.0000 8 8 Table1 . Estimated cross-validation error for linear regression.... ..."

### Table 4: Linear regression results for predicting overall rating for good and not-good pages. The F value and corresponding signifi- cance level shows the linear combination of the metrics to be related to the overall rating.

2001

"... In PAGE 4: ... This process is repeated until the Adjusted R Square shows a significant reduction with the elimination of a predictor. Table4 shows the details of the analysis. The adjusted R2 for all of the regression analyses was significant at the .... ..."

Cited by 30

### Table 4: Linear regression results for predicting overall rating for good and not-good pages. The F value and corresponding signifi- cance level shows the linear combination of the metrics to be related to the overall rating.

2001

"... In PAGE 4: ... This process is repeated until the Adjusted R Square shows a significant reduction with the elimination of a predictor. Table4 shows the details of the analysis. The adjusted R2 for all of the regression analyses was significant at the .... ..."

Cited by 30

### Table 2. Linear regressions of 3-year runs of the PBS model showing the change in wetland elevations and the buildup of wetland eleva- tions due to biomass accumulation in the sediments as a function of three sedimentation parameter values.

"... In PAGE 9: ...ther two sites (27.0, 20.9, and 25.7 cm/28 years, respectively) but were still sensitive to the degree of water level fluctuations. The wetland elevations decreased in each poly- gon as a linear function of time ( Table2 ). The slopes of the regression lines indicate the rates of land loss in each polygon (Elevation) and the rela- tive deposition rates of organic matter (EBM).... In PAGE 9: ... Suspended sediments reach Trapagnier via pump water but this water is relatively devoid of sediments. Increasing the sedi- mentation parameter (Ksed) had little effect upon the land loss slopes shown in Table2 . This implies that there must be an increase in sediment loading if Trapagnier is to reverse the current trend.... In PAGE 12: ...413 1 emerged. That is, accretion from suspended sedi- ment deposition is proportionally more important in those areas where biomass deposition is lowest ( Table2 ), suspended sediment deposition is non- linear (Fig. 6), and habitat change is a function of spatial differences in the apparent subsidence rates (Fig.... ..."

### Table 2. Set of kinematic features that showed high correlation with subjective proficiency measures for each gesture. The regression coefficients for the linear model are also shown.

"... In PAGE 6: ...05) with the subjective proficiency ratings of gestures performed by all the groups. The combination of kinematic features that revealed statistically significant correlation with subjective proficiency measures of all samples of gestures (each gesture class is presented separately) performed by senior surgeons is shown in Table2 . For example, Table 2 shows that the thumb MCP angle value, wrist flexion and the wrist pitch had statistically high correlation with subjective measures.... In PAGE 6: ... Hence for example as shown in table 2, the thumb MCP angle, wrist flexion and wrist pitch were employed for developing predictive model for Grasping subjective proficiency ratings while for in gesture x,y,z component of wrist velocity was employed for development of the model. Multiple regression analysis was employed to determine a linear model that predicted subjective proficiency ratings for a gesture based on kinematic features identified for the gesture as shown in Table2 . The subjective proficiency measures and the associated feature values were divided into a training set and testing set.... In PAGE 6: ... Parameters were determined for a regression model for the confidence interval of 95% based on the training set between normalized proficiency ratings and predicted ratings. These parameters are shown in Table2 . The test data feature values were fed to the linear model determined by the regression analysis to determine the predicted values of subjective measures.... ..."

### Table 5 Linear regression and Pearson correlation Equation of the

"... In PAGE 9: ...00.3717 to 0.3487, and a standard deviation of the residues of 0.0373 ( Table5 ). The Pearson correlation coefficient also showed little relation between both methods (r = C00.... In PAGE 9: ...9448 for multi-layer perceptron and time delay neural networks experiments, respectively). The linear regression analysis also showed very consistent results ( Table5 ). However, as reported by Bland and Altman in their study on the comparison of the two measurement methods, assessment [1] of the agree- ment between methods is more important than the correlation or linear regression.... ..."