### Table 4 Correctness, coverage and number of actually classified cases for each classifier in the two cascades computed on the test set (118 cases)a

"... In PAGE 9: ..., 1994) per network and the average number of features measured in the cas- caded classifier computed on the 474 cases in the training set. Table4 contains the same statistics but computed on the 118 test cases. In the second cascade, the two threshold vec- tors, z1 and z2, were calibrated such that no case, which was classified correctly by the network with 5 features, was misclassified by the two preceding networks (using 2 and 3 features).... ..."

### Table 2. The number of completely or partially correct sequences computed by PEAKS and Lutefisk.

2003

"... In PAGE 7: ...able 1. The performance of PEAKS and Lutefisk on Albumin (bovine) MS/MS data set. The spectrum quality column s/m shows the average signal intensity of each spectrum. For the 54 MS/MS spectra, Table2 gives the numbers of sequences that PEAKS and Lutefisk computed completely correct or partially correct (with at least 6 consecutively correct amino acids). It can be seen that PEAKS performs better than Lutefisk on these 54 spectra.... In PAGE 8: ... Finally, we want to point out that all of the wrongly assigned amino acids by PEAKS are caused by mass equivalence. Some examples in Table2 are: mass (SL) = mass(TV) in precursor ... ..."

Cited by 18

### Table 3. Residual errors for corrections performed with computer-assisted technique.

"... In PAGE 6: ... Table 2 gives the angular and translational residuals for fluo- roscopic guidance. Table3 gives the angular and translational residuals for computer- assisted guidance. For both techniques, the mean and standard deviations of the residu- als is shown.... ..."

### Table 3 Cross-Section Estimates of Saving Equations Dependent Variable: GNS/GNP

"... In PAGE 21: ...orrelated with real per capita income (the corresponding correlation coefficients exceed .88). It will be useful to keep in mind these features of the data for the discussion of the empirical results below. Table3 shows estimation results using the basic equation for a variety of samples. As a benchmark, the first column reports parameter estimates using a specification excluding income distribution indicators.... In PAGE 22: ...49, which overwhelmningly rejects the null at the I percent level. Columns 2-4 in Table3 augment the specification in the first column using the Gini coefficient as income distribution indicator in different country samples. The sign pattern of the parameter estimates in the first six rows remains unchanged, and the full-sample estimates in column 2 are virtually identical to those in column 1.... In PAGE 22: ... Apart from a general loss of precision, the estimation results are otherwise very sumilar to those obtained usmg the Gini coefficient, as should be expected in view of the very high correlation reported above between the two income distribution indicators. Columns 8 and 9 of Table3 show the results of excluding from the sample the group of take-off developing countries, which some might argue are apos;exceptional apos; from the viewpoint of saving (and also growth). For both the full and LDC samples in columns 8 and 9, the main consequence is that the estimated coefficient on growth loses all significance, a finding similar to that reported by Carroll and Weil (1994) when excluding from their sample the East-Asian apos;tigers apos;.... In PAGE 23: ... The first two columns estimate our basic specification on the full and LDC sample, respectively. As can be seen, the main difference with the estimation results in Table3 is the loss of significance of income growth as a saving determinant. For the full sample, the parameter estimate on the Gini coefficient is very similar to that reported by Sahota ( 1993), but falls far short of statistical significance.... ..."

### Table 4 Cross-Section Estimates of Saving Equations Dependent Variable: GNSIGNP

"... In PAGE 23: ...stimates are biased, although the direction of the bias is not known in general (e.g., Maddala 1983). Next we check the robustness of our main result -- that income inequality does not affect aggregate saving -- by estimating altemative specifications that have been used in previous studies. Table4 presents the results using the full sample. The first two columns explore possible non-linear effects of income distribution, interacting the Gini coefficient with real per capita income and adding a quadratic term, respectively.... In PAGE 23: ...681, far below conventional significance levels). The last two columns in Table4 investigate alternative inequality indicators: column 5 uses the income share of the middle class, and column 6 adds to this the ratio of income shares of the top 20 and bottom 40 percent of the population. In neither case do we find any significant effects on saving.... ..."

### Table 3. Incremental computation is not correct if Y -disjointedness is not held

1999

"... In PAGE 5: ...1 rdisj0 and rndisj are de ned in Table 2 and are not Y -disjoint. Table3 shows that the recomputation and the incremental computation of nest operator are... ..."

Cited by 1

### Table 1. Components of the Sensor Correction That Can be Computed by a Given Number of Lines

"... In PAGE 10: ...uire additional equations (see Section 5.4). Reconsidered, the number of unknowns that can be computed by eqs. (22) and (23) depends on the number of lines that are visible (see Table1 ). Possibly we need assumptions on some of the com- ponents of r(k+i(j,l))Td(k+i(j,l)/k).... ..."

### Table 5.3: Extract of the frequencies p(correct|w) computed on the training set.

2004

### Table A5: Truncation correction for citations in computer-related patents, based on Hall, Jaffe, and Trajtenberg (2005)

2006

### Table 1: Components of the sensor correction that can be computed by a given number of lines

in (Special Issue on Visual Servoing) Predictive Visual Tracking of Lines by Industrial Robots Abstract