### Table 1: Group number, number of observations per group, classi cation, and site code. CC stands for Cnoc Coig and CNG stands for Caisteal nan Gillean. Site codes for the \modern quot; sand samples directly relate to locations shown in Figure 1. The classical statistical analysis of particle size data such as the Oronsay data tries to identify particle size distributions. While originally these distribu- tions have been typi ed by their sample moments, more recent studies tried to t parameter estimates. In the latter case, a classi cation of the (unknown) samples will be based on the estimated parameters for these distributions. In Fieller et al. (1984), log{hyperbolic and log{skew Laplace models have been discussed. See Fieller, Flenley amp; Olbricht (1992) for a summary on statistical methods for particle size data and a comparison of several parametric models that have been t to the Oronsay data. While Fieller et al. (1992) distinguish only between beach and dune sand for

"... In PAGE 10: ... e., groups 6 to 20 (see Table1 ). Within each of the 15 groups we randomly selected 2 samples and brushed them according to their classi - cation as beach at Cnoc Coig, beach at Caisteal nan Gillean, dune at Cnoc Coig, and dune at Caisteal nan Gillean.... In PAGE 32: ...entioned rule for variable `0.355 { 0.5 mm apos; (see Figure 20(c)) we come up with the classi cation rule visualized in the classi cation tree in Figure 21. When comparing the so{obtained results with the classi cation as given in Table1 , we see that we have misclassi ed two Caisteal nan Gillean midden... ..."

### Table 1: Generalized hyperbolic parameter estimates for the daily returns of the DAX from December 15, 1993 to November 26, 1997. The parameter is xed for the estimation of the hyperbolic and the NIG distribution. Log-Likelihood

2002

Cited by 11

### Table 1: The L

"... In PAGE 14: ... The total number of observed daily log-returns for each benchmarked stock is about 2500, whichprovides reliable asymptotic results for the maxi- mum likelihood ratio test. In Table1 weshow the test statistics L n for twenty leading shares of the US market. The stock codes correspond to those com- monly used.... In PAGE 14: ... We note that for the majority of log-returns of benchmarked stockpricesthe Student t distribution gives the smallest L n value and thus yields the best t in the class of symmetric generalized hyperbolic distributions considered. We observe that fourteen of the twenty L n values in Table1 appear to be smaller than the 2 0:01;;1 =0:0002 quantile. For these benchmarked stock price log-returns the hypothesis that the Student t distribution is the true underlying distribution cannot be rejected at a 99% signi cance level.... ..."

### Table 3. Confirmation of the Results

1996

"... In PAGE 17: ... As explicit analytical equations are not available for this problem, to confirm the adequacy of the response model in predicting the mean and variance of system performance, random simulations are used. In Table3 , the results are compared to those from 100 random simulations and 500 random simulations. For these simulations, the values of the control factors are fixed at their solution point and the values of the noise factors vary within the given range.... In PAGE 17: ... It can be noted that the estimations for the mean of power, mean of efficiency and mean of savings are quite accurate. For variance, in column 2 of Table3 , the estimated values are provided when assuming the noise factors are normally distributed or uniformly distributed. Random simulations yield values which are close to those obtained when assuming the noise factors are uniformly distributed.... In PAGE 17: ... Note that the accuracy is satisfactory. - INSERT TABLE 3 HERE - Table3 . Confirmation of the Results When considering multiple aspects of quality, designers may have different preferences... ..."

Cited by 36

### Table 2: Compatibility of range distribution formats The syntax of the RANGE directive is de ned as follows: Syntax: The RANGE Directive range-directive is RANGE object-name range-attr-stuff range-attr-stuff is range-distribution-list

### Table 3: Income classes for the United States and for Italy US Italy

### Table 15: Poverty and Inequality Group Weights Welfare Theil P0 P1 P2 P0*

"... In PAGE 47: ... The second (P0*) corresponds to the computation of the poverty rate under the standard assumption of a lognormal distribution of the within-group income, with endogenous mean and fixed variance. Table15 gives a static image of the differences between the two measures. At the aggregated level, P0* underestimates the poverty rate, but the results differ according to groups.... ..."

Cited by 1

### Table 7 Electricity sector in Finland after restructuring - 1998

2000

Cited by 6