### Table 1 Unit root tests for classical and robust measures of location, scale and skewness (augmented Dickey-Fuller test statistic)

"... In PAGE 8: ... The interested reader is referred to other papers in this field for a deeper analysis.10 As the ADF tests reported in Table1 fail to reject the null hypothesis of a unit root, both time series contain a stochastic trend. The smoothed curves in Graph 3 seem to confirm this conclusion.... In PAGE 13: ... As for scale, the time series properties of the robust measures of skewness are fundamentally different from those of the classical ones. As the ADF tests in Table1 indicate, the null hypothesis of a unit root in the classical measures was rejected at the 99% significance level. Moreover, the constant term in the test equation was not different from zero at the conventional significance levels for skew(class).... In PAGE 17: ...18 As such, the long-term behaviour of the chronic right skewness measured by dskew(125) seems to be an integral part of the inflationary process itself. Also for dskew(250), the Johansen cointegration test reveals the existence of a positive cointegration relation with inflation, notwithstanding the fact that the ADF test reported in Table1 suggests that dskew(250) is stationary.19 This measure of asymmetry tends to increase by 0.... ..."

### Table 3. Stochastic transition relation for stochastic CCP

2006

Cited by 1

### Table II: Stochastic Resonance versus Stochastic Chaos

### Table 2: Skewness of Optional Parts Skewness

"... In PAGE 6: ...optional parts can be considered with or without the skew- ness of the models. Table2 shows the skewness given to the optional parts. For the eight-merchandizing model case, skewness 1 (FS1) assigns the penetration 0.... In PAGE 9: ...When the skewness is given both on the models and parts, the resulting usage patterns resemble the skewness given in Table2 and no clear skewness effect is found. From these analysis results, appropriate plan with regard to the number of models and optional parts can be developed to reduce customer wait time and condition mismatch.... ..."

### Table 2. Model stochasticity.

2006

"... In PAGE 3: ... The PLAN C model produces as its output the individual traces of all its agents and statistical infor- mation about the time-course of the global behavior. In this paper, we have decided to investigate and analyze the three criteria presented in Table2 : the percentage of fatal- ities, average ill-health of the affected5 population (at the end of 16 hours) and the average waiting time at the hos- pitals (during the first 16 hours). The global behavior is the emergent interaction between the different classes of agents and available resources for the specific emergency scenario.... In PAGE 4: ... It follows that one simulation is not enough to evaluate the fitness function, and can only be considered as an esti- mate of the fitness. In order to study the stochasticity of the PLAN C model, Table2 shows the error rate in the esti- mation of the different analyzed objectives with respect to a true fitness value estimated on 1000 independent runs. As expected, the stochasticity is different for each objective / criteria: the number of fatalities and the average waiting time are more sensitive to the stochastic behavior than the average ill-health.... ..."

Cited by 1

### Table 1. Stochastic automata for

1999

"... In PAGE 3: ...The set of edges ?! between locations is defined as the smallest relation satisfying the rules in Table1 . The func- tion F is defined by F(xG) = G for each clock x in p.... In PAGE 6: ... Since in our semantics (cf. Table1 ) a location corre- sponds to a term, simulation can be carried out on the ba- sis of expressions rather than using their semantic repre- sentation. This means that the stochastic automaton is not entirely generated a priori but only the parts that are re- quired to choose the next step.... In PAGE 6: ...erm pi (i.e. location) and the input specification E. From term pi the set of clocks (pi) to be set is determined (by module (A) in Figure 1) and the set of possible next edges is computed according to the inference rules of Table1 (by module (B)). To compute the next valuation we only need to keep track off the last valuation vi.... ..."

Cited by 9

### Table Stochastic Data

2002

Cited by 8

### Table 1: Stochastic automata for

"... In PAGE 5: ...smallest relation satisfying the rules in Table1 . The function F is de ned by F(xG) = G for each clock x in p.... ..."

### Table 1: Stochastic automata for

"... In PAGE 5: ...smallest relation satisfying the rules in Table1 . The function F is de ned by F(xG) = G for each clock x in p.... ..."