ParetoPosStable (version 1.1)

GoF: Goodness of fit tests for the Pareto Positive Stable (PPS) distribution

Description

Kolmogorov-Smirnov, Anderson-Darling and PPS goodness of fit tests to validate a PPS fit (typically from PPS.fit()).

Usage

GoF(PPSfit, k = 2000, parallel = TRUE, ncores = 2, ...)

Arguments

PPSfit

A PPSfit Object.

k

The number of iterations in the bootstrap procedure to approximate the p-values.

parallel

A logical argument specifying if parallelization is allowed in the bootstrap iteration procedure.

ncores

is the number of cores that we use if parallel is TRUE.

...

Other arguments.

Value

A list with the values of the tests statistics and the approximated p-values.

Details

It returns the Kolmogorov-Smirnov, the Anderson-Darling tests and a specific test for PPS distributions. p-values are approximated by a bootstrap procedure. The specific goodness of fit test for PPS distributions is based on the linearity of the survival function vs. the scaled observations in a double log-log scale (see Sarabia and Prieto, 2009).

References

Sarabia, J.M and Prieto, F. (2009). The Pareto-positive stable distribution: A new descriptive model for city size data, Physica A: Statistical Mechanics and its Applications, 388(19), 4179-4191.

See Also

PPS.fit, plot.PPSfit

Examples

x <- rPPS(50, 1.2, 100, 2.3)
fit <- PPS.fit(x)
GoF(fit, k = 50)