Massart Inequality Plot Function
Creates a Massart inequality plot for testing the empirical distribution and distribution function based on an inequality due to Massart (1990).
distIneqMassartPlot(densFn = "norm", param = NULL,
nSamp = 50, n = 100, ...)densFn |
Character. The root name of the distribution to be tested. |
n |
Numeric. The size of the sample to be used. |
nSamp |
Numeric. The number of samples used to approximate the LHS probability of the inequality. |
param |
Numeric. A vector giving the parameter values for the
distribution specified by |
... |
Passes the parameters of the distribution other than
specified by |
Massart (1990) gave a version of the Dvoretsky-Kiefer-Wolfowitz inequality with the best possible constant:
P(sup_x|F_n(x)-F(x)|> t) <= 2exp(-2nt^2)
where F_n is the empirical distribution function for a sample of n independent and identically distributed random variables with distribution function F. This inequality is true for all distribution functions, for all n and t.
The red curve in the plot shows the LHS probabilities and the black curve gives the RHS bound. The red curve should lie below the black curve in order that the empirical distribution represents a sample from the theoretical distribution.
Returns NULL invisibly.
David Scott d.scott@auckland.ac.nz, Xinxing Li xli053@aucklanduni.ac.nz
Massart P. (1990) The tight constant in the Dvoretsky-Kiefer-Wolfovitz inequality. Ann. Probab., 18, 1269–1283.
## Not run:
### Not run because of timing requirements of CRAN
### The Massart Inequality plot for standard Normal Distribution
distIneqMassartPlot()
### The Massart Inequality plot for Gamma Distribution
distIneqMassartPlot("gamma", shape = 1)
## End(Not run)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.