# testunknown: Process the Samples Whose Distribution is to be Tested In MVNtestchar: Test for Multivariate Normal Distribution Based on a Characterization

## Description

Create positive definite matrices without nuisance parameters. Tabulate distribution. Calculate goodness of fit

## Usage

 ```1 2``` ```testunknown(x, pvector, k, diagnose.s = FALSE, diagnose = FALSE, verbose = TRUE) ```

## Arguments

 `x ` Name of matrix or array. `pvector` Dimensionality of random vectors `k ` Number of cuts per unit for diagonal elements of matrix. Program uses 2k cuts per unit for off-diagonal elements `diagnose.s ` Logical T causes printing of diagnostic terms in internal called function(s) `diagnose ` Logical. T causes printing of diagnostic content `verbose ` Logical. T causes printing of function ID before and after running

## Value

a list including elements

 `Distribution` List. Count of pd matrices within individual subcubes of pd space, 1 for each layer of list `Goodness of fit` List. Chi square test of goodness of fit to uniform distribution, 1 for each layer of list `Call` Call to testunknown function

## Author(s)

William R. Fairweather

## References

Csorgo, M and Seshadri, V (1970). On the problem of replacing composite hypotheses by equivalent simple ones, Rev. Int. Statist. Instit., 38, 351-368 Csorgo,M and Seshadri,V (1971). Characterizing the Gaussian and exponential laws by mappings onto the unit interval, Z. Wahrscheinlickhkeitstheorie verw. Geb., 18, 333-339. Fairweather, WR (1973). A test for multivariate normality based on a characterization. Dissertation submitted in partial fulfillment of the requirements for the Doctor of Philosophy, University of Washington, Seattle WA.

## Examples

 ```1 2 3``` ```data(unknown.Np2) testunknown(x=unknown.Np2, pvector=2, k=20, diagnose.s = FALSE, diagnose = FALSE, verbose = TRUE) ```

MVNtestchar documentation built on July 26, 2020, 1:07 a.m.