Testing for Normality

The MODEL Procedure

Testing for Normality

The NORMAL option on the FIT statement performs multivariate and univariate tests of normality.

The three multivariate tests provided are Mardia's skewness test and kurtosis test (Mardia 1980) and the Henze-Zirkler ${T_{n, {\beta}}}$ test (Henze and Zirkler 1990). The two univariate tests provided are the Shapiro-Wilk W test and the Kolmogorov-Smirnov test. (For details on the univariate tests, refer to "Tests for Normality" in "The UNIVARIATE Procedure" chapter in the SAS Procedures Guide.) The null hypothesis for all these tests is that the residuals are normally distributed.

For a random sample X₁, ... , X_n, ${X_{i} {\in} \rm{R}^d}$ ,where d is the dimension of X_i and n is the number of observations, a measure of multivariate skewness is

$b_{1,d} = \frac{1}{n^2} \sum_{i=1}^n \sum_{j=1}^n{[ ( X_{i} - {\mu})' S^{-1} (X_{j} - {\mu})]^3 }$

where S is the sample covariance matrix of X. For weighted regression, both S and ${(X_{i} - {\mu})}$ are computed using the weights supplied by the WEIGHT statement or the _WEIGHT_ variable.

Mardia showed that under the null hypothesis [n/6]b_1,d is asymptotically distributed as ${{\chi}^2( d(d+1)(d+2)/6)}$ .

A measure of multivariate kurtosis is given by

$b_{2,d} = \frac{1}n \sum_{i=1}^n{[( X_{i} - {\mu})^{'} S^{-1} ( X_{i} - {\mu})]^2 }$

Mardia showed that under the null hypothesis b_2,dis asymptotically normally distributed with mean d(d+2) and variance 8d(d+2)/n.

The Henze-Zirkler test is based on a nonnegative functional D(.,.)that measures the distance between two distribution functions and has the property that

D(N_d(0, I_d), Q) = 0

if and only if

Q = N_d(0, I_d)

where ${\rm{N}_{d}({\mu}, {\Sigma}_{d}) }$ is a d-dimensional normal distribution.

The distance measure D(.,.) can be written as

$D_{{\beta}}( P, Q ) = \int_{\rm{R}^d}^{}{| \hat{P}(t) - \hat{Q}(t) |^2 {\varphi}_{{\beta}}(t) dt}$

where ${\hat{P}(t)}$ and ${\hat{Q}(t)}$ are the Fourier transforms of P and Q, and ${{\varphi}_{{\beta}}(t)}$ is a weight or a kernel function. The density of the normal distribution ${\rm{N}_{d}(0,{\beta}^2I_{d})}$ is used as ${{\varphi}_{{\beta}}(t)}$

${\varphi}_{{\beta}}(t) = ( 2{\pi}{\beta}^2)^{\frac{-d}2} \rm{exp} ( \frac{- | t|^2}{2{\beta}^2} ), \hspace*{1em} t {\in} \rm{R}^d$

where |t| = ( t^' t)^0.5.

The parameter ${{\beta}}$ depends on n as

${\beta}_{d}(n) = \frac{1}{\sqrt{2}}( \frac{2d+1}4 )^{1/(d+4)} n^{1/(d+4)}$

The test statistic computed is called ${T_{{\beta}}(d)}$ and is approximately distributed as a log normal. The log normal distribution is used to compute the null hypothesis probability.

$T_{{\beta}}(d) = &\frac{1}{n^2}& \sum_{j=1}^n{\sum_{k=1}^n{{\exp}(- \frac{{\beta... ...{\exp}(- \frac{{\beta}^2}{2(1+{\beta}^2)} | Y_{j}|^2)} + (1+2{\beta}^2)^{-d/2}$

where

|Y_j - Y_k|² = (X_j - X_k)' S^-1 (X_j - X_k)

$| Y_{j}|^2 = (X_{j} - \bar{X})' S^{-1} (X_{j} - \bar{X})$

Monte Carlo simulations suggest that ${T_{{\beta}}(d)}$ has good power against distributions with heavy tails.

The Shapiro-Wilk W test is computed only when the number of observations (n) is less than 2000.

The following is an example of the output produced by the NORMAL option:

The MODEL Procedure

Normality Test
Equation	Test Statistic	Value	Prob
y1	Shapiro-Wilk W	0.37	<.0001
y2	Shapiro-Wilk W	0.84	<.0001
System	Mardia Skewness	286.4	<.0001
	Mardia Kurtosis	31.28	<.0001
	Henze-Zirkler T	7.09	<.0001

Figure 14.31: Normality Test Output

Chapter Contents
Previous
Next
Top