Abstract
In this paper we introduce a modified version of the BUS test, which we call NBUS (New Borovkov–Utev Statistic). This latter defines a family of goodness of fit tests that can be used to detect normality against alternative hypothesis of which all moments up to the fifth exist. The test statistic depends on empirical moments and real parameters that have to be chosen appropriately. The good abilities of the NBUS with respect to BUS and other powerful normality tests are illustrated by means of a Monte Carlo experiment for finite samples. Besides, we show how an adaptation of NBUS for testing departing from normality due only to kurtosis, leads to comparable performances with classical tests based on the fourth moment.
Similar content being viewed by others
References
Anderson TW, Darling DA (1952) Asymptotic theory of certain “goodness-of-fit” criteria based on stochastic processes. Ann Stat 23:193–212
Borovkov AA, Utev SA (1984) On an inequality and a related characterization of the normal distribution. Theory Probab Appl 28:219–228
Bonett DG, Seier E (2002) A test of normality with high uniform power. Comput Stat Data Anal 40:435–445
Carota C (2010) Tests for normality in classes of skew-t alternatives. Stat Probab Lett 80:1–8
Coin D (2008) A goodness-of-fit test for normality based on polynomial regression. Comput Stat Data Anal 52:2185–2198
Daniel C (1959) Use of half-normal plots in interpreting factorial two level experiments. Technometrics 1:311–341
D’Agostino RB, Belanger A, D’Agostino RB Jr (1990) A suggestion for using powerful and informative tests of normality. Am Stat 44:316–321
D’Agostino RB, Stephens MA (eds) (1986) Goodness-of-fit techniques. Statistics: textbooks and monograph. Marcel Dekker, New York
Donnell DJ, Buja A, Stuetzle W (1994) Analysis of additive dependencies and concurvities using smallest additive principal components. Ann Stat 22:1635–1668
Goia A, Salinelli E (2010) Optimal nonlinear transformations of random variables. Ann Inst H Poincaré Probab Statist 46:653–676
Goia A, Salinelli E, Sarda P (2011) Exploring the statistical applicability of the Poincaré inequality: a test of normality. Test 20:334–352
Jarque CM, Bera AK (1980) Efficient tests for normality, homoschedasticity and serial independence of regression residuals. Econ Lett 6:255–259
Lilliefors HW (1967) On the Kolmogorov–Smirnov test for normality with mean and variance. J Am Stat Assoc 62:399–402
Mudholkar GS, Marchetti CE, Lin CT (2002) Independence characterizations and testing normality against restricted skewness–kurtosis alternatives. J Stat Plan Inferference 104:485–501
Ning W, Ngunkeng G (2013) An empirical likelihood ratio based goodness-of-fit test for skew normality. Stat Methods Appl 22:209–226
Poitras G (2006) More on the correct use of omnibus tests for normality. Econ Lett 90:304–309
Razali NM, Wah YB (2011) Power comparisons of Shapiro–Wilk, Kolmogorov–Smirnov, Lilliefors, and Anderson–Darling tests. J Stat Model Anal 2:21–33
Salinelli E (2009) Nonlinear principal components II. Characterization of normal distributions. J Multivar Anal 100:652–660
Shapiro SS, Wilk MB (1965) An analysis of variance test for normality (complete samples). Biometrika 52:591–611
Stuart A, Ord JK (1994) Kendall’s advanced theory of statistics. Distribution theory, vol 1, VI edn. Edward Arnold, New York
Thode HC (2002) Testing for normality. Marcel Dekker Inc., New York
Thode HC, Smith LA, Finch SJ (1983) Power of tests of normality for detecting scale contaminated normal samples. Commun Stat Simul 12:675–695
Urzúa CM (1996) On the correct use of omnibus tests for normality. Econ Lett 53:247–251
Yap BW, Sim CH (2011) Comparisons of various types of normality tests. J Stat Comput Simul 81:2141–2155
Acknowledgments
We wish to thank the Associate Editor and an anonymous referee for their helpful comments and suggestions which have led to substantial improvement in the presentation of this paper.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix: Proof of Proposition 1
For \(m_{3}=0\) the matrix:
has characteristic polynomial:
Since
\(\xi =1\) is an eigenvalue of \(\mathbf {M}_{Q}\) if and only if \(m_{4}=3\). Furthermore, if \(m_{4}\ne 3\) then \(\mathcal {P}\left( 1\right) >0\), hence there exists a positive eigenvalue of \(\mathbf {M}_{Q}\) smaller than \(1\). If \( m_{4}=3\), since
we find
These results imply that:
-
1.
if \(m_{5}^{2}>12\), then there exists an eigenvalue smaller than \(1\);
-
2.
if \(m_{5}^{2}<12\), the smaller eigenvalues of \(\mathbf {M}_{Q}\) is \(1\);
-
3.
if \(m_{5}^{2}=12\), the smaller eigenvalue of \(\mathbf {M}_{Q}\) is \(1\) that is a double root of the characteristic equation of \(\mathbf {M}_{Q}\).
Proof of Proposition 2
Note first of all that \(A^{2}>\xi _{2}\) for any \(m_{4}\), \(B\) and \(D\). Indeed, this inequality is true if and only if
If the left hand side of (13) is negative, then the inequality is always satisfied while, if it is non negative, (13) is equivalent to:
which is always satisfied. This result implies that if \(\xi ^{G}=A^{2}\) then \(\xi ^{G}>\xi _{\min }\). The conclusion is obvious when \(\xi ^{G}=4B^{2}\). Finally, we suppose that \(\xi ^{G}=18D^{2}\) for which the inequality \(\xi ^{G}>\xi _{\min }\) is equivalent to \(18D^{2}>\xi _{2}\). Then in this case we have \(18D^{2}<A^{2}\) and \(\xi _{2}<4B^{2}\). Assume now that these two last inequalities are satisfied. Then, \(18D^{2}>\xi _{2}\) if and only if
Note that
Assume that \(m_{4}<3\). Then, either \(A^{2}-18D^{2}\le \left( 3-m_{4}\right) \left( m_{4}+6\right) D^{2}\) and (14) is satisfied or \( A^{2}-18D^{2}>\left( 3-m_{4}\right) \left( m_{4}+6\right) D^{2}\), which leads by straightforward calculations to
which again implies that (14) is satisfied.
Assume now that \(m_{4}\ge 3\). Then (14) is satisfied if and only if
The derivation of an approximated distribution for the test statistic \(\mathfrak {N}_{n,3}\)
In order to compute the null distribution of the test statistic \(\mathfrak {N} _{n,3}\) for finite sample sizes, one could refer to the classical formula for the density of a transformation of a continuous r.v., when the transformation is defined for \(x\ge 1\) by
If \(A=1\), \(B=1/\sqrt{2}\) and \(D=1/\sqrt{6}\), then \(g\left( x\right) \) is non negative, decreasing for \(x<3\) and increasing for \(x>3\). Hence the density of \(\mathfrak {N}_{n,3}/n=g\left( \widehat{m}_{4}\right) \) can be derived using the following expression:
where \(f\) is the density of \(\widehat{m}_{4}\) and \(g_{j}\) is the restriction of \(g\) to the \(j\)-th interval of monotonicity.
Since we have not an explicit expression for \(f\), we can use one of the approximations available in the literature (see e.g. Thode 2002, Ch. 3). For instance, when we apply the approximation based on the Pearson Type IV curve, we have
where the coefficients are given by the following expressions. Defining
we have
where the moment coefficients \(\sigma \), \(\beta _{1}\) and \(\beta _{2}\) for the statistic \(\widehat{m}_{4}\) are given at page 51 of Thode (2002).
Proof of Proposition 3
The proof is based on a direct application of the Second Order Delta Method when we consider the function:
Using the second order Taylor expansion at \(\widehat{m}_{4}=3\), we have
and thus
Since under the hypothesis of normality \(\sqrt{n}\left( \widehat{m} _{4}-3\right) \) converges in distribution to a standard normal r.v., it follows that
Therefore, by Slutsky Theorem, it follows
With the choice \(A=1\) and \(D=1/\sqrt{6}\) the result follows.
The distribution of NBUS test statistic for \(k=2\)
We study the distribution of \(\mathfrak {N}_{n,2}\) under \(\mathcal {H}_{0}\). As the power of the test does not change with \(B\) and \(C\), it is not restrictive to set \(A=1\) and \(B=1/2\) (that is \(C=2\)), a choice that gives a simplified form to \(\mathfrak {N}_{n,2}\) useful for further computations. Since \(\mathfrak {N}_{n,2}\) is a transformation of \(\widehat{m}_{3}\), it is possible to deduce an approximation of the critical value of the test for finite sample sizes, as illustrated in the following remark.
Remark 3
An approximation of the critical value of the test at level \( \alpha \) when \(n\ge 8\) is given by
where \(t_{1-\alpha /2}\) is the \(1-\alpha /2\) order quantile of the Student’s t r.v. with \(v\) degrees of freedom, and
The steps to obtain the result above are the following.
We have to consider the r.v.\(~Y=g\left( X\right) \) where
Such function is bounded between \(0\) and \(1\), even and strictly increasing on the interval \(\left( 0,+\infty \right) \). Therefore, the quantile of order \(1-\alpha \) of \(Y\) can be deduced directly from the ones of order \( 1-\alpha /2\) of \(X\). Since the law of the r.v. \(X=\widehat{m}_{3}\) is well approximated (for \(n\ge 8\)) by the one of a scaled Student’s t distribution with \(\nu \) degrees of freedom (see Thode 2002, p. 50):
where
it follows that the quantile of order \(1-\alpha \) of \(Y\) is obtained by inserting the expression of the quantile of order \(1-\alpha /2\) of \(\widehat{ m}_{3}\), that is \(t_{1-\alpha /2}s\left( \dfrac{\nu }{\nu -2}\right) ^{-1/2}\) (where \(t_{1-\alpha /2}\) is the \(1-\alpha /2\) order quantile of \(T_{\nu }\) ), in (17).
For the sake of completeness, we derive the explicit expression of the density of \(Y\) and its cumulative distribution function (cdf). Since the inverse of the restriction of \(g\) to the interval of monotonicity \(\left( 0,+\infty \right) \) is equal to
by straightforward calculations we obtain the expression of the density of the r.v. \(Y\):
The cdf of \(Y\) on the interval \(\left( 0,1\right) \) is given by
where \(G\) is the cdf of the Student’s t with \(\nu \) degree of freedom.
For large samples, the asymptotic law of \(\mathfrak {N}_{n,2}\) is provided by the following:
Proposition 5
Under the hypothesis of normality one has
where \(H\) is the Daniel’s half-normal distribution (see Daniel 1959).
Proof of Proposition 5
We have to consider the transformation (17). Since \( g\left( x\right) =\left| x\right| /2+o\left( \left| x\right| \right) \) for \(x\rightarrow 0\), it follows that
Recalling that for a Gaussian sample \(\sqrt{n}\left( \widehat{m} _{3}-m_{3}\right) \) converges in distribution to a centered Gaussian r.v. with variance equal to \(6\), we obtain
Finally, recalling that \(H=\left| \mathcal {N}\left( 0,1\right) \right| \) is a half-normal distribution, by Slutsky Theorem we get
\(\square \)
Proof of Proposition 4
Consider
where \(\widehat{\xi }\) is defined in (12). The first partial derivatives of
for \(x=0\) and \(y=3\) are zero and
Since in the normal case \(m_{3}=0\), \(m_{4}=3\), and \(\left( \sqrt{n}\left( \widehat{m}_{3}-m_{3}\right) ,\sqrt{n}\left( \widehat{m}_{4}-m_{4}\right) \right) \) is asymptotically normally distributed with zero mean and covariance matrix
a direct application of the Second Order Delta Method gives
Hence (recall that under assumption of normality, \(\xi =1\)) one has:
Since, for a Gaussian population, \(\widehat{m}_{3}\overset{P}{ \longrightarrow }0\), \(\widehat{m}_{4}\overset{P}{\longrightarrow }3\) and \( \xi \left( x,y\right) \) is continuous at \(\left( 0,3\right) \), it follows \( \widehat{\xi }\overset{P}{\longrightarrow }1\). Therefore, thanks to Slutsky Theorem the statements follows.
Rights and permissions
About this article
Cite this article
Goia, A., Salinelli, E. & Sarda, P. A new powerful version of the BUS test of normality. Stat Methods Appl 24, 449–474 (2015). https://doi.org/10.1007/s10260-014-0292-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-014-0292-5