On the choice of the smoothing parameter for the BHEP goodness-of-fit test. (English) Zbl 1452.62322

Tenreiro, Carlos

Comput. Stat. Data Anal. 53, No. 4, 1038-1053 (2009).

Summary: The BHEP (Baringhaus-Henze-Epps-Pulley) test for assessing univariate and multivariate normality has shown itself to be a relevant test procedure, recommended in some recent comparative studies. It is well known that the finite sample behaviour of the BHEP goodness-of-fit test strongly depends on the choice of a smoothing parameter \(h\). A theoretical and finite sample based description of the role played by the smoothing parameter in the detection of departures from the null hypothesis of normality is given. Additionally, the results of a Monte Carlo study are reported in order to propose an easy-to-use rule for choosing \(h\). In the important multivariate case, and contrary to the usual choice of \(h\), the BHEP test with the proposed smoothing parameter presents a comparatively good performance against a wide range of alternative distributions. In practice, if no relevant information about the tail of the alternatives is available, the use of this new bandwidth is strongly recommended. Otherwise, new choices of \(h\) which are suitable for short tailed and long tailed alternative distributions are also proposed.

MSC:

62G10	Nonparametric hypothesis testing
62H15	Hypothesis testing in multivariate analysis
62-08	Computational methods for problems pertaining to statistics

Software:

R

References:

[1]	Anderson, N.H.; Hall, P.; Titterington, D.M., Two-sample test statistics for measuring discrepancies between two multivariate probability density functions using kernel-based density estimates, J. multivariate anal., 50, 41-54, (1994) · Zbl 0798.62055
[2]	Arcones, M.A., (), 196-206
[3]	Arcones, M.A.; Wang, Y., Some new tests for normality based on U-processes, Statist. probab. lett., 76, 69-82, (2006) · Zbl 1085.62047
[4]	Arcones, M.A., Two tests for multivariate normality based on the characteristic function, Math. methods statist., 16, 177-201, (2007) · Zbl 1231.62102
[5]	Bahadur, R.R., Stochastic comparison of tests, Ann. math. statist., 31, 276-295, (1960) · Zbl 0201.52203
[6]	Bahadur, R.R., Rates of convergence of estimates and test statistics, Ann. math. statist., 38, 303-324, (1967) · Zbl 0201.52106
[7]	Bahadur, R.R., Some limit theorems in statistics, (1971), SIAM Philadelphia · Zbl 0257.62015
[8]	Baringhaus, L.; Henze, N., A consistent test for multivariate normality based on the empirical characteristic function, Metrika, 35, 339-348, (1988) · Zbl 0654.62046
[9]	Baringhaus, L.; Danschke, R.; Henze, N., Recent and classical tests for normality. A comparative study, Comm. statist. simulation comput., 18, 363-379, (1989) · Zbl 0695.62120
[10]	Bickel, P.J.; Rosenblatt, M., On some global measures of the deviations of density function estimates, Ann. statist., 1, 1071-1095, (1973) · Zbl 0275.62033
[11]	Bowman, A.W.; Foster, P.J., Adaptive smoothing and density-based tests of multivariate normality, J. amer. statist. assoc., 88, 529-537, (1993) · Zbl 0775.62086
[12]	Coin, D., A goodness-of-fit test for normality based on polynomial regression, Comput. statist. data anal., 52, 2185-2198, (2008) · Zbl 1452.62307
[13]	Csörgő, S., Consistency of some tests for multivariate normality, Metrika, 36, 107-116, (1989) · Zbl 0705.62053
[14]	Durbin, J.; Knott, M.; Taylor, C.C., Components of cramér – von Mises statistics, II, J. roy. statist. soc. ser. B, 37, 216-237, (1975) · Zbl 0335.62032
[15]	Epps, T.W.; Pulley, L.B., A test for normality based on the empirical characteristic function, Biometrika, 70, 723-726, (1983) · Zbl 0523.62045
[16]	Fan, Y., Testing the goodness of fit of a parametric density function by kernel method, Econom. theory, 10, 316-356, (1994)
[17]	Fan, Y., Goodness-of-fit tests based on kernel density estimators with fixed smoothing parameters, Econom. theory, 14, 604-621, (1998)
[18]	Fang, H.-B.; Fang, K.-T.; Kotz, S., The meta-elliptical distributions with given marginals, J. multivariate anal., 82, 1-16, (2002) · Zbl 1002.62016
[19]	Farrel, P.J.; Salibian-Barrera, M.; Naczk, K., On tests for multivariate normality and associated simulation studies, J. stat. comput. simul., 77, 1065-1080, (2007) · Zbl 1255.62163
[20]	Gouriéroux, C.; Tenreiro, C., Local power properties of kernel based goodness of fit tests, J. multivariate anal., 78, 161-190, (2001) · Zbl 1081.62529
[21]	Gregory, G.G., On efficiency and optimality of quadratic tests, Ann. statist., 8, 116-131, (1980) · Zbl 0424.62012
[22]	Hall, P., The bootstrap and Edgeworth expansion, (1997), Springer New York
[23]	Henze, N.; Zirkler, B., A class of invariant consistent tests for multivariate normality, Comm. stat. theory methods, 19, 3595-3617, (1990) · Zbl 0738.62068
[24]	Henze, N., Extreme smoothing and testing for multivariate normality, Statist. probab. lett., 35, 203-213, (1997) · Zbl 0955.62060
[25]	Henze, N.; Wagner, T., A new approach to the BHEP tests for multivariate normality, J. multivariate anal., 62, 1-23, (1997) · Zbl 0874.62043
[26]	Johnson, M.E.; Tietjen, G.L.; Beckman, R.J., A new family of probability distributions with applications to Monte Carlo studies, J. amer. statist. assoc., 75, 276-279, (1980) · Zbl 0462.62022
[27]	Johnson, M.E., Multivariate statistical simulation, (1987), Wiley New York · Zbl 0604.62056
[28]	Mecklin, C.J.; Mundfrom, D.J., A Monte Carlo comparison of type I and type II error rates of tests of multivariate normality, J. stat. comput. simul., 75, 93-107, (2005) · Zbl 1096.62058
[29]	Nikitin, Y., Asymptotic efficiency of nonparametric tests, (1995), Cambridge University Press · Zbl 0879.62045
[30]	R: A language and environment for statistical computing, (2006), R Foundation for Statistical Computing Vienna, Austria
[31]	Ramberg, J.S.; Schmeiser, B.W., An approximate method for generating asymmetric random variables, Commun. ACM, 17, 78-82, (1974) · Zbl 0273.65004
[32]	Romeu, J.L.; Ozturk, A., A comparative study of goodness-of-fit tests for multivariate normality, J. multivariate anal., 46, 309-334, (1993) · Zbl 0778.62051
[33]	Tenreiro, C., On the role played by the fixed bandwidth in the bickel – rosenblatt goodness-of-fit test, Sort, 29, 201-216, (2005) · Zbl 1274.62333
[34]	Tenreiro, C., On the asymptotic behaviour of location-scale invariant bickel – rosenblatt tests, J. statist. plann. inference, 137, 103-116, (2007) · Zbl 1098.62055
[35]	Yazici, B.; Yolacan, S., A comparison of various tests of normality, J. stat. comput. simul., 77, 175-183, (2007) · Zbl 1112.62039