Abstract
In this paper, a test for the homogeneity of two bidimensional populations is proposed. It is based on the L 2-norm of the difference between the empirical characteristic functions associated with independent random samples from each population. We first approximate this norm and then we give two bootstrap algorithms to consistently estimate the null distribution of the resultant test statistic. A simulation study illustrates the goodness of these two bootstrap estimators and compares the proposed test with others.
Similar content being viewed by others
References
Alba-Fernández V, Barrera D, Jiménez MD (2001) A homogeneity test based on empirical characteristic functions. Comput Stat 16: 255–270
Alba-Fernández V, Ibáñez MJ, Jiménez MD (2004) A bootstrap algorithm for the two-sample problem using trigonometric Hermite Spline interpolation. Commun Nonlinear Sci Numer Simul 9: 275–286
Baringhaus L, Franz C (2004) On a new multivariate two-sample test. J Multivar Anal 88: 190–206
Baringhaus L, Henze N (1988) A consistent test for multivariate normality based on the empirical characteristic function. Metrika 35: 339–348
Bickel PJ, Freedman DA (1981) Some asymptotic theory for the bootstrap. Ann Stat 9: 1196–1217
Ciarlet PG (1991) Basic error estimates for elliptic problems. In: Ciarlet PG, Lions LL (eds) Handbook of numerical analysis. Finite elements methods (Part 1), vol II. North Holland, pp 17–351
Csörgő S (1981a) Limit behaviour of the empirical characteristic function. Ann Probab 9: 130–144
Csörgő S (1981) The empirical characteristic process when parameters are estimated. In: Gani J, Rohatgi VK (eds) Contributions to probability. Academic Press, London, pp 708–723
Epps TW (2005) Tests for location-scale families based on the empirical characteristic function. Metrika 62: 99–114
Epps TW, Pulley LB (1983) A test for normality based on the empirical characteristic function. Biometrika 70: 723–726
Epps TW, Singleton KJ (1986) An Omnibus test for the two-sample problem using the empirical characteristic function. J Stat Comput Simul 26: 177–203
Feuerverger A, Mureika RA (1977) The empirical characteristic function and its applications. Ann Stat 5: 88–97
Jiménez Gamero MD, Muñoz García J, Pino Mejías R (2005) Testing goodness of fit for the distribution of errors in multivariate linear models. J Multiv Anal 95: 301–322
Johnson NL, Kotz S, Balakrishnan N (1997) Discrete multivariate distributions. Wiley, New York
Koutrouvelis IA (1980) A goodness-of-fit test of simple hypothesis based on the empirical characteristic function. Biometrika 67: 238–240
Koutrouvelis IA, Kellermeier J (1981) A goodness-of-fit test based on the empirical characteristic function when parameters must be estimated. J R Stat Soc Ser B 43: 173–176
Lancaster P, Salkauskas K (1986) Curve and surface fitting. Academic Press, London
Powell MJD, Sabin MA (1977) Piecewise quadratic approximation on triangles. ACM Trans Math Softw 3: 316–325
Romano JP (1988) A bootsprap revival of some nonparametric distance tests. J Am Stat Assoc 83: 698–708
Sorokina T, Worsey AJ (2008) A multivariate Powell–Sabin interpolant. Adv Comput Math 29: 71–89
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Alba Fernández, V., Barrera Rosillo, D., Ibáñez Pérez, M.J. et al. A homogeneity test for bivariate random variables. Comput Stat 24, 513–531 (2009). https://doi.org/10.1007/s00180-008-0144-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-008-0144-6