Abstract
Many test statistics follow a χ2 distribution because a normal model is assumed as underlying distribution. In this paper we obtain good analytic approximations for the p-value and the critical value of χ2 tests when the underlying distribution is close but different from the normal model. With these approximations we study the robustness of validity of χ2 tests
Similar content being viewed by others
References
Altman DG (1991) Practical statistics for medical research. Chapman and Hall, London
Becker RA, Chambers JM, Wilks AR (1988) The new s language. Chapman and Hall, London (Formely Wadsworth and Brooks-Cole)
Benjamini Y (1983) Is the t test really conservative when the parent distribution is long-tailed?. J Am Stat Assoc 78:645–654
Box GEP (1953) Non-normality and tests on variances. Biometrika 40:318–335
Daniels HE (1983) Saddlepoint approximations for estimating equations. Biometrika 70:89–96
Field CA, Ronchetti E (1985) A tail area influence function and its application to testing. Commun Stat 4:19–41
Filippova AA (1961) Mises’ theorem on the asymptotic behaviour of functionals of empirical distribution functions and its statistical applications. Theory Probab Appl 7:24–57
García-Pérez A (1993) On robustness for hypotheses testing. Int Stat Rev 61:369–385
García-Pérez A (1996) Behaviour of sign test and one sample median test against changes in the model. Kybernetika 32:159–173
García-Pérez A (2003) von Mises approximation of the critical value of a test. Test 12:385–411
Hampel F (1974) The influence curve and its role in robust estimation. J Am Stat Assoc 69:383–393
Jensen JL (1995) Saddlepoint approximations. Clarendon Press, Oxford
Loh WY (1984) Bounds on AREs for restricted classes of distributions defined via tail-orderings. Ann Stat 12:685-701
Lugannani R, Rice S (1980) Saddle point approximation for the distribution of the sum of independent random variables. Adv Appl Probab 12:475–490
R Development Core Team (2003) The R Enviroment for statistical computing and graphics
Reeds JA (1976) On the definitions of von Mises functionals. PhD thesis, Harvard University, Cambridge, Massachusetts
Rivest L-P (1986) Bartlett’s, Cochran’s, and Hartley’s tests on variances are liberal when the underlying distribution is long-tailed. J Am Stat Assoc 81:124–128
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
García-Pérez, A. Chi-Square Tests Under Models Close to the Normal Distribution. Metrika 63, 343–354 (2006). https://doi.org/10.1007/s00184-005-0024-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00184-005-0024-9