The Annals of Applied Probability

Chi-square approximation by Stein’s method with application to Pearson’s statistic

Robert E. Gaunt, Alastair M. Pickett, and Gesine Reinert

Full-text: Access denied (no subscription detected)

We're sorry, but we are unable to provide you with the full text of this article because we are not able to identify you as a subscriber. If you have a personal subscription to this journal, then please login. If you are already logged in, then you may need to update your profile to register your subscription. Read more about accessing full-text


This paper concerns the development of Stein’s method for chi-square approximation and its application to problems in statistics. New bounds for the derivatives of the solution of the gamma Stein equation are obtained. These bounds involve both the shape parameter and the order of the derivative. Subsequently, Stein’s method for chi-square approximation is applied to bound the distributional distance between Pearson’s statistic and its limiting chi-square distribution, measured using smooth test functions. In combination with the use of symmetry arguments, Stein’s method yields explicit bounds on this distributional distance of order $n^{-1}$.

Article information

Ann. Appl. Probab., Volume 27, Number 2 (2017), 720-756.

Received: July 2015
First available in Project Euclid: 26 May 2017

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 60F05: Central limit and other weak theorems 62G10: Hypothesis testing 62G20: Asymptotic properties

Stein’s method chi-square approximation Pearson’s statistic rate of convergence


Gaunt, Robert E.; Pickett, Alastair M.; Reinert, Gesine. Chi-square approximation by Stein’s method with application to Pearson’s statistic. Ann. Appl. Probab. 27 (2017), no. 2, 720--756. doi:10.1214/16-AAP1213.

Export citation


  • [1] Asylbekov, Z. A., Zubov, V. N. and Ul’yanov, V. V. (2011). On the approximation of some statistics of goodness-of-fit tests for the case of discrete three-dimensional data. Sibirsk. Mat. Zh. 52 728–744.
  • [2] Barbour, A. D. (1990). Stein’s method for diffusion approximations. Probab. Theory Related Fields 84 297–322.
  • [3] Bentkus, V. (2003). On the dependence of the Berry-Esseen bound on dimension. J. Statist. Plann. Inference 113 385–402.
  • [4] Chatterjee, S., Fulman, J. and Röllin, A. (2011). Exponential approximation by Stein’s method and spectral graph theory. ALEA Lat. Am. J. Probab. Math. Stat. 8 197–223.
  • [5] Chen, L. H. Y. (1975). Poisson approximation for dependent trials. Ann. Probab. 3 534–545.
  • [6] Chen, L. H. Y., Goldstein, L. and Shao, Q.-M. (2011). Normal Approximation by Stein’s Method. Springer, Heidelberg.
  • [7] Cressie, N. and Read, T. R. C. (1984). Multinomial goodness-of-fit tests. J. Roy. Statist. Soc. Ser. B 46 440–464.
  • [8] Diaconis, P. and Zabell, S. (1991). Closed form summation for classical distributions: Variations on a theme of de Moivre. Statist. Sci. 6 284–302.
  • [9] Dicker, L. H. and Erdogdu, M. A. (2016). Flexible results for quadratic forms with applications to variance components estimation. Ann. Statist. To appear.
  • [10] Döbler, C. (2015). Stein’s method of exchangeable pairs for the beta distribution and generalizations. Electron. J. Probab. 20 34.
  • [11] Döbler, C., Gaunt, R. E. and Vollmer, S. J. (2015). An iterative technique for bounding derivatives of solutions of Stein equations. Available at arXiv:1510:02623.
  • [12] Fan, J., Hung, H.-N. and Wong, W.-H. (2000). Geometric understanding of likelihood ratio statistics. J. Amer. Statist. Assoc. 95 836–841.
  • [13] Gaunt, R. E. (2013). Rates of convergence of variance-gamma approximations via Stein’s method. D.Phil. thesis, Univ. Oxford.
  • [14] Gaunt, R. E. (2014). Variance-gamma approximation via Stein’s method. Electron. J. Probab. 19 33.
  • [15] Goldstein, L. and Rinott, Y. (1996). Multivariate normal approximations by Stein’s method and size bias couplings. J. Appl. Probab. 33 1–17.
  • [16] Götze, F. (1991). On the rate of convergence in the multivariate CLT. Ann. Probab. 19 724–739.
  • [17] Götze, F. and Ulyanov, V. V. Asymptotic distribution of $\chi^{2}$-type statistics. In Research Group Spectral Analysis, Asymptotic Distributions and Stochastic Dynamics. Bielefeld Univ., Preprint 03–033.
  • [18] Greenwood, P. E. and Nikulin, M. S. (1996). A Guide to Chi-Squared Testing. Wiley, New York.
  • [19] Koehler, K. J. and Larntz, K. (1980). An empirical investigation of goodness-of-fit statistics for sparse multinomials. J. Amer. Statist. Assoc. 75 446–344.
  • [20] Loh, W.-L. (1992). Stein’s method and multinomial approximation. Ann. Appl. Probab. 2 536–554.
  • [21] Luk, H. M. (1994). Stein’s method for the Gamma distribution and related statistical applications. Ph.D. thesis, Univ. Southern California, Los Angeles, CA.
  • [22] Mann, B. (1997). Stein’s method for $\chi^{2}$ of a multinomial. Unpublished manuscript.
  • [23] Mann, B. (1997). Convergence rate for $\chi^{2}$ of a multinomial. Unpublished manuscript.
  • [24] Meckes, E. (2009). On Stein’s method for multivariate normal approximation. In High Dimensional Probability V: The Luminy Volume. Inst. Math. Stat. Collect. 5 153–178. IMS, Beachwood, OH.
  • [25] Nourdin, I. and Peccati, G. (2009). Stein’s method on Wiener chaos. Probab. Theory Related Fields 145 75–118.
  • [26] Pearson, K. (1900). On the criterion that a given system of deviations is such that it can be reasonably supposed to have arisen from random sampling. Philos. Mag. 50 157–175.
  • [27] Peköz, E. A. and Röllin, A. (2011). New rates for exponential approximation and the theorems of Rényi and Yaglom. Ann. Probab. 39 587–608.
  • [28] Pickett, A. M. (2004). Rates of convergence of $\chi^{2}$ approximations via Stein’s method. D.Phil. thesis, Univ. Oxford.
  • [29] Pike, J. and Ren, H. (2014). Stein’s method and the Laplace distribution. ALEA Lat. Am. J. Probab. Math. Stat. 11 571–587.
  • [30] Rice, J. A. (1995). Mathematical Statistics and Data Analysis, 2nd ed. Duxbury Press, North Scituate, MA.
  • [31] Roscoe, J. T. and Byars, J. A. (1971). An investigation of the restraints with respect to sample size commonly imposed on the use of the Chi-Square statistic. J. Amer. Statist. Assoc. 66 755–759.
  • [32] Stein, C. (1972). A bound for the error in the normal approximation to the distribution of a sum of dependent random variables. In Proceedings of the Sixth Berkeley Symposium on Mathematical Statistics and Probability, Probability Theory 2 583–602. Univ. California Press, Berkeley, CA.
  • [33] Stein, C. (1986). Approximate Computation of Expectations. IMS, Hayward, CA.
  • [34] Stuart, A. and Ord, J. K. (1987). Kendall’s Advanced Theory of Statistics: Volume I, 5th ed. Charles Griffin. London.
  • [35] Tumanyan, S. H. (1956). Asymptotic distribution of $\chi^{2}$ criterion when the size of observations and the number of groups simultaneously increase. Teor. Veroyatn. Primen. 1 131–145.
  • [36] Ulyanov, V. V. and Zubov, V. N. (2009). Refinement on the convergence of one family of goodness-of-fit statistics to chi-squared distribution. Hiroshima Math. J. 39 133–161.
  • [37] Yarnold, J. K. (1972). Asymptotic approximations for the probability that a sum of lattice random vectors lies in a convex set. Ann. Math. Stat. 43 1566–1580.