In the present paper we obtain approximations to the distribution of a sum of squared normalized variables with small number of summands, and provide an estimate of approximation accuracy. We compare confidence intervals for the unknown parameter σ constructed with the use of the obtained approximations when α 1 is known, with the intervals constructed with the use of the classical chi-square distribution under the assumption of normality of normalized sums.
Similar content being viewed by others
References
O. Barndorff-Nielsen and D. Cox, Asymptotic Techniques for Use in Statistics, Chapman and Hall, London (1989).
L. N. Bolshev and N. V. Smirnov, Tables of Mathematical Statistics, Nauka, Moscow (1965).
V.Yu. Korolev, “On distributions in which symmetrization is a scale mixture of normal laws,” Stat. Methods of Estimating and Hypothesis Testing, 136–143 (2000).
V. V. Petrov, Sums of Independent Random Variables, Nauka, Moscow (1972).
Yu.V. Prokhorov, “Local theorem for densities,” Proc. USSR Acad. Sci., 83, No. 6, 797–800 (1952).
P.N. Sapozhnikov, “Estimation of Parameters of a Compound–Poisson Process,” Stat. Methods of Estimating and Hypothesis Testing, 46–52 (2000).
G. I. Devyatkova, M.V. Radionova, and A.V. Popov, “The system of estimating optimal boundaries for some biological parameters of examination of calculous cholecystitis pqatients,” Perm’s Med. J., 47–53 (2005).
Guidelines for Designing Reference Values for Laboratory Parameters, Ministry of Health, Moscow (1983).
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Statisticheskie Metody Otsenivaniya i Proverki Gipotez, Vol. 19, pp. 135–148, 2006
Rights and permissions
About this article
Cite this article
Radionova, M.V., Sapozhnikov, P.N. An Analog of the Chi-Square Distribution for Normalized Sums with Small Number of Summands. J Math Sci 220, 724–733 (2017). https://doi.org/10.1007/s10958-016-3216-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10958-016-3216-0