Summary
This paper is concerned with non-asymptotic error evaluation for the uniform (or (B) d -type) joint normal approximation fork sample quantiles. The evaluation generalizes Reiss’ single sample quantile case in [6], where the type of approximation is a little weaker than that of the present article.
Some improvements of the previous results [2] are also given for the uniform asymptotic joint normality of increasing number of sample quantiles as the sample size increases.
Similar content being viewed by others
References
David, F. N. and Johnson, N. L. (1954). Statistical treatment of censored data Part I, Fundamental Formulae,Biometrika,41, 228–240.
Ikeda, S. and Matsunawa, T. (1972). On the uniform asymptotic joint normality of sample quantiles,Ann. Inst. Statist. Math.,24, 33–52.
Kraft, O. (1969). A note on exponential bounds for binomial probabilities,Ann. Inst. Statist. Math.,21, 219–220.
Matsunawa, T. (1973). Uniform asymptotic joint normality of sample quantiles in censored cases,Ann. Inst. Statist. Math.,25, 261–278.
Matsunawa, T. (1975). Some inequalities based on inverse factorial series,Research Memorandum No. 82, The Institute of Statistical Mathematics.
Reiss, R. D. (1974). On the accuracy of the normal approximation for quantiles,Ann. Prob.,2, 741–744.
Additional information
The institute of statistical mathematics
About this article
Cite this article
Matsunawa, T. On the error evaluation of the joint normal approximation for sample quantiles. Ann Inst Stat Math 27, 189–199 (1975). https://doi.org/10.1007/BF02504639
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02504639