We investigate normalized extreme order statistics for distributions supported on a finite interval. Under local endpoint assumptions of the form $ f(x)\sim C(b-x)^{r-1}\; \; (x\to b-), $ and its left-endpoint analogue, we prove that the normalized sample maximum and minimum are uniformly integrable in every positive power. As a consequence, weak convergence upgrades to convergence of all positive moments. We then establish the joint weak convergence of the normalized lower and upper extremes, and prove that they are asymptotically independent. This leads to the limit law of their difference and an explicit asymptotic variance formula. These results are applied to the sample midrange in symmetric bounded location families. In particular, when the endpoint exponent satisfies $ 1\le r < 2 $, the sample midrange has asymptotic variance of order $ n^{-2/r} $ and is therefore asymptotically more efficient than the sample mean and interior sample quantiles, whose variances are typically of order $ n^{-1} $. We also obtain the asymptotic law of the sample range as a natural companion result. The main statistical application remains the sample midrange as an estimator of the center parameter. Semicircular and geometric localization examples are discussed, and a simulation study confirms the asymptotic results.
Citation: Hongjun Qiu, Yanhong Zhang. On convergence of some normalized extreme order statistics[J]. AIMS Mathematics, 2026, 11(7): 19808-19823. doi: 10.3934/math.2026804
We investigate normalized extreme order statistics for distributions supported on a finite interval. Under local endpoint assumptions of the form $ f(x)\sim C(b-x)^{r-1}\; \; (x\to b-), $ and its left-endpoint analogue, we prove that the normalized sample maximum and minimum are uniformly integrable in every positive power. As a consequence, weak convergence upgrades to convergence of all positive moments. We then establish the joint weak convergence of the normalized lower and upper extremes, and prove that they are asymptotically independent. This leads to the limit law of their difference and an explicit asymptotic variance formula. These results are applied to the sample midrange in symmetric bounded location families. In particular, when the endpoint exponent satisfies $ 1\le r < 2 $, the sample midrange has asymptotic variance of order $ n^{-2/r} $ and is therefore asymptotically more efficient than the sample mean and interior sample quantiles, whose variances are typically of order $ n^{-1} $. We also obtain the asymptotic law of the sample range as a natural companion result. The main statistical application remains the sample midrange as an estimator of the center parameter. Semicircular and geometric localization examples are discussed, and a simulation study confirms the asymptotic results.
| [1] |
I. S. Akhundov, N. Balakrishnan, V. B. Nevzorov, New characterizations by properties of midrange and related statistics, Comm. Statist. Theory Methods, 33 (2004), 3133–3143. https://doi.org/10.1081/STA-200039063 doi: 10.1081/STA-200039063
|
| [2] | B. C. Arnold, N. Balakrishnan, H. N. Nagaraja, A first course in order statistics, SIAM, 2008. https://doi.org/10.1137/1.9780898719062 |
| [3] |
H. M. Barakat, E. M. Nigm, Weak limits of random quasi-ranges and random quasi-half-ranges, Microelectron. Reliab., 31 (1991), 941–953. https://doi.org/10.1016/0026-2714(91)90039-A doi: 10.1016/0026-2714(91)90039-A
|
| [4] |
H. M. Barakat, E. M. Nigm, A. M. Elsawah, Asymptotic distributions of the generalized range, midrange, extremal quotient and extremal product, with a comparison study, Comm. Statist. Theory Methods, 44 (2015), 900–913. https://doi.org/10.1080/03610926.2012.750356 doi: 10.1080/03610926.2012.750356
|
| [5] |
J. D. Broffitt, An example of the large sample behavior of the midrange, Amer. Statist., 28 (1974), 69–70. https://doi.org/10.1080/00031305.1974.10479075 doi: 10.1080/00031305.1974.10479075
|
| [6] | A. DasGupta, Asymptotic theory of statistics and probability, New York: Springer, 2008. https://doi.org/10.1007/978-0-387-75971-5 |
| [7] | L. Haan, A. Ferreira, Extreme value theory: An introduction, New York: Springer, 2006. https://doi.org/10.1007/0-387-34471-3 |
| [8] | M. R. Leadbetter, G. Lindgren, H. Rootzén, Extremes and related properties of random sequences and processes, New York: Springer, 1983. https://doi.org/10.1007/978-1-4612-5449-2 |
| [9] | E. L. Lehmann, G. Casella, Theory of point estimation, 2 Eds., New York: Springer, 1998. https://doi.org/10.1007/b98854 |
| [10] | S. I. Resnick, Extreme values, regular variation, and point processes, New York: Springer, 1987. https://doi.org/10.1007/978-0-387-75953-1 |
| [11] |
P. R. Rider, The midrange of a sample as an estimator of the population midrange, J. Amer. Statist. Assoc., 52 (1957), 537–542. https://doi.org/10.2307/2281703 doi: 10.2307/2281703
|
| [12] | J. Shao, Mathematical statistics, 2 Eds., New York: Springer, 2003. https://doi.org/10.1007/b97553 |
| [13] |
G. J. Székely, T. F. Mori, An extremal property of rectangular distributions, Statist. Probab. Lett., 3 (1985), 107–109. https://doi.org/10.1016/0167-7152(85)90035-5 doi: 10.1016/0167-7152(85)90035-5
|
| [14] |
J. Wang, C. Deng, J. Li, M. Zhou, On variances and covariances of a kind of extreme order statistics, Commun. Statist. Theory Methods, 45 (2016), 3274–3282. https://doi.org/10.1080/03610926.2014.901373 doi: 10.1080/03610926.2014.901373
|
Figures(2) / Tables(3)
Hongjun Qiu, Yanhong Zhang. On convergence of some normalized extreme order statistics[J]. AIMS Mathematics, 2026, 11(7): 19808-19823. doi: 10.3934/math.2026804
DownLoad: