Abstract
In designs of experiments and reliability analyze, order statistics (OS) are used for various purposes including model checking, estimations of parameters and prediction. Most of these procedures are defined on the basis of expectations of OS problems. In this paper, explicit expressions for central moments of OS coming from the skew-normal (SN) distribution are derived. The SN model enjoys interesting properties from the normal distribution while captures asymmetric behavior in the parent population. Another important topic which is related to OS is record statistics. These data are arising in some practical situations including shock models, sports and epoch times of a non-homogeneous Poisson processes. Here, we derive moments of the upper and the lower record values arising from the skew normal distribution. The obtained results may be used for prediction purposes such as predictive maintenance in a repairable system and prediction of performance of a transmission oil pipeline. Some real data sets are analyzed using the results obtained for illustration purposes.
Similar content being viewed by others
References
Aitchison J, Dunsmore IR (1975) Statistical prediction analysis. Cambridge University Press, Cambridge
Arellano-Valle RB, Azzalini A (2006) On the unification of families of skew-normal distributions. Scand J Stat 33:561–574
Arnold BC, Balakrishnan N, Nagaraja HN (1992) A first course in order statistics. Wiley, New York
Arnold BC, Balakrishnan N, Nagaraja HN (1998) Records. Wiley, New York
Arnold BC, Balakrishnan N, Nagaraja HN (2008) A first course in order statistics. Unabridged republication of the 1992 original. Classics in Applied Mathematics, No. 54. Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PA
Azzalini A (1985) A class of distributions which includes the normal ones. Scand J Stat 12:171–178
Azzalini A, Bacchieri A (2010) A prospective combination of phase II and phase III in drug development. METRON Int J Stat LXVIII(3):347–369
Azzalini A (2013) R package ‘sn’: The skew-normal and skew-\(t\) distributions (version 0.4-18). http://azzalini.stat.unipd.it/SN
Balakrishnan N, Chan PS (1995) On the normal record values and associated inference. Technical Report, McMaster University, Hamilton, Ontario, Canada
Balakrishnan N, Chan PS (1998) On the normal record values and associated inference. Stat Probab Lett 39:73–80
Bose RC, Gupta SS (1959) Moments of order statistics from a normal population. Biometrika 46:433–440
Burnham KP, Anderson DR (2002) Model selection and multimodel inference, a practical information-theoretic approach, 2nd edn. Springer, New York
Capitanio A, Azzalini A, Stanghellini E (2003) Graphical models for skew-normal variates. Scand J Stat 30:129–144
Castillo E, Hadi AS, Balakrishnan N, Sarabia JM (2005) Extreme value and related models with applications in engineering and science. Wiley, Hoboken, NJ
Chiogna M (1998) Some results on the scalar skew-normal distribution. J Ital Stat Soc 1:1–13
Cook RD, Weisberg S (1994) An introduction to regression graphics. Wiley, New York
David HA, Nagaraja HN (2003) Order statistics, 3rd edn. Wiley, Hoboken, NJ
Doostparast M, Balakrishnan N (2011) Optimal statistical procedures on the basis of records in a two-parameter exponential distribution. J Stat Comput Simul 81(12):2003–2019
Genz A (Fortran code), Azzalini A (R code) (2012) mnormt: the multivariate normal and \(t\) distributions. R package version 1.4-5. http://CRAN.R-project.org/package=mnormt
Harter HL (1961) Expected values of normal order statistics. Biometrika 48:151–165 (Correction 48, 476)
Harter HL (1970) Order statistics and their use in testing and estimation, vol 1 and 2. U.S. Government Printing Office, Washington, DC
Jamalizadeh A, Balakrishnan N (2008) On order statistics from bivariate skew-normal and skew-\(\text{ t }_{\nu }\) distributions. J Stat Plan Inference 138:4187–4197
Jamalizadeh A, Balakrishnan N (2009) Order statistics from trivariate normal and \(t_{\nu }\)-distributions in terms of generalized skew-normal and skew-\(t_{\nu }\) distributions. J Stat Plan Inference 139:3799–3819
Kotz S, Balakrishnan N, Johnson N (2000) Continuous multivariate distributions. Wiley, New York
Nadarajah S (2008) Explicit expressions for moments of order statistics. Stat Probab Lett 78:196–205
R Development Core Team (2012) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. http://www.R-project.org/. ISBN 3-900051-07-0
Salehi M, Ahmadi J (2014) Record ranked set sampling scheme. METRON Int J Stat 72(3):351–365
Salehi M, Ahmadi J, Balakrishnan N (2015) Prediction of order statistics and record values based on ordered ranked set sampling. J Stat Comput Sim 85(1):77–88
Salehi M, Jamalizadeh A, Doostparast M (2014) A generalized skew two-piece skew-elliptical distribution. Stat Pap 55:409–429
Tietjen GL, Kahaner DK, Beckman RJ (1977) Variances and covariances of the normal order statistics for sample sizes 2 to 50. Sel Tables Math Stat 5:1–73. 7:122–128
Henningsen A, Toomet O (2011) maxLik: a package for maximum likelihood estimation in R. Comput Stat 26(3):443–458
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
Proof of Lemma 3
Assuming \(g(t)=\varPhi _{SN}^{k}(t)\), a simple integration yields [see also Chiogna (1998)]
So, one can use Lemma 2 for computing the expectation \(E\left[ Z_{\lambda }\varPhi _{SN}^k(Z_{\lambda };\lambda )\right] \). Substituting \(\lambda _1=\lambda \) and \(\lambda _2=\rho =0\) into (11) and (12), we have (for \(k\ge 2\))
where \(\alpha =\frac{\lambda }{\sqrt{1+\lambda ^2}}\) and \(Z_0\sim N(0,1)\). The first term in right hand side (RHS) of (44) can be expressed as
where \(Z_{\frac{\lambda }{\sqrt{2}},\frac{\lambda }{\sqrt{2}}}\sim GSN\left( \frac{\lambda }{\sqrt{2}},\frac{\lambda }{\sqrt{2}},0\right) \). Let \(Z_{\lambda }^{(n)}\)’s, \(1\le n \le k-1\) be iid random variables coming from the \(SN(\lambda )\)-distribution. Thus
From (2) and (5) with \(\gamma =\rho =0\), we have
where \(X,Y_1^{\star },Y_2^{\star },X_{n},Y_{n},1\le n \le k-1\), are iid random variables arising from \(N(0,1)\) and
with partitioned covariance matrix \({\varvec{\Delta }}_1\) as
and
From (6), (7) and (46), we conclude that
Similarly, for the second expression in RHS of (44), we have
where
and
Thus
By substituting (45)–(53) into (44) and using Lemma 1, the desired result follows provided that \(k\ge 2\). For \(k=1\), with a similar manner we have
Finally, using Lemma 1 and the fact that \(\varPhi _2\left( \mathbf {0};\left( \begin{array}{ll} 1&{}\quad \rho \\ \rho &{}\quad 1\\ \end{array}\right) \right) =\frac{1}{4}+\frac{1}{2\pi }\sin ^{-1}\rho \) [see for example Kotz et al. (2000)], the proof is completed. \(\square \)
Proof of Proposition 1
Set \(d+i-1=j\), and from the density (13), we have
where
From (1) and a change of variable, the integration \(I(s,j;\lambda )\) in (56) simplifies to
where \(Z^{\star }_{\lambda ,\lambda s}\sim ESN (\lambda ,\lambda s)\). Let \(Z_{\lambda }^{(1)}, {\ldots },Z_{\lambda }^{(j)}\mathop {\sim }\limits ^{iid}SN(\lambda )\) and be independent of the random variable \(Z^{\star }_{\lambda ,\lambda s}\) in (57). Then
and the stochastic representation (2) imply
where
and \(X^{\star },Y^{\star },X_{n},Y_{n},1\le n \le j\), are copies from the standard normal distribution. Finally, by (6) and (7) we get
By applying Lemma 1, the required result follows. \(\square \)
Proof of Eq. (36)
From (30) and (35), the expectation of the \(m\)th lower record from the \(SN(\lambda )\)-distribution is
where \(Z_{\lambda }\sim SN(\lambda )\). So, the proof is completed. \(\square \)
Rights and permissions
About this article
Cite this article
Salehi, M., Doostparast, M. Expressions for moments of order statistics and records from the skew-normal distribution in terms of multivariate normal orthant probabilities. Stat Methods Appl 24, 547–568 (2015). https://doi.org/10.1007/s10260-015-0306-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-015-0306-y