Some reliability properties of order statistics

Let X_i:j denote the i^th order statistic of a random sample of size j from a continuous life distribution. We show that if X_k:n, is IFR, IFRA, NBU, or DMRL, so are X_k+1:n, X_k+1:n?1 and X_k+1:n+1. Further we show that, in the first three cases, X_k+1:n+2 also shares the corresponding property if k ≤ (n+3)/2. We also present dual results for DFR, DFRA and NWU classes.     

Distributions of certain variables in samples from two-parameter exponential distribution

Cumulative distribution function of the variable Y=(U+c)/(Z/2ν)) is given. Here U and Z are independent random variables, U has the exponential distribution (1.1) with θ=0, σ=1, Z has the distribution χ² (2ν) and c is a real quantity. The variable Y with U and Z given by (2.2) and (2.3) is used for inference about the parametric functions ?=θ?kσ of a two-parameter exponential distribution (1.1) with k or ? known. Special cases of ? or k are: the parameter θ, the Pth quantile Xp, the mean θ+σ and the value of the cumulative distribution function or of the reliability function at given point a. Also one-sided tolerance limits for a two-parameter exponential distribution can be derived from the distribution of the variable Y. The results are also applied to the Pareto distribution.     

On a further generalization of the savage test

A statistic based on the frequencies within the k+1 intervals specified by k arbitrary quantiles is proposed for a LMP test against Lehmann alternatives generalizing the Savage test for the two-sample problem. The maximum efficiency relative to the Savage test for optimally chosen k quantiles is also provided for k=l(2)l5. The asymptotic normality of the statistic follows from the asymptotic multinomial distribution of the frequencies in the classes determined by the k quantiles.     

Tests for multiple upper or lower outliers in an exponential sample

SUMMARY T = \[x + ... + x ]/ Sigma x (T*= \[x + ... + x ] Sigma x ) is the max k (n- k+ 1 ) (n) i k ( 1 ) (k) i imum likelihood ratio test statistic for k upper ( lower ) outliers in an exponential sample x , ..., x . The null distributions of T for k= 1,2 were given by Fisher and by Kimber 1 n k and Stevens , while those of T*(k= 1,2) were given by Lewis and Fieller . In this paper , k the simple null distributions of T and T* are found for all possible values of k, and k k percentage points are tabulated for k= 1, 2, ..., 8. In addition , we find a way of determining k, which can reduce the masking or ' swamping ' effects .     

Cross-over Designs in the Presence of Higher Order Carry-overs

In cross-over experiments, where different treatments are applied successively to the same experimental unit over a number of time periods, it is often expected that a treatment has a carry-over effect in one or more periods following its period of application. The effect of interaction between the treatments in the successive periods may also affect the response. However, it seems that all systematic studies of the optimality properties of cross-over designs have been done under models where carry-over effects are assumed to persist for only one subsequent period. This paper proposes a model which allows for the possible presence of carry-over effects up to k subsequent periods, together with all the interactions between treatments applied at k + 1 successive periods. This model allows the practitioner to choose k for any experiment according to the requirements of that particular experiment. Under this model, the cross-over designs are studied and the class of optimal designs is obtained. A method of constructing these optimal designs is also given.     

A note on hazard rates of order statistics

Let F_k:m be the cumulative disribution function of the kth order statistic in a sample of size n from a distribution

F(x) with density function f(x).The primary objective of this paper is to show that F_k+1mis IHR(increasing hazard rate) if F_km(x)is IHH and that F_k-1:n(x)is DHR.(decreasing hazard rate) if F_km(x) is DHR.     

Multivariate tests for non-additivity

A full bivariate generalization of the Anscombe-Tukey one degree of freedom for univariate non-additivity is presented, and is compared to other proposals. Higher dimensional extensions follow directly. In general, k(k+1)/2 degrees of freedom can be allocated to assessing non-additivity in k dimensions. Hence coordinate-wise additivity is necessary but not sufficient for multivariate additivity.     

Estimation of system reliability

In this paper, we estimate the reliability of a system with k components. The system functions when at least s (1≤s≤k) components survive a common random stress. We assume that the strengths of these k components are subjected to a common stress which is independent of the strengths of these k components. If (X ₁,X ₂,…,X _k ) are strengths of k components subjected to a common stress (Y), then the reliability of the system or system reliability is given byR=P[Y<X _(k−s+1)] whereX _(k−s+1) is (k−s+1)-th order statistic of (X ₁,…,X _k ). We estimate R when (X ₁,…,X _k ) follow an absolutely continuous multivariate exponential (ACMVE) distribution of Hanagal (1993) which is the submodel of Block (1975) and Y follows an independent exponential distribution. We also obtain the asymptotic normal (AN) distribution of the proposed estimator.     

Multiple decision rules for comparing several populations with a fixed known standard

Independent observations are available from k univariate distributions indexed by a real parameter θ. It is desired to select that distribution with the largest parameter value unless this value is smaller than some fixed standard θ₀ in which case no distribution is to be selected. Various single-stage procedures for this (k+l)-decision problem are discussed, using indifference zone, decision theoretic, Bayesian, and subset selection approaches.     

Spacing of information in polynomial regression:a simple solution

Consider a k polynomial regression on a single real variable. If n uncorrelated observations are to be taken in a design with support on more than k+1 points, there is an approximate experiment, ν, with support on k+1 points and n observations such that both designs have the same information matrix for the model. A proof of this result is provided. A method to obtain the approximate design ν is given and illustrated by an example. The source of disagreement between Kiefer (1959) and De La Garza (1954) in the solution of this problem is clarified.     

Local asymptotic normality of intermediate and central order statistics

Consider n independent random variables Z_i,…, Z_n on R with common distribution function F, whose upper tail belongs to a parametric family F(t) = F_θ(t),t ≥ x₀, where θ ∈ ? ? R ^d. A necessary and sufficient condition for the family F_θ, θ ∈ ?, is established such that the k-th largest order statistic Z_n?k+1:n alone constitutes the central sequence yielding local asymptotic normality ( LAN ) of the loglikelihood ratio of the vector (Z_n?i+1:n)¹ _i=kof the k largest order statistics. This is achieved for k = k(n)→_n→∞∞ with k/n→_n→∞ 0.

In the case of vectors of central order statistics ( Z_r:n, Z_r+1:n,…, Z_s:n ), with r/n and s/n both converging to q ∈ ( 0,1 ), it turns out that under fairly general conditions any order statistic Z_m:n with r ≤ m ≤s builds the central sequence in a pertaining LAN expansion.These results lead to asymptotically optimal tests and estimators of the underlying parameter, which depend on single order statistics only     

Normal quantile estimation based on minimizing the error in predicted distribution functions

Estimators of the form [Xbar] + kS for estimating the p quantile of a normal distribution are studied when k is chosen to either minimize the mean square error in the predicted distribution function or to make the predicted distribution function unbiased for p. Here, [Xbar] and S are the usual sample mean and standard deviation, respectively, and the predicted distribution function is the true (normal) distribution function evaluated at the estimated quantile.

These k values are presented for various sample sizes and values of p, and application to warranty determination is discussed.     

Some characterizations of geometric tail distributions based on record values

Let R_j be the jth upper record value from an infinite sequence of independent identically distributed positive integer valued random variables. We show that their common distribution must have geometric tail if R_j+k?R_j and R_j are partially independent for some j≥1 and k≥1 or if E(R_j+2?R_j+1| R_j) is a constant. Three versions of partial independence, each of which provides a characterization of the geometric tail are presented.     

ON CHARACTERIZING DISTRIBUTIONS VIA LINEARITY OF REGRESSION FOR ORDER STATISTICS

Let X₁X_n be a random sample from an absolutely continuous distribution with the corresponding order statistics X_1:n≤X_2:n≤X_n:n. A complete solution of the problem, posed in 1967 by T. Ferguson, of determining the distribution by linearity of regression of X_k+2:n with respect to X_k:n is given. The only possible distributions are of the exponential, power and Pareto type. A linear regression relation for exponents of order statistics is also considered.     

Exact and approximate distributions of the chi-square statistic for equiprobability

The distribution of the chi-square goodness-of-fit statistic is studied in the equiprobable case. Tables of exact critical values are given for a = .1, .05, .01, .005; k = 2(1)4, N = 26(1)50; k = 5, N = 26(1)40; k = 6(1)10, N = 26(1)30, where a is the desired significance level, k is the number of cells and N is the sample size. Methods of fitting the true distribution are compared. If k> 3, it is found that a simple additive adjustment to the asymptotic chi-square fit leads to high accuracy even for N between 10 and 20. For k = 2, the Yates corrected chi-square statistic is very accurately fitted by the usual chi-square distribution.     

Selecting the t-best cells in a multinomial distribution

The problem of selecting the t-best cells in a multinomial distribution with t + k cells, k > 1, 2 <= t is considered under the fixed sample-size indifference zone approach. The least favourable configuration is derived for the usual procedure of selection, for large values of N (the sample size). The result settles Conjecture I (for large N) and Conjecture IV of Chen and Hwang (Commun. Statist. - Theory Meth. 13 (10), 1289-1298, 1984) in the affirmative.     

Bayesian approach to the prediction problem in complete and censored samples from the gamma and exponential populations

The situation considered in this paper is that in which a single complete sample and an additional set of k censored samples, each of which is censòred both above as well as below, are vailable from the gamma with known integervalued shape parameter. The purpose hers is to predict an order statistic in the future sample, that is., in the (k+1)-th sample (or at stage k), based on the aarlier samples. For this purpose, a predictive dinfcrTout Ion is obtained for the general case of gammn distribution with knowa shape parameter. Particular cases including exponential are considered. A discussion on the comparison between the variances of the complete sample case and that of the censored case is given, An illustrative example is provided by a simulated life test.     

Reduced Rank Discrimination

In this paper the problem of classifying an individual with p characteristics into one of k multivariate normal distributions with common unknown covariance matrix is considered when the matrix of ( k +1) means has a linear structural relationship, that is, it lies in an r -dimensional plane, where r 相似文献   

A unified approach to binomial-type distributions of order k

In this paper, we consider the distribution of the number of "1"-runs of length k in a sequence of {0,1}-valued random variables of length n by using a new (unified) counting scheme called l-overlapping counting. Here, k and n are positive integers with k ≦ and l is an integer less than k. We obtain the prohabi!ity generating function of the distribution of the number of eoverlapping "in-runs of iength k in the sequence, even when the underiying sequence is a dependent sequence such as a highcr order Markov chaic.     

Extended tables of the distribution of friedman’ s s-statistic in the two-way layout

Friedman’s (1937, 1940) S-statistic is designed to test the hypothesis that there is no treatment effect in a randomized-block design with k treatments and n blocks. In this paper we give tables of the null distribution of S for k = 5, n = 6(1)8, and for k = 6, n = 2(1)6. Computational details are discussed.