Robust symmetric distribution location estimation and regression

A procedure for estimating the location parameter of an unknown symmetric distribution is developed for application to samples from very light-tailed through very heavy-tailed distributions. This procedure has an easy extension to a technique for estimating the coefficients in a linear regression model whose error distribution is symmetric with arbitrary tail weights. The regression procedure is, in turn, extended to make it applicable to situations where the error distribution is either symmetric or skewed. The potentials of the procedures for robust location parameter and regression coefficient estimation are demonstrated by simulation studies.     

Optimal spacing of the selected sample quantiles for the joint estimation of the location and scale parameters of a symmetric distribution

We are considering the ABLUE’s – asymptotic best linear unbiased estimators – of the location parameter μ and the scale parameter σ of the population jointly based on a set of selected k sample quantiles, when the population distribution has the density of the form

where the standardized function f(u) being of a known functional form.A set of selected sample quantiles with a designated spacing

or in terms of u=(x−μ)/σ

where

λ_i=∫_−∞^u_if(t) dt, i=1,2,…,k

are given by

x(n₁)<x(n₂)<<x(n_k),

where

Asymptotic distribution of the k sample quantiles when n is very large is given by

h(x(n₁),x(n₂),…,x(n_k);μ,σ)=(2πσ²)^−k/2[λ₁(λ₂−λ₁)(λ_k−λ_k−1)(1−λ_k)]^−1/2n^k/2 exp(−nS/2σ²),

where

f_i=f(u_i), i=0,1,…,k,k+1,

f₀=f_k+1=0, λ₀=0, λ_k+1=1.

The relative efficiency of the joint estimation is given by

where

and κ being independent of the spacing . The optimal spacing is the spacing which maximizes the relative efficiency η(μ,σ).We will prove the following rather remarkable theorem. Theorem. The optimal spacing for the joint estimation is symmetric, i.e.

λ_i+λ_k−i+1=1,

or

u_i+u_k−i+1=0, i=1,2,…,k,

if the standardized density f(u) of the population is differentiable infinitely many times and symmetric

f(−u)=f(u), f′(−u)=−f′(u).

     

Adaptive m estimation of symmetric distribution location

An adaptive M esitmation procedure for using a random sample to estimate the location parameter of an unknown symmetric distribution is developed. The procedure may be applied to samples from distributions with tail lenghts at least as heavy as normal distribution tails. Simulation studies demonstrate the potential of the new estimator for producing good location estimates.     

Estimation of location and scale parameters of a distribution by U-statistics based on best linear functions of order statistics

In this work we propose a technique of estimating the location parameter μ$\mu$ and scale parameter σ$\sigma$ of a distribution by U-statistics constructed by taking best linear functions of order statistics as kernels. The method has been illustrated for estimating the location and scale parameters of type-I extreme value distribution. We have computed the asymptotic relative efficiencies of the proposed U-statistics with the appropriate maximum likelihood estimators based on samples drawn from each of type-I extreme value, logistic and normal distributions. In all cases very high asymptotic relative efficiencies are obtained.     

Estimation of a scale parameter in mixture models with unknown location

Estimation of the scale parameter in mixture models with unknown location is considered under Stein's loss. Under certain conditions, the inadmissibility of the “usual” estimator is established by exhibiting better estimators. In addition, robust improvements are found for a specified submodel of the original model. The results are applied to mixtures of normal distributions and mixtures of exponential distributions. Improved estimators of the variance of a normal distribution are shown to be robust under any scale mixture of normals having variance greater than the variance of that normal distribution. In particular, Stein's (Ann. Inst. Statist. Math. 16 (1964) 155) and Brewster's and Zidek's (Ann. Statist. 2 (1974) 21) estimators obtained under the normal model are robust under the t model, for arbitrary degrees of freedom, and under the double-exponential model. Improved estimators for the variance of a t distribution with unknown and arbitrary degrees of freedom are also given. In addition, improved estimators for the scale parameter of the multivariate Lomax distribution (which arises as a certain mixture of exponential distributions) are derived and the robustness of Zidek's (Ann. Statist. 1 (1973) 264) and Brewster's (Ann. Statist. 2 (1974) 553) estimators of the scale parameter of an exponential distribution is established under a class of modified Lomax distributions.     

Estimation of the mean of a spherically symmetric distribution with constraints on the norm

The authors consider the problem of estimating, under quadratic loss, the mean of a spherically symmetric distribution when its norm is supposed to be known and when a residual vector is available. They give a necessary and sufficient condition for the optimal James‐Stein estimator to dominate the usual estimator. Various examples are given that are not necessarily variance mixtures of normal distributions. Consideration is also given to an alternative class of robust James‐Stein type estimators that take into account the residual vector. A more general domination condition is given for this class.     

Estimation of location extremes within general families of scale mixtures

In this paper, we study the estimation of the minimum and maximum location parameters, respectively, representing the minimum guaranteed lifetime of series and parallel systems of components, within a general class of scale mixtures. The conditional or underlying distribution has only the primary restriction of being a location-scale family with positive support. The mixing distribution is also quite general in that we only assume that it has positive support and finite second moment. For demonstrative purposes several special cases are highlighted such as the gamma, inverse-Gaussian, and discrete mixture. Various estimators, including bootstrap bias corrected estimators, are compared with respect to both mean-squared-error and Pitman's measure of closeness.     

Estimation of a symmetric density

Kraft, Lepage, and van Eeden (1985) have suggested using a symmetrized version of the kernel estimator when the true density f of the observation is known to be symmetric around a possibly unknown point θ. The effect of this symmetrization device depends on the smoothness of f * f(x) = f f(x+t)f(t) dt at zero. We show that if θ has to be estimated and if f is not absolutely continuous, symmetrization may deteriorate the estimate.     

Linear estimation of location and scale parameters in the generalized gamma distribution

The expressions for moments of order statistics from the generalized gamma distribution are derived. Coefficients to get the BLUEs of location and scale parameters in the generalized gamma distribution are computed. Some simple alternative linear unbiased estimates of location and scale parameters are also proposed and their relative efficiencies compared to the BLUEs are studied.     

Variable selection in joint location and scale models of the skew-normal distribution

A regression model with skew-normal errors provides a useful extension for ordinary normal regression models when the data set under consideration involves asymmetric outcomes. Variable selection is an important issue in all regression analyses, and in this paper, we investigate the simultaneously variable selection in joint location and scale models of the skew-normal distribution. We propose a unified penalized likelihood method which can simultaneously select significant variables in the location and scale models. Furthermore, the proposed variable selection method can simultaneously perform parameter estimation and variable selection in the location and scale models. With appropriate selection of the tuning parameters, we establish the consistency and the oracle property of the regularized estimators. Simulation studies and a real example are used to illustrate the proposed methodologies.     

Approximate MLEs for the location and scale parameters of the skew logistic distribution

Azzalini (Scand J Stat 12:171–178, 1985) provided a methodology to introduce skewness in a normal distribution. Using the same method of Azzalini (1985), the skew logistic distribution can be easily obtained by introducing skewness to the logistic distribution. For the skew logistic distribution, the likelihood equations do not provide explicit solutions for the location and scale parameters. We present a simple method of deriving explicit estimators by approximating the likelihood equations appropriately. We examine numerically the bias and variance of these estimators and show that these estimators are as efficient as the maximum likelihood estimators (MLEs). The coverage probabilities of the pivotal quantities (for location and scale parameters) based on asymptotic normality are shown to be unsatisfactory, especially when the effective sample size is small. To improve the coverage probabilities and for constructing confidence intervals, we suggest the use of simulated percentage points. Finally, we present a numerical example to illustrate the methods of inference developed here.     

Maximum likelihood estimators of the location and scale parameters of the exponential distribution from a censored sample

In this note explicit expressions are given for the maximum likelihood estimators of the parameters of the two-parameter exponential distribution, when a doubly censored sample is available.     

Best linear unbiased estimation of location and scale parameters of the log-logistic distribution

If an assumption, such as homoscedasticity, or some other aspect of an inference problem, such as the number of cases, is altered, our conclusions may change and different parts of the conclusions can be affected in different ways. Most diagnostic procedures measure the influence on one particular aspect of the conclusion - such as model fit or change in parameter estimates. The effect on all aspects of the conclusions can be described by the difference in two log likelihood functions and when the log likelihood functions come from an exponential family or are quasi-likelihoods, this difference can be factored into three terms: one depending only on the alteration, another depending only on the aspects of the conclusions to be considered, and a third term depending on both. The third term is interesting because it shows which aspects of the conclusions are relatively insensitive even to large alterations.     

Estimation of eigenvalues of the scale matrix of the multivariate f distribution

Let F have the multivariate F distribution with a scale matrix Δ. In this paper, the problem of estimating the eigenvalues of the scale matrix Δ is considered. New class of estimators are obtained which dominate the best linear estimator of the form cF. Simulation study is also carried out to compare the performance of these estimators.     

Estimation of the scale parameter of the Rayleigh distribution under general progressive censoring

Based on a general progressively type II censored sample, the maximum likelihood estimator (MLE), Bayes estimator under squared error loss and credible intervals for the scale parameter and the reliability function of the Rayleigh distribution are derived. Also, the Bayes predictive estimator and highest posterior density (HPD) prediction interval for future observation are considered. Comparisons among estimators are investigated through Monte Carlo simulations. An illustrative example with real data concerning 23 ball bearings in a life test is presented.     

Estimation of the shape and scale parameters of Pareto distribution using ranked set sampling

In the current paper, the estimation of the shape and location parameters α and c, respectively, of the Pareto distribution will be considered in cases when c is known and when both are unknown. Simple random sampling (SRS) and ranked set sampling (RSS) will be used, and several traditional and ad hoc estimators will be considered. In addition, the estimators of α, when c is known using an RSS version based on the order statistic that maximizes the Fisher information for a fixed set size, will be considered. These estimators will be compared in terms of their biases and mean square errors. The estimators based on RSS can be real competitors against those based on SRS.