A note on finite-sample efficiencies of estimators for the minimum volume ellipsoid

Among the most well known estimators of multivariate location and scatter is the Minimum Volume Ellipsoid (MVE). Many algorithms have been proposed to compute it. Most of these attempt merely to approximate as close as possible the exact MVE, but some of them led to the definition of new estimators which maintain the properties of robustness and affine equivariance that make the MVE so attractive. Rousseeuw and van Zomeren (1990) used the <$>(p+1)<$>- subset estimator which was modified by Croux and Haesbroeck (1997) to give rise to the averaged <$>(p+1)<$>- subset estimator . This note shows by means of simulations that the averaged <$>(p+1)<$>-subset estimator outperforms the exact estimator as far as finite-sample efficiency is concerned. We also present a new robust estimator for the MVE, closely related to the averaged <$>(p+1)<$>-subset estimator, but yielding a natural ranking of the data.     

Markov Chain Markov Field dynamics: Models and statistics

This study deals with time dynamics of Markov fields defined on a finite set of sites with state space <$>E<$>, focussing on Markov Chain Markov Field (MCMF) evolution. Such a model is characterized by two families of potentials: the instantaneous interaction potentials, and the time delay potentials. Four models are specified: auto-exponential dynamics (<$>E = {\of R}^+<$>), auto-normal dynamics (<$>E = {\of R}<$>), auto-Poissonian dynamics (<$>E = {\of N}<$>) and auto-logistic dynamics ( E qualitative and finite). Sufficient conditions ensuring ergodicity and strong law of large numbers are given by using a Lyapunov criterion of stability, and the conditional pseudo-likelihood statistics are summarized. We discuss the identification procedure of the two Markovian graphs and look for validation tests using martingale central limit theorems. An application to meteorological data illustrates such a modelling.     

Improved approaches to interval estimation of effective doses for a logistic dose-response curve

Asymptotic confidence (delta) intervals and intervals based upon the use of Fieller's theorem are alternative methods for constructing intervals for the <$>\gamma<$>% effective doses (ED<$>_\gamma<$>). Sitter and Wu (1993) provided a comparison of the two approaches for the ED<$>_{50}<$>, for the case in which a logistic dose response curve is assumed. They showed that the Fieller intervals are generally superior. In this paper, we introduce two new families of intervals, both of which include the delta and Fieller intervals as special cases. In addition we consider interval estimation of the ED<$>_{90}<$> as well as the ED<$>_{50}<$>. We provide a comparison of the various methods for the problem of constructing a confidence interval for the ED<$>_\gamma<$>.     

Formulating robust regression estimation as an optimum allocation problem

The Mallows-type estimator, one of the most reasonable bounded influence estimators, often downweights leverage points regardless of the magnitude of the corresponding residual, and this could imply a loss of efficiency. In this article, we consider whether the efficiency of this bounded influence estimator could be improved by regarding both the robust x -distance and the residual size. We develop a new robust procedure based on the ideas of the Mallows-type estimator and the general robust recipe, where data been cleaned by pulling outliers towards their fitted values. Our basic idea is to formulate the robust estimation as an allocation problem, where the objective function is a Huber-type "loss" function, but the pulling resource is restricted. Using a mathematical programming technique, the pulling resource is optimally allocated to influential points <$>({x}_i, y_i)<$> with respect to residual size and given weights, <$>w({x}_i)<$>. Three previously published approaches are compared to our proposal via simulated experiments. In the case of contaminated data by regression outliers and "good" leverage points, the proposed robust estimator is a reasonable bounded influence estimator concerning both efficiency and norm of bias. In addition, the proposed approach offers the potential to establish constraints for the regression parameters and also may potentially provide insight regarding outlier detection.     

Estimating with percentile grouped and truncated date from a scale parameter distribution

Data which is grouped and truncated is considered. We are given numbers n₁<…<n_k=n and we observe X_ni ),i=1,…k, and the tottal number of observations available (N> n_k is unknown. If the underlying distribution has one unknown parameter θ which enters as a scale parameter, we examine the form of the equations for both conditional, unconditional and modified maximum likelihood estimators of θ and N and examine when these estimators will be finite, and unique. We also develop expressions for asymptotic bias and search for modified estimators which minimize the maximum asymptotic bias. These results are specialized tG the zxponential distribution. Methods of computing the solutions to the likelihood equatims are also discussed.     

Minimax estimation of a lower-bounded scale parameter of a gamma distribution for scale-invariant squared-error loss

Let X have a gamma distribution with known shape parameter θr;aL and unknown scale parameter θ. Suppose it is known that θ ≥ a for some known a > 0. An admissible minimax estimator for scale-invariant squared-error loss is presented. This estimator is the pointwise limit of a sequence of Bayes estimators. Further, the class of truncated linear estimators C = {θ_ρ|θ_ρ(x) = max(a, ρ), ρ > 0} is studied. It is shown that each θ_ρ is inadmissible and that exactly one of them is minimax. Finally, it is shown that Katz's [Ann. Math. Statist., 32, 136–142 (1961)] estimator of θ is not minimax for our loss function. Some further properties of and comparisons among these estimators are also presented.     

Simultaneous robust estimation of location and scale parameters: A minimum-distance approach

Simultaneous robust estimates of location and scale parameters are derived from minimizing a minimum-distance criterion function. The criterion function measures the squared distance between the pth power (p > 0) of the empirical distribution function and the pth power of the imperfectly determined model distribution function over the real line. We show that the estimator is uniquely defined, is asymptotically bivariate normal and for p > 0.3 has positive breakdown. If the scale parameter is known, when p = 0.9 the asymptotic variance (1.0436) of the location estimator for the normal model is smaller than the asymptotic variance of the Hodges-Lehmann (HL)estimator (1.0472). Efficiencies with respect to HL and maximum-likelihood estimators (MLE) are 1.0034 and 0.9582, respectively. Similarly, if the location parameter is known, when p = 0.97 the asymptotic variance (0.6158) of the scale estimator is minimum. The efficiency with respect to the MLE is 0.8119. We show that the estimator can tolerate more corrupted observations at oo than at – for p < 1, and vice versa for p > 1.     

Parameter Estimation in Conditional Heteroscedastic Models

Abstract

We study asymptotics of parameter estimates in conditional heteroscedastic models. The estimators considered are those obtained by minimizing certain functionals and those obtained by solving estimation equations. We establish consistency and derive asymptotic limit laws of the estimators. Condition under which the limit law is normal is studied. Further, bootstrap for these estimators is discussed. The limiting distribution of the estimators is not necessary always normal, and we present a real data example to illustrate this.     

Problems with Maximum Likelihood Estimation and the 3 Parameter Gamma Distribution

The three parameters involved are scale a , shape 𝜌 , and location s . Maximum likelihood estimators are (\hata, \hat\rho, \hats) . Using recent work on the second order variances, skewness, and kurtosis we establish the facts, that if the location parameter s is to be estimated, then the asymptotic variances only exist if 𝜌 >2, asymptotic skewness only exists if 𝜌 >3, and 2nd order variances and third order fourth central moments only exist if 𝜌 >4. The result of these limitations is that in general very large sample sizes may be needed to avoid inference problems. We also include new continued fractions for the asymptotic covariances of the maximum likelihood estimators considered.     

On the efficiencies of some common quick estimators

The quick estimators of location and scale have broad applications and are widely used. For a variety of symmetric populations we obtain the quantiles and the weights for which the asymptotic variances of the quick estimators are minimum. These optimal quick estimators are then used to obtain the asymptotic relative efficiencies of the commonly used estimators such as trimean. gastwirth. median, midrange. and interquartile range with respect to the optimal quick estimators in order to determine a choice among them and to check whether they are unacceptably poor. In the process it is seen that the interquartile range is the optimal quick estimator of scale for Cauchy populations; but the interdecile range is in general preferable. Also the optimal estimator of the location for the logistic distribution puts weights 0.3 on each of the two quartiles and 0.4 on the median. It is shown that for the symmetric distributions, such as the beta and Tukey- lambda with [d] > 0, which have finite support and short tails, i.e. the tail exponents (Parzen, 1979) satisfy [d] < 1, the midrange and the range are the optimal quick estimators of location and scale respectively if [d] < 1/2. The class of such distributions Include the distributions with high discontinuous tails, e.g. Tukey-lambda with [d] > 1, as well as some distributions with p.d.f.'s going to zero at the ends of the finite support, such as Tukey-lambda with 1/2 < [d] < 1. As a byproduct an interesting tail correspondence between beta and Tukey-lambda distributions is seen.     

CONCOMITANT SCALE ESTIMATION IN REGRESSION PROBLEMS WITH INCREASING DIMENSION

We obtain Bahadur representations for the semi-interquartile range and the median deviation when these estimators are based on the residuals from a linear regression model with increasing dimension. These representations yield a variety of central limit theorems and conditions under which the two estimators are equivalent. In particular, the representations justify the use of the estimators as concomitant scale estimators in general scale equivariant M-estimation of a regression parameter when the dimension of the parameter increases with the sample size.     

An alternative to unit root tests: Bridge estimators differentiate between nonstationary versus stationary models and select optimal lag

This paper introduces a novel way of differentiating a unit root from stationary alternatives using so-called “Bridge” estimators; this estimation procedure can potentially generate exact zero estimates of parameters. We exploit this property and treat this as a model selection problem. We show that Bridge estimators can select the correct model with probability tending to 1. They estimate “zero” parameter on the lagged dependent variable as zero (nonstationarity), if this is nonzero (stationary), estimate the coefficient with standard normal limit. In this sense, we extend the statistics literature as well, since that literature only deals with model selection among only stationary variables.     

Bayesian analysis of head and neck cancer data using generalized inverse Lindley stress–strength reliability model

In this article, we present the analysis of head and neck cancer data using generalized inverse Lindley stress–strength reliability model. We propose Bayes estimators for estimating P(X > Y), when X and Y represent survival times of two groups of cancer patients observed under different therapies. The X and Y are assumed to be independent generalized inverse Lindley random variables with common shape parameter. Bayes estimators are obtained under the considerations of symmetric and asymmetric loss functions assuming independent gamma priors. Since posterior becomes complex and does not possess closed form expressions for Bayes estimators, Lindley’s approximation and Markov Chain Monte Carlo techniques are utilized for Bayesian computation. An extensive simulation experiment is carried out to compare the performances of Bayes estimators with the maximum likelihood estimators on the basis of simulated risks. Asymptotic, bootstrap, and Bayesian credible intervals are also computed for the P(X > Y).     

Improved shrinkage estimators for the mean vector of a scale mixture of normals with unknown variance

The problem of estimating the mean θ of a not necessarily normal p-variate (p > 3) distribution with unknown covariance matrix of the form σ²A (A a known diagonal matrix) on the basis of n_i > 2 observations on each coordinate X_t (1 < i < p) is considered. It is argued that the class of scale (or variance) mixtures of normal distributions is a reasonable class to study. Assuming the loss function is quadratic, a large class of improved shrinkage estimators is developed in the case of a balanced design. We generalize results of Berger and Strawderman for one observation in the known-variance case. This methodology also permits the development of a new class of minimax shrinkage estimators of the mean of a p-variate normal distribution for an unbalanced design. Numerical calculations show that the improvements in risk can be substantial.     

On cusp location estimation for perturbed dynamical systems

We consider the problem of parameter estimation in the case of observation of the trajectory of the diffusion process. We suppose that the drift coefficient has a singularity of cusp type and that the unknown parameter corresponds to the position of the point of the cusp. The asymptotic properties of the maximum likelihood estimator and Bayesian estimators are described in the asymptotic of small noise, that is, as the diffusion coefficient tends to zero. The consistency, limit distributions, and the convergence of moments of these estimators are established.     

Universal domination of stein-type estimators

For the problem of estimating the location parameter of a p-variate spherically symmetric distribution (p>3), Hwang (1985) established the dominance of some positive-part James-Stein (1961) estimators over the usual estimator simultaneously under a very general class of loss function. Vie show that many of his results can be extended to a class of positive-part Baranchik-type estimators (1970).     

Maximum log-likelihood ratio test for a change in three parameter Weibull distribution

Asymptotic behavior of a log-likelihood ratio statistic for testing a change in a three parameter Weibull distribution is studied. It is shown that if a shape parameter α>2$\alpha >2$ the law of iterated logarithm for maximum-likelihood estimators is still valid and the log-likelihood testing statistic is asymptotically distributed (after an appropriate normalization) according to a Gumbel distribution.     

UMVU estimation of the reliability function of the generalized life distributions

The problems of estimating the reliability function and P=P_rX > Y are considered for the generalized life distributions. Uniformly minimum variance unbiased estimators (UMVUES) of the powers of the parameter involved in the probabilistic model and the probability density function (pdf) at a specified point are derived. The UMVUE of the pdf is utilized to obtain the UMVUE of the reliability function and ‘P’. Our method of obtaining these estimators is quite simple than the traditional approaches. A theoretical method of studying the behaviour of the hazard-rate is provided.     

A concentration approach to sensitivity studies in statistical estimation problems

It is shown that the concept of concentration is of potential interest in the sensitivity study of some parameters and related estimators. Basic ideas are introduced for a real parameter θ>0 together with graphical representations using Lorenz curves of concentration. Examples based on the mean, standard deviation and variance are provided for some classical distributions. This concentration approach is also discussed in relation with influence functions. Special emphasis is given to the average concentration of an estimator which provides a sensitivity measure allowing one to compare several estimators of the same parameter. Properties of this measure are investigated through simulation studies and its practical interest is illustrated by examples based on the trimmed mean and the Winsorized variance.     

A computational study of a quasi-PORT methodology for VaR based on second-order reduced-bias estimation

In this paper, we deal with the estimation, under a semi-parametric framework, of the Value-at-Risk (VaR) at a level p, the size of the loss occurred with a small probability p. Under such a context, the classical VaR estimators are the Weissman–Hill estimators, based on any intermediate number k of top-order statistics. But these VaR estimators do not enjoy the adequate linear property of quantiles, contrarily to the PORT VaR estimators, which depend on an extra tuning parameter q, with 0≤q<1. We shall here consider ‘quasi-PORT’ reduced-bias VaR estimators, for which such a linear property is obtained approximately. They are based on a partially shifted version of a minimum-variance reduced-bias (MVRB) estimator of the extreme value index (EVI), the primary parameter in Statistics of Extremes. Due to the stability on k of the MVRB EVI and associated VaR estimates, we propose the use of a heuristic stability criterion for the choice of k and q, providing applications of the methodology to simulated data and to log-returns of financial stocks.