Iterative Bias Correction of the Cross‐Validation Criterion

Abstract. The cross‐validation (CV) criterion is known to be asecond‐order unbiased estimator of the risk function measuring the discrepancy between the candidate model and the true model, as well as the generalized information criterion (GIC) and the extended information criterion (EIC). In the present article, we show that the 2kth‐order unbiased estimator can be obtained using a linear combination from the leave‐one‐out CV criterion to the leave‐k‐out CV criterion. The proposed scheme is unique in that a bias smaller than that of a jackknife method can be obtained without any analytic calculation, that is, it is not necessary to obtain the explicit form of several terms in an asymptotic expansion of the bias. Furthermore, the proposed criterion can be regarded as a finite correction of a bias‐corrected CV criterion by using scalar coefficients in a bias‐corrected EIC obtained by the bootstrap iteration.     

A Stochastic Estimator of the Trace of the Influence Matrix for Laplacian Smoothing Splines

An unbiased stochastic estimator of tr(I–A), where A is the influence matrix associated with the calculation of Laplacian smoothing splines, is described. The estimator is similar to one recently developed by Girard but satisfies a minimum variance criterion and does not require the simulation of a standard normal variable. It uses instead simulations of the discrete random variable which takes the values 1, -1 each with probability 1/2. Bounds on the variance of the estimator, similar to those established by Girard, are obtained using elementary methods. The estimator can be used to approximately minimize generalised cross validation (GCV) when using discretized iterative methods for fitting Laplacian smoothing splines to very large data sets. Simulated examples show that the estimated trace values, using either the estimator presented here or the estimator of Girard, perform almost as well as the exact values when applied to the minimization of GCV for n as small as a few hundred, where n is the number of data points.     

The uniformly minimum variance unbiased estimator of odds ratio in case–control studies under inverse sampling

The stated goal of this paper is to propose the uniformly minimum variance unbiased estimator of odds ratio in case–control studies under inverse sampling design. The problem of estimating odds ratio plays a central role in case–control studies. However, the traditional sampling schemes appear inadequate when the expected frequencies of not exposed cases and exposed controls can be very low. In such a case, it is convenient to use the inverse sampling design, which requires that random drawings shall be continued until a given number of relevant events has emerged. In this paper we prove that a uniformly minimum variance unbiased estimator of odds ratio does not exist under usual binomial sampling, while the standard odds ratio estimator is uniformly minimum variance unbiased under inverse sampling. In addition, we compare these two sampling schemes by means of large-sample theory and small-sample simulation.     

Characterization of an optimal matrix estimator under convex loss function

Characterization of an optimal vector estimator and an optimal matrix estimator are obtained. In each case appropriate convex loss functions are considered. The results are illustrated through the problems of simultaneous unbiased estimation, simultaneous equivariant estimation and simultaneous unbiased prediction. Further an optimality criterion is proposed for matrix unbiased estimation and it is shown that the matrix unbiased estimation of a matrix parametric function and the minimum variance unbiased estimation of its components are equivalent.     

MODEL-UNBIASEDNESS AND THE HORVITZ-THOMPSON ESTIMATOR IN FINITE POPULATION SAMPLING

Under the, notion of superpopulation models, the concept of minimum expected variance is adopted as an optimality criterion for design-unbiased estimators, i.e. unbiased under repeated sampling. In this article, it is shown that the Horvitz-Thompson estimator is optimal among such estimators if and only if it is model-unbiased, i.e. unbiased under the model. The family of linear models is considered and a sample design is suggested to preserve the model-unbiasedness (and hence the optimality) of the Horvitz-Thompson estimator. It is also shown that under these models the Horvitz-Thompson estimator together with the suggested sample design is optimal among design-unbiased estimators with any sample design (of fixed size n ) having non-zero probabilities of inclusion for all population units.     

Estimation in a linear regression model under the Kullback–Leibler loss and its application to model selection

This paper is concerned with the problem of constructing a good predictive distribution relative to the Kullback–Leibler information in a linear regression model. The problem is equivalent to the simultaneous estimation of regression coefficients and error variance in terms of a complicated risk, which yields a new challenging issue in a decision-theoretic framework. An estimator of the variance is incorporated here into a loss for estimating the regression coefficients. Several estimators of the variance and of the regression coefficients are proposed and shown to improve on usual benchmark estimators both analytically and numerically. Finally, the prediction problem of a distribution is noted to be related to an information criterion for model selection like the Akaike information criterion (AIC). Thus, several AIC variants are obtained based on proposed and improved estimators and are compared numerically with AIC as model selection procedures.     

A note on umvu estimation in the transformed chi-square family

The transformed chi-square family includes many common one-parameter continuous distributions. In that family, we give conditions under which a given function of the mean admits a minimum variance unbiased estimator and an orthogonal expansion for this estimator in terms of the generalized Laguerre polynomials. We show that such expansion is useful for obtaining bounds for the variance and for the study of the asymptotic properties of the unbiased estimators.     

An alternate version of the conceptual predictive statistic based on a symmetrized discrepancy measure

The conceptual predictive statistic, C_p, is a widely used criterion for model selection in linear regression. C_p serves as an estimator of a discrepancy, a measure that reflects the disparity between the generating model and a fitted candidate model. This discrepancy, based on scaled squared error loss, is asymmetric: an alternate measure is obtained by reversing the roles of the two models in the definition of the measure. We propose a variant of the C_p statistic based on estimating a symmetrized version of the discrepancy targeted by C_p. We claim that the resulting criterion provides better protection against overfitting than C_p, since the symmetric discrepancy is more sensitive towards detecting overspecification than its asymmetric counterpart. We illustrate our claim by presenting simulation results. Finally, we demonstrate the practical utility of the new criterion by discussing a modeling application based on data collected in a cardiac rehabilitation program at University of Iowa Hospitals and Clinics.     

Estimation of reliability for a multicomponent survival stress-strength model based on exponential distributions

Uniformly minimum variance unbiased estimator (UMVUE) of reliability in stress-strength model (known stress) is obtained for a multicomponent survival model based on exponential distributions for parallel system. The variance of this estimator is compared with Cramer-Rao lower bound (CRB) for the variance of unbiased estimator of reliability, and the mean square error (MSE) of maximum likelihood estimator of reliability in case of two component system.     

Unbiased variance estimation in a simple exponential population using ranked set samples

The problem considered in this paper is that of unbiased estimation of the variance of an exponential distribution using a ranked set sample (RSS). We propose some unbiased estimators each of which is better than the non-parametric minimum variance quadratic unbiased estimator based on a balanced ranked set sample as well as the uniformly minimum variance unbiased estimator based on a simple random sample (SRS) of the same size. Relative performances of the proposed estimators and a few other properties of the estimators including their robustness under imperfect ranking have also been studied.     

A Proportional Hazards Regression Model for the Subdistribution with Covariates‐adjusted Censoring Weight for Competing Risks Data

With competing risks data, one often needs to assess the treatment and covariate effects on the cumulative incidence function. Fine and Gray proposed a proportional hazards regression model for the subdistribution of a competing risk with the assumption that the censoring distribution and the covariates are independent. Covariate‐dependent censoring sometimes occurs in medical studies. In this paper, we study the proportional hazards regression model for the subdistribution of a competing risk with proper adjustments for covariate‐dependent censoring. We consider a covariate‐adjusted weight function by fitting the Cox model for the censoring distribution and using the predictive probability for each individual. Our simulation study shows that the covariate‐adjusted weight estimator is basically unbiased when the censoring time depends on the covariates, and the covariate‐adjusted weight approach works well for the variance estimator as well. We illustrate our methods with bone marrow transplant data from the Center for International Blood and Marrow Transplant Research. Here, cancer relapse and death in complete remission are two competing risks.     

Selection Strategy for Covariance Structure of Random Effects in Linear Mixed‐effects Models

Linear mixed‐effects models are a powerful tool for modelling longitudinal data and are widely used in practice. For a given set of covariates in a linear mixed‐effects model, selecting the covariance structure of random effects is an important problem. In this paper, we develop a joint likelihood‐based selection criterion. Our criterion is the approximately unbiased estimator of the expected Kullback–Leibler information. This criterion is also asymptotically optimal in the sense that for large samples, estimates based on the covariance matrix selected by the criterion minimize the approximate Kullback–Leibler information. Finite sample performance of the proposed method is assessed by simulation experiments. As an illustration, the criterion is applied to a data set from an AIDS clinical trial.     

Estimating Mark Functions Through Spectral Analysis for Marked Point Patterns

Classical techniques for modeling numerical data associated to a regular grid have been widely developed in the literature. When a trigonometric model for the data is considered, it is possible to use the corresponding least squares (classical) estimators, but when the data are not observed on a regular grid, these estimators do not show appropriate properties. In this article we propose a novel way to model data that is not observed on a regular grid, and we establish a practical criterion, based on the mean squared error (MSE), to objectively decide which estimator should be used in each case: the inappropriate classical or the new unbiased estimator, which has greater variance. Jackknife and cross-validation techniques are used to follow a similar criterion in practice, when the MSE is not known. Finally, we present an application of the methodology to univariate and bivariate data.     

On the cramer-frechet-rao inequality for translation parameter in the case of finite support

In this paper we investigate the problem of deriving the C-F-R (CRAMER-FRECHET-RAO) bound for the variance of an unbiased estimator of the translation para¬meter for a class of distributions having as support an interval of fixed length. Starting with the general form of the O-F-R, inequality studied earlier by VINCZE (1979) for mixed

densities, we prove some inequalities related to the information quantity occurring in the C-F-R bound. The case when the variance of the unbiased estimator does not depend upon the translation parameter is investigated. The case when the variance depends upon the translation parameter is also briefly discussed. Finally some remarks will be given

concerning the attainability of the variance,bounds given in this paper     

Unbiased Estimation of Central Moments by using U-statistics

We obtain an estimator of the r th central moment of a distribution, which is unbiased for all distributions for which the first r moments exist. We do this by finding the kernel which allows the r th central moment to be written as a regular statistical functional. The U-statistic associated with this kernel is the unique symmetric unbiased estimator of the r th central moment, and, for each distribution, it has minimum variance among all estimators which are unbiased for all these distributions.     

Improved predictive model selection

This paper introduces a new information criterion for model selection, based on a predictive distribution which improves the estimative one. The selection statistic is defined as a first-order estimator for the expected Kullback–Leibler information between the true model and the fitted one, obtained by means of the improved predictive procedure. The criterion turns out to be a simple, non-computationally demanding, alternative to the Takeuchi information criterion. Whenever the information identity holds, the Akaike information criterion is recovered as a particular case. The results are obtained in the case of independent, but not necessarily identically distributed, observations. Some applications, related to exponential families of distributions and regression models, are presented.     

Best unbiased estimation of fixed effects in mixed ANOVA models

In a linear model with an arbitrary variance–covariance matrix, Zyskind (Ann. Math. Statist. 38 (1967) 1092) provided necessary and sufficient conditions for when a given linear function of the fixed-effect parameters has a best linear unbiased estimator (BLUE). If these conditions hold uniformly for all possible variance–covariance parameters (i.e., there is a UBLUE) and if the data are assumed to be normally distributed, these conditions are also necessary and sufficient for the parametric function to have a uniformly minimum variance unbiased estimator (UMVUE). For mixed-effects ANOVA models, we show how these conditions can be translated in terms of the incidence array, which facilitates verification of the UBLUE and UMVUE properties and facilitates construction of designs having such properties.     

Comparison of normal variance estimators under multiple criteria and towards a compromise estimator

For estimating a normal variance under the squared error loss function it is well known that the best affine (location and scale) equivariant estimator, which is better than the maximum likelihood estimator as well as the unbiased estimator, is also inadmissible. The improved estimators, e.g., stein type, brown type and Brewster–Zidek type, are all scale equivariant but not location invariant. Lately, a good amount of research has been done to compare the improved estimators in terms of risk, but comparatively less attention had been paid to compare these estimators in terms of the Pitman nearness criterion (PNC) as well as the stochastic domination criterion (SDC). In this paper, we have undertaken a comprehensive study to compare various variance estimators in terms of the PNC and the SDC, which has been long overdue. Finally, using the results for risk, the PNC and the SDC, we propose a compromise estimator (sort of a robust estimator) which appears to work ‘well’ under all the criteria discussed above.     

Optimal sequential estimation for semi-markov and markov renewal processes

We consider the problem of obtaining efficient estimators and sampling plans for semi-Markov and Markov-renewal processes. A lower bound for the variance of an unbiased estimator of a function of the parameters is obtained under a sequential scheme and we characterize the parametric functions and sampling plans which admit minimum variance unbiased estimators.     

On the restricted almost unbiased estimators in linear regression

In this paper, the restricted almost unbiased ridge regression estimator and restricted almost unbiased Liu estimator are introduced for the vector of parameters in a multiple linear regression model with linear restrictions. The bias, variance matrices and mean square error (MSE) of the proposed estimators are derived and compared. It is shown that the proposed estimators will have smaller quadratic bias but larger variance than the corresponding competitors in literatures. However, they will respectively outperform the latter according to the MSE criterion under certain conditions. Finally, a simulation study and a numerical example are given to illustrate some of the theoretical results.