A diagnostic test for the distribution-free efficiency estimator: An example using U.S. commercial bank data

The distribution-free approach (DFA) to estimating X-efficiency assumes that individual firms exhibit constant inefficiency across time, and that inefficiency can be revealed by estimating a panel cost (or profit or production) function and averaging together the annual residuals for individual firms. However, the existing DFA literature may not pay enough attention to the consequences of including too many, or too few, time series observations in the data panel. This paper derives a test of whether additional annual data improves or worsens estimated X-efficiency, and demonstrates the test using a DFA cost efficiency model and U.S. commercial bank data from 1984 through 1994.     

Compact supported endographs and fuzzy sets

A metric is defined on a space of functions from a locally compact metric space X into the unit interval I in terms of the Hausdorff metric distance between their compact supported endographs in X × I. Convergence in this metric is shown to be equivalent to the conjunction of the Hausdorff metric convergence of supports in X and two conditions involving numerical values of the functions. The space of nonempty compact subsets of X with the Hausdorff metric is imbedded in the above function space by the characteristic function on subsets of X. Applications of these results to fuzzy subsets of X and fuzzy dynamical systems on X are indicated.     

The constructive theory of preference relations on a locally compact space

This paper, which is written within a rigorously constructive framework, deals with preference relations (strict weak orders) on a locally compact space X, and with the representation of such relations by continuous utility functions (order isomorphisms) from X into ℝ. Necessary conditions are given for finding the values of a utility function algorithmically in terms of the parameters when X is a locally compact, convex subset of R^N. These conditions single out the class of admissible preference relations, which are investigated in some detail. The paper concludes with some results on the algorithmic continuity of the process which assigns utility functions to admissible preference relations.The work of this paper can be regarded as a recursive development of preference and utility theory.     

Lipschitz-type functions on metric spaces

In order to find metric spaces X for which the algebra Lip^∗(X) of bounded Lipschitz functions on X determines the Lipschitz structure of X, we introduce the class of small-determined spaces. We show that this class includes precompact and quasi-convex metric spaces. We obtain several metric characterizations of this property, as well as some other characterizations given in terms of the uniform approximation and the extension of uniformly continuous functions. In particular we show that X is small-determined if and only if every uniformly continuous real function on X can be uniformly approximated by Lipschitz functions.     

Rates of convergence for partitioning and nearest neighbor regression estimates with unbounded data

Estimation of regression functions from independent and identically distributed data is considered. The L₂ error with integration with respect to the design measure is used as an error criterion. Usually in the analysis of the rate of convergence of estimates besides smoothness assumptions on the regression function and moment conditions on Y also boundedness assumptions on X are made. In this article we consider partitioning and nearest neighbor estimates and show that by replacing the boundedness assumption on X by a proper moment condition the same rate of convergence can be shown as for bounded data.     

Two Characterizations of Super-Reflexive Banach Spaces by the Behaviour of Differences of Convex Functions

A function defined on a Banach space X is called Δ-convex if it can be represented as a difference of two continuous convex functions. In this work we study the relationship between some geometrical properties of a Banach space X and the behaviour of the class of all Δ-convex functions defined on it. More precisely, we provide two new characterizations of super-reflexivity in terms Δ-convex functions.     

Quantile regression for robust bank efficiency score estimation

We discuss quantile regression techniques as a robust and easy to implement alternative for estimating Farell technical efficiency scores. The quantile regression approach estimates the production process for benchmark banks located at top conditional quantiles. Monte Carlo simulations reveal that even when generating data according to the assumptions of the stochastic frontier model (SFA), efficiency estimates obtained from quantile regressions resemble SFA-efficiency estimates. We apply the SFA and the quantile regression approach to German bank data for three banking groups, commercial banks, savings banks and cooperative banks to estimate efficiency scores based on a simple value added function and a multiple-input–multiple-output cost function. The results reveal that the efficient (benchmark) banks have production and cost elasticities which differ considerably from elasticities obtained from conditional mean functions and stochastic frontier functions.     

On error bounds for lower semicontinuous functions

We give some sufficient conditions for proper lower semicontinuous functions on metric spaces to have error bounds (with exponents). For a proper convex function f on a normed space X the existence of a local error bound implies that of a global error bound. If in addition X is a Banach space, then error bounds can be characterized by the subdifferential of f. In a reflexive Banach space X, we further obtain several sufficient and necessary conditions for the existence of error bounds in terms of the lower Dini derivative of f. Received: April 27, 2001 / Accepted: November 6, 2001?Published online April 12, 2002     

Admissibilities of linear estimator in a class of linear models with a multivariate t error variable

This paper discusses admissibilities of estimators in a class of linear models,which include the following common models:the univariate and multivariate linear models,the growth curve model,the extended growth curve model,the seemingly unrelated regression equations,the variance components model,and so on.It is proved that admissible estimators of functions of the regression coefficient β in the class of linear models with multivariate t error terms,called as Model II,are also ones in the case that error terms have multivariate normal distribution under a strictly convex loss function or a matrix loss function.It is also proved under Model II that the usual estimators of β are admissible for p 2 with a quadratic loss function,and are admissible for any p with a matrix loss function,where p is the dimension of β.     

On boundaries on the predual of the Lorentz sequence space

Let X be the canonical predual of the Lorentz sequence space and let Au(BX) be the Banach algebra of all complex valued functions defined on the closed unit ball BX of X which are uniformly continuous on BX and holomorphic on the interior of BX, endowed with the sup norm. A characterization of the boundaries for Au(BX) is given in terms of the distance to the strong peak sets of this algebra.     

Criterion of uniform approximability by harmonic functions on compact sets in ℝ3

For a function continuous on a compact set X ? ?³ and harmonic inside X, we obtain a criterion of uniform approximability by functions harmonic in a neighborhood of X in terms of the classical harmonic capacity. The proof is based on an improved localization scheme of A.G. Vitushkin, on a special geometric construction, and on the methods of the theory of singular integrals.     

Monotonicity properties of a class of stochastic inventory systems

We consider inventory systems which are governed by an (r,q) or (r,nq) policy. We derive general conditions for monotonicity of the three optimal policy parameters, i.e., the optimal reorder level, order quantity and order-up-to level, as well as the optimal cost value, as a function of the various model primitives, be it cost parameters or complete cost rate functions or characteristics of the demand and leadtime processes. These results are obtained as corollaries from a few general theorems, with separate treatment given to the case where the policy parameters are continuous variables and that where they need to be restricted to integer values. The results are applied both to standard inventory models and to those with general shelf age and delay dependent inventory costs.     

Formal loops III: Additive functions and the Radon transform

To any algebraic variety X and closed 2-form ω on X, we associate the “symplectic action functional” T(ω) which is a function on the formal loop space LX introduced by the authors earlier. The correspondence ω→T(ω) can be seen as a version of the Radon transform. We give a characterization of the functions of the form T(ω) in terms of factorizability (infinitesimal analog of additivity in holomorphic pairs of pants) as well as in terms of vertex operator algebras.These results will be used in the subsequent paper which will relate the gerbe of chiral differential operators on X (whose lien is the sheaf of closed 2-forms) and the determinantal gerbe of the tangent bundle of LX (whose lien is the sheaf of invertible functions on LX). On the level of liens this relation associates to a closed 2-form ω the invertible function expT(ω).     

Vector measures and strict topologies

Let X be a completely regular Hausdorff space and Cb(X) be the space of all real-valued bounded continuous functions on X, endowed with the strict topology βσ. We study topological properties of continuous and weakly compact operators from Cb(X) to a locally convex Hausdorff space in terms of their representing vector measures. In particular, Alexandrov representation type theorems are derived. Moreover, a Yosida-Hewitt type decomposition for weakly compact operators on Cb(X) is given.     

Adaptive age replacement strategies based on nonparametric predictive inference

We consider an age replacement problem using nonparametric predictive inference (NPI) for the lifetime of a future unit. Based on n observed failure times, NPI provides lower and upper bounds for the survival function for a future lifetime X_n+1, which are lower and upper survival functions in the theory of interval probability, and which lead to upper and lower cost functions, respectively, for age replacement based on the renewal reward theorem. Optimal age replacement times for X_n+1 follow by minimizing these cost functions. Although the renewal reward theorem implicitly assumes that the corresponding optimal strategy will be used for a long period, we study the effect on this strategy when the observed value for X_n+1, which is either an observed failure time or a right-censored observation, becomes available. This is possible due to the fully adaptive nature of our nonparametric approach, and the next optimal strategy will be for X_n+2. We compare the optimal strategies for X_n+1 and X_n+2 both analytically and via simulation studies. Our NPI-based approach is fully adaptive to the data, to which it adds only few structural assumptions. We discuss the possible use of this approach, and indeed the wider importance of the conclusions of this study to situations where one wishes to combine the statistical aspects of estimating a lifetime distribution with the more traditional operational research approach of determining optimal replacement strategies for lifetime distributions that are assumed to be known.     

Representation and approximation by series of continuous functions

Let X be a topological space and let C(X) be the ring of all real-valued continuous functions defined on X. We study the representation and approximation of continuous functions by sums of infinite series. Among other results, we give sufficient conditions in order to represent or approximate every continuous function by infinite series of functions, belonging to a previously fixed subfamily of C(X), when X is either a locally compact paracompact space or a Lindelöf space.     

General theorems on rates of convergence in distribution of random variables I. General limit theorems

Let (X_n)_n?$\text{N}$ be a sequence of real, independent, not necessarily identically distributed random variables (r.v.) with distribution functions F_Xn, and S_n = Σ_i=1ⁿX_i. The authors present limit theorems together with convergence rates for the normalized sums ?(n)S_n, where ?: $\text{N}$ → $\text{R}$⁺, ?(n) → 0, n → ∞, towards appropriate limiting r.v. X, the convergence being taken in the weak (star) sense. Thus higher order estimates are given for the expression ∝_$\text{R}$f(x) d[F_?(n)Sn(x) ? F_X(x)] which depend upon the normalizing function ?, decomposability properties of X and smoothness properties of the function f under consideration. The general theorems of this unified approach subsume O- and o-higher order error estimates based upon assumptions on associated moments. These results are also extended to multi-dimensional random vectors.     

Harmonic functions and exit boundary of superdiffusion

All positive harmonic functions in an arbitrary domain of a Euclidean space can be described in terms of the so-called exit boundary. This was established in 1941 by R.S. Martin. A probabilistic approach to the Martin theory is due to Doob and Hunt. It was extended later to harmonic functions associated with a wide class of Markov processes. The subject of this paper are harmonic functions associated with a superdiffusion X (we call them X-harmonic). The results of Evans and Perkins imply the existence and uniqueness of an integral representation of positive X-harmonic functions through extreme functions. An outstanding problem is to find all extremal functions (they are in 1-1 correspondence with the points of the exit boundary).An interest in X-harmonic functions is motivated, in part, by the fact that each of them provides a way of conditioning a superprocess. Path properties of conditioned superprocesses (corresponding to various special X-harmonic functions) were investigated by a number of authors.Important classes of X-harmonic functions are related to positive solutions of semilinear partial differential equations. Almost nothing is known about their decomposition into extreme elements. A progress in this direction may create new tools for investigating solutions of the equations.The goal of this paper is to summarize all known facts about X-harmonic functions, to present the results of various authors in a more general setting in a unified form and to outline a program of further work.     

The Witten deformation for even dimensional spaces with cone-like singularities and admissible Morse functions

In this Note we generalise the Witten deformation to even dimensional Riemannian manifolds with cone-like singularities X and certain functions f, which we call admissible Morse functions. As a corollary we get Morse inequalities for the L²-Betti numbers of X. The contribution of a singular point p of X to the Morse inequalities can be expressed in terms of the intersection cohomology of the local Morse datum of f at p. The definition of the class of functions which we study here is inspired by stratified Morse theory as developed by Goresky and MacPherson. However the setting here is different since the spaces considered here are manifolds with cone-like singularities instead of Whitney stratified spaces.     

Vector-valued Hardy spaces in non-smooth domains

We characterize the Radon-Nikodým property of a Banach space X in terms of the existence of non-tangential limits of X-valued harmonic functions u defined in a domain D⊂Rn, n>2, with Lipschitz boundary and belonging to maximal Hardy spaces. This extends the same result previously known for the unit disk of C. We also prove an atomic decomposition of the Borel X-valued measures in ∂D that arise as boundary limits of X-valued harmonic functions whose non-tangential maximal function is integrable with respect to harmonic measure of ∂D.