Ramon van den Akker

Local Asymptotic Normality and Efficient Estimation for INAR(p) Models

Integer-valued autoregressive (INAR) processes have been introduced to model nonnegative integervalued phenomena that evolve in time.The distribution of an INAR(p) process is determined by two parameters: a vector of survival probabilities and a probability distribution on the nonnegative integers, called an immigration or innovation distribution.This paper provides an efficient estimator of the parameters, and in particular, shows that the INAR(p) model has the Local Asymptotic Normality property.

The asymptotic structure of nearly unstable non negative integer-valued AR(1) models

This paper considers non-negative integer-valued autoregressive processes where the autoregression parameter is close to unity. We consider the asymptotics of this ‘near unit root’ situation. The local asymptotic structure of the likelihood ratios of the model is obtained, showing that the limit experiment is Poissonian. To illustrate the statistical consequences we discuss efficient estimation of the autoregression parameter and efficient testing for a unit root.

Semiparametric Gaussian copula models : Geometry and efficient rank-based estimation

We propose, for multivariate Gaussian copula models with unknown margins and structured correlation matrices, a rank-based,semiparametrically efficient estimator for the Euclidean copula parameter. This estimator is defined as a one-step update of a rank-based pilot estimator in the direction of the efficient influence function, which is calculated explicitly. Moreover, finite-dimensional algebraic conditions are given that completely characterize efficiency of the pseudo-likelihood estimator and adaptivity of the model with respect to the unknown marginal distributions. For correlation matrices structured according to a factor model, the pseudo-likelihood estimator turns out to be semiparametrically efficient. On the other hand, for Toeplitz correlation matrices, the asymptotic relative efficiency of the pseudo-likelihood estimator can be as low as 20%. These findings are confirmed by Monte Carlo simulations. We indicate how our results can be extended to joint regression models.

On Quadratic Expansions of Log-Likelihoods and a General Asymptotic Linearity Result

Abstract Irrespective of the statistical model under study, the derivation of limits,in the Le Cam sense, of sequences of local experiments (see [7]-[10]) oftenfollows along very similar lines, essentially involving differentiability in quadraticmean of square roots of (conditional) densities. This chapter establishes two abstractand very general results providing sufficient and nearly necessary conditionsfor (i) the existence of a quadratic expansion, and (ii) the asymptotic linearity oflocal log-likelihood ratios (asymptotic linearity is needed, for instance, when unspecifiedmodel parameters are to be replaced, in some statistic of interest, withsome preliminary estimator). Such results have been established, for locally asymptoticallynormal (LAN) models involving independent and identically distributedobservations, by, e.g. [1], [11] and [12]. Similar results are provided here for modelsexhibiting serial dependencies which, so far, have been treated on a case-by-casebasis (see [4] and [5] for typical examples) and, in general, under stronger regularityassumptions. Unlike their i.i.d. counterparts, our results extend beyond the contextof LAN experiments, so that non-stationary unit-root time series and cointegrationmodels, for instance, also can be handled (see [6]).

A Class of Simple Semiparametrically Efficient Rank-Based Unit Root Tests

We propose a class of simple rank-based tests for the null hypothesis of a unit root. This class is indexed by the choice of a reference density g, which needs not coincide with the unknown actual innovation density f. The validity of these tests, in terms of exact finite sample size, is guaranteed by distribution-freeness, irrespective of the value of the drift and the actual underlying f. When based on a Gaussian reference density g, our tests (of the van der Waerden form) perform uniformly better, in terms of asymptotic relative effciency, than the Dickey and Fuller test --except under Gaussian f, where they are doing equally well. Under Student t3 density f, the effciency gain is as high as 110%, meaning that Dickey-Fuller requires over twice as many observations as we do in order to achieve comparable performance. This gain is even larger in case the underlying f has fatter tails; under Cauchy f, where Dickey and Fuller is no longer valid, it can be considered infinite. The test associated with reference density g is semiparametrically e±cient when f happens to coincide with g, in the ubiquitous case that the model contains a non-zero drift. Finally, with an estimated density f(n) substituted for the reference density g, our tests achieve uniform (with respect to f) semiparametric efficiency.

The Power Envelope of Panel Unit Root Tests in Case Stationary Alternatives Offset Explosive Ones

We derive the power envelope for panel unit root tests where heterogeneous alternatives are modeled via zero-expectation random perturbations. We obtain an asymptotically UMP test and discuss how to proceed when one is agnostic about the expectation of the perturbations.

Unit Root Tests for Cross-Sectionally Dependent Panels: The Influence of Observed Factors

This paper considers a heterogeneous panel unit root model with cross-sectional dependence generated by a factor structure—the factor common to all units being an observed covariate. The model is shown to be Locally Asymptotically Mixed Normal (LAMN), with the random part of the limiting Fisher information due to information generated by the covariate. Because of the LAMN structure, no asymptotically uniformly most powerful test exists; we investigate the asymptotic power properties of the locally optimal test, the best point optimal test, and the conditionally optimal t-test. Although one might expect the best point optimal test to be superior, the performance of the computationally simpler t-test is comparable.

Rank-based Tests of the Cointegrating Rank in Semiparametric Error Correction Models

This paper introduces rank-based tests for the cointegrating rank in an Error CorrectionModel with i.i.d. elliptical innovations. The tests are asymptotically distribution-free,and their validity does not depend on the actual distribution of the innovations. Thisresult holds despite the fact that, depending on the alternatives considered, the model exhibitsa non-standard Locally Asymptotically Brownian Functional (LABF) and LocallyAsymptotically Mixed Normal (LAMN) local structure—a structure which we completelycharacterize. Our tests, which have the general form of Lagrange multiplier tests, dependon a reference density that can freely be chosen, and thus is not restricted to be Gaussianas in traditional quasi-likelihood procedures. Moreover, appropriate choices of the referencedensity are achieving the semiparametric efficiency bounds. Simulations show thatour asymptotic analysis provides an accurate approximation to finite-sample behavior.Our results are based on an extension, of independent interest, of two abstract resultson the convergence of statistical experiments and the asymptotic linearity of statistics tothe context of, possibly non-stationary, time series

Superefficient estimation of the marginals by exploiting knowledge on the copula

We consider the problem of estimating the marginals in the case where there is knowledge on the copula. If the copula is smooth, it is known that it is possible to improve on the empirical distribution functions: optimal estimators still have a rate of convergence n^-^1^/^2, but a smaller asymptotic variance. In this paper we show that for non-smooth copulas it is sometimes possible to construct superefficient estimators of the marginals: we construct both a copula and, exploiting the information our copula provides, estimators of the marginals with the rate of convergence logn/n.