An approximation of the distribution function of the LIML identifiability test statistic using the method of moments

This paper contains an application of the asymptotic expansion of a pFp() function to a problem encountered in econometrics. In particular we consider an approximation of the distribution function of the limited information maximum likelihood (LIML) identifiability test statistic using the method of moments. An expression for the Sth order asymptotic approximation of the moments of the LIML identifiability test statistic is derived and tabulated. The exact distribution function of the test statistic is approximated by a member of the class of F (variance ratio) distribution functions having the same first two integer moments. Some tabulations of the approximating distribution function are included.     

The covariance matrix of normal order statistics

An approximation is given to calculate V, the covariance matrix for normal order statistics. The approximation gives considerable improvement over previous approximations, and the computing algorithm is available from the authors.     

Contributions to-asymptotic theory in regression models with linear covariance structure 1

Asymptotic results are .presented- for estimating the parameters in variance-components models both with linear and with nonlinear regression functions.     

Modelling association between two irregularly observed spatiotemporal processes by using maximum covariance analysis

Summary.  Climatic phenomena such as the El-Niño–southern oscillation and the north Atlantic oscillation are results of complex interactions between atmospheric and oceanic processes. Understanding the interactions has enabled scientists to give early warning of the forthcoming phenomena, thereby reducing damage caused by them. Statistical methods have played an important role in revealing effects of these phenomena on different regions of the world. One such method is maximum covariance analysis (MCA). Two apparent weaknesses are associated with MCA. Firstly, it tends to produce estimates with a low signal-to-noise ratio, especially when the sample size is small. Secondly, there has been no objective way of incorporating incomplete records, which are frequently encountered in climatology and oceanographic data-bases. We introduce an MCA which incorporates a smoothing procedure on the estimates. The introduction of the smoothing procedure is shown to improve the signal-to-noise ratio on the estimates. The estimation of smoothing parameters is carried out by using a penalized likelihood approach, which makes the inclusion of incomplete records quite straightforward. The methodology is applied to investigate the association between Irish winter precipitation and sea surface temperature anomalies around the world. The results show relationships between Irish precipitation anomalies and the El-Niño–southern oscillation and the north Atlantic oscillation phenomena.     

On repeated measures analysis with misspecified covariance structure

In recent years various sophisticated methods have been developed for the analysis of repeated measures, or longitudinal data. The more traditional approach, based on a normal likelihood function, has been shown to be unsatisfactory, in the sense of yielding asymptotically biased estimates when the covariance structure is misspecified. More recent methodology, based on generalized linear models and quasi-likelihood estimation, has gained widespread acceptance as 'generalized estimating equations'. However, this also has theoretical problems. In this paper a suggestion is made for improving the asymptotic behaviour of estimators by using the older approach, implemented via Gaussian estimation. The resulting estimating equations include the quasi-score function as one component, so the methodology proposed can be viewed as a combination of Gaussian estimation and generalized estimating equations which has a firmer asymptotic basis than either alone has.     

A Multiple Imputation Approach to Linear Regression with Clustered Censored Data

Weextend Wei and Tanner's (1991) multiple imputation approach insemi-parametric linear regression for univariate censored datato clustered censored data. The main idea is to iterate the followingtwo steps: 1) using the data augmentation to impute for censoredfailure times; 2) fitting a linear model with imputed completedata, which takes into consideration of clustering among failuretimes. In particular, we propose using the generalized estimatingequations (GEE) or a linear mixed-effects model to implementthe second step. Through simulation studies our proposal comparesfavorably to the independence approach (Lee et al., 1993), whichignores the within-cluster correlation in estimating the regressioncoefficient. Our proposal is easy to implement by using existingsoftwares.     

Estimating parameters in a simple errors-in-variables model: a new approach base on finite sample distribution theory

This article presents a first direct application of finite sample distribution theory. The relevance of analytical finite sample research is exemplified in the framework of a simple linear errors-in-variables model (EV Model) with known or approximately known measurement error variance. Analytical results derived byRichardson/Wu (1970) are applied for constructing new approximately unbiased estimators for the slope coefficient in the EV model. The new estimators are compared with the biased least squares estimator and with asymptotic theory based corrected least squares estimators. Retaining responsibility for remaining errors the author is indebted to Prof. H. Schneewei\ and Prof. J. Gruber for helpful comments and discussions. Mrs. A. Brandtstater deserves special mention and thanks for performing the computations reported in section 4.     

Basic structure of the asymptotic theory in dynamic nonlinear econometric models

This is the second of two papers that provide an expository discussion of the basic structure of the asymptotic theory of M-estimators in dynamic nonlinear models and a review of the literature. The first paper, Pötscher and Prucha(1991), deals with consistency. In the present paper we discuss asymptotic normality. As an important ingredient to the asymptotic normality proof in dynamic nonlinear models we consider central limit theorems for dependent random variables. We also discuss the estimation of the variance covariance matrix of m-estimators under heteroscedasticity and autocorrelation.     

Least squares theory for possibly singular models

In a recent paper, Scobey (1975) observed that the usual least squares theory can be applied even when the covariance matrix σ²V of Y in the linear model Y = Xβ + e is singular by choosing the Moore-Penrose inverse (V+XX′)⁺ instead of V^-1 when V is nonsingular. This result appears to be wrong. The appropriate treatment of the problem in the singular case is described.     

Parameter estimation for three-parameter generalized Pareto distribution by weighted non linear least squares

Generalized Pareto distribution (GPD) is widely used to model exceedances over thresholds. In this paper, we propose a new method, called weighted non linear least squares (WNLS), to estimate the parameters of the three-parameter GPD. Some asymptotic results of the proposed method are provided. An extensive simulation is carried out to evaluate the finite sample behaviour of the proposed method and to compare the behaviour with other methods suggested in the literature. The simulation results show that WNLS outperforms other methods in general situations. Finally, the WNLS is applied to analysis the real-life data.     

Representations of the covariance matrix for robustness in the gauss-markov model

This paper considers some extensions of the results of Rao and Rao and Mitra. They gave a table of general representations of the covariance matrix in terms of the given design matrix, under which various statistical procedures in the least squares theory based on the simple Gauss-Markov model with the spherical covariance matrix are also valid under the general Gauss-Markov model. We shall give extended tables adding some more results relating to robustness, especially in connection with the estimation and testing of hypotheses on linear parametric functions     

The collected works of john w. tukey

We describe novel, analytical, data-analysis, and Monte-Carlo-simulation studies of strongly heteroscedastic data of both small and wide range.Many different types of heteroscedasticity and fixed or variable weighting are incorporated through error-variance models.Attention is given to parameter bias determinations, evaluations of their significances, and to new ways to correct for bias.The error-variance models allow for both additive and independent power-law errors, and the power exponent is shown to be able to be well determined for typical physicalsciences data by the rapidly-converging, general-purpose, extended-least-squares program we use.The fitting and error-variance models are applied to both low-and high-heteroscedasticity situations, including single-response data from radioactive decay.Monte-Carlo simulations of data with similar parameters are used to evaluate the analytical models developed and the various minimization methods em-ployed, such as extended and generalized least squares.Logarithmic and inversion transformations are investigated in detail, and it is shown analytically and by simulations that exponential data with constant percentage errors can be logarithmically transformed to allow a simple parameter-bias-removal procedure.A more-general bias-reduction approach combining direct and inversion fitting is also developed.Distributions of fitting-model and error-variance-model parameters are shown to be typically non-normal, thus invalidating the usual estimates of parameter bias and precision.Errors in conventional confidence-interval estimates are quantified by comparison with accurate simulation results.     

Residuals for the linear model with general covariance structure

A general theory is presented for residuals from the general linear model with correlated errors. It is demonstrated that there are two fundamental types of residual associated with this model, referred to here as the marginal and the conditional residual. These measure respectively the distance to the global aspects of the model as represented by the expected value and the local aspects as represented by the conditional expected value. These residuals may be multivariate. Some important dualities are developed which have simple implications for diagnostics. The results are illustrated by reference to model diagnostics in time series and in classical multivariate analysis with independent cases.     

Recovering Information from Incremental Responses

Some yields analysed and reported in the literature have been adjusted by subtracting a control. It is found that full information can be recovered for estimable parameters and the error variance using these incremental responses, in comparison with unadjusted data. These findings are of practical importance, and they supplement materials usually found in a graduate course in linear inference. The issues are illustrated using a case study from the literature.     

Nonparametric bayesian inference for dichotomous response models

A Bayesian least squares approach is taken here to estimate certain parameters in generalized linear models for dichotomous response data. The method requires that only first and second moments of the probability distribution representing prior information be specified* Examples are presented to illustrate situations having direct estimates as well as those which require approximate or iterative solutions.     

The multiplier method in constrained estimation of covariance structure models

Based on the multiplier method of constrained minimization, an algorithm is developed to handle the constrained estimation problem in covariance structure analysis. In the context of a general model which has wide applicability in multivariate medical and behavioural researches, computer programs are implemented to produce the weighted least squares estimates and the maximum likelihood estimates. The multiplier method is compared with the penalty function method in terms of computer time, number of iterations and number of unconstrained minimizations. The indication is that the multiplier method is substantially better.     

A note on the unified theory of least squares

The general form of a matrix which appears in the normal equation for estimating parameters in the Gauss-Markoff linear model has been obtained.     

An asymptotic theory for semiparametric generalized least squares estimation in partially linear regression models

Consider a partially linear regression model with an unknown vector parameter β, an unknown functiong(·), and unknown heteroscedastic error variances. In this paper we develop an asymptotic semiparametric generalized least squares estimation theory under some weak moment conditions. These moment conditions are satisfied by many of the error distributions encountered in practice, and our theory does not require the number of replications to go to infinity.     

Semiparametric estimation of employment duration models

There are a variety of economic areas, such as studies of employment duration and of the durability of capital goods, in which data on important variables typically are censored. The standard techinques for estimating a model from censored data require the distributions of unobservable random components of the model to be specified a priori up to a finite set of parameters, and misspecification of these distributions usually leads to inconsistent parameter estimates. However, economic theory rarely gives guidance about distributions and the standard estimation techniques do not provide convenient methods for identifying distributions from censored data. Recently, several distribution-free or semiparametric methods for estimating censored regression models have been developed. This paper presents the results of using two such methods to estimate a model of employment duration. The paper reports the operating characteristics of the semiparametric estimators and compares the semiparametric estimates with those obtained from a standard parametric model.     

Comparisons among regression estimators under the generalized mean square error criterion

It is not always prossible to establish a preference ordering among regression estimators in terms of the generalized mean square error criterion. In the paper, we determine when it is feasible to use this criteion to couduct comparisons among ordinary least squares, principal components, ridge regression, and shrunken least squares estimators.