THE INEFFICIENCY OF LEASTSQUARES IN GAUSS-MARKOV ANDVARIANCE COMPONENT MODELS

1.IntroductionThispaperwillusethefollowingnotations.ForanymatrixA,A andW(A)denotetheMoors-PenroseinverseandthecolumnspaceofA,respectively.ForanysquarematrixA,IAImeansthedeterminantofA,A20(A>0)meansAisnonnegative(positive)definite.ConsidertheGauss-MarkovmodelY=Xo e,E(e)=0,Coy(e)~a'E,(1.1)whereYisann-dimensionalobservablerandomvector,XisannxpknownmatrixwithcolUInn-fUllrank,Tisapdimensionalparametervector,eisann-dimensionalunobserVablerandomvector,aZisanunknownpositiveparameter,Z20.I…     

Jackknifing in partially linear regression models with serially correlated errors

In this paper jackknifing technique is examined for functions of the parametric component in a partially linear regression model with serially correlated errors. By deleting partial residuals a jackknife-type estimator is proposed. It is shown that the jackknife-type estimator and the usual semiparametric least-squares estimator (SLSE) are asymptotically equivalent. However, simulation shows that the former has smaller biases than the latter when the sample size is small or moderate. Moreover, since the errors are correlated, both the Tukey type and the delta type jackknife asymptotic variance estimators are not consistent. By introducing cross-product terms, a consistent estimator of the jackknife asymptotic variance is constructed and shown to be robust against heterogeneity of the error variances. In addition, simulation results show that confidence interval estimation based on the proposed jackknife estimator has better coverage probability than that based on the SLSE, even though the latter uses the information of the error structure, while the former does not.     

A third order optimum property of the ML estimator in a linear functional relationship model and simultaneous equation system in econometrics

Summary The maximum likelihood (ML) estimator and its modification in the linear functional relationship model with incidental parameters are shown to be third-order asymptotically efficient among a class of almost median-unbiased and almost mean-unbiased estimators, respectively, in the large sample sense. This means that the limited information maximum likelihood (LIML) estimator in the simultaneous equation system is third-order asymptotically efficient when the number of excluded exogenous variables in a particular structural equation is growing along with the sample size. It implies that the LIML estimator has an optimum property when the system of structural equations is large. The research was partly supported by National Science Foundation Grant SES 79-13976 at the Institute for Mathematical Studies in the Social Sciences, Stanford University and Grant-in-Aid 60301081 of the Ministry of Education, Science and Culture at the Faculty of Economics, University of Tokyo. This paper was originally written as a part of the author's Ph.D. dissertation submitted to Stanford University in August, 1981. Some details of the paper were deleted at the suggestion of the associate editor of this journal.     

Some test statistics for the structural coefficients of the multivariate linear functional relationship model

Summary For the testing problem concerning the coefficients of the multivariate linear functional relationship model, the distribution of a statistic previously proposed by A. P. Basu depends on the unknown covariance matrixV of errors, so limiting its applicability. This article proposes new test statistics with sampling distributions which are independent of the unknown parameters for the cases whereV is either unknown or known only up to a proportionality factor. The exact distributions of the test statistics are also discussed.     

The superiority of empirical bayes estimation of parameters in partitioned normal linear model

In this article,the empirical Bayes（EB）estimators are constructed for the estimable functions of the parameters in partitioned normal linear model.The superiorities of the EB estimators over ordinary least-squares（LS）estimator are investigated under mean square error matrix（MSEM）criterion.     

The rate of convergence for the least squares estimator in nonlinear regression model with dependent errors

We study the parameter estimation in a nonlinear regression model with a general error's structure,strong consistency and strong consistency rate of the least squares estimator are obtained.     

On the consistency of a least squares identification procedure in linear evolution systems

Conditions for the convergence of parameter estimates to the true value applicable in continuous time linear stochastic evolution systems are presented. A special case, continuous time linear stochastic systems with delays, is also considered. A persistent excitation property is proved by control theory methods     

Latent scale linear models for multivariate ordinal responses and analysis by the method of weighted least squares

Summary A multivariate latent scale linear model is defined for multivariate ordered categorical responses and inference procedures based on the weighted least squares method are developed. Several applications of the model are suggested and illustrated through an analysis of real data. Asymptotic properties of the weighted least squares method are examined and some consequences of misspecification of the model are also discussed.     

Approximation to the distribution of the least squares estimators in two dimensional cosine models by randomly weighted bootstrap

Recently, Kundu and Gupta （Metrika, 48：83 C 97, 1998） established the asymptotic normality of the least squares estimators in the two dimensional cosine model. In this paper, we give the approximation to the general least squares estimators by using random weights which is called the Bayesian bootstrap or the random weighting method by Rubin （Annals of Statistics, 9：130 C 134, 1981） and Zheng （Acta Math. Appl. Sinica （in Chinese）, 10（2）： 247 C 253, 1987）. A simulation study shows that this approximation works very well.     

Precise asymptotics for the first moment of the error variance estimator in linear models

Let σ² be the unknown error variance of a linear model and let be the estimator of σ² based on the residual sum of squares. In this work, we show the precise asymptotics in the law of the logarithm for the first moment of the error variance estimator.     

Asymptotic expansion of the null distribution of test statistic for linear hypothesis in nonnormal linear model

This paper is concerned with the null distribution of test statistic T for testing a linear hypothesis in a linear model without assuming normal errors. The test statistic includes typical ANOVA test statistics. It is known that the null distribution of T converges to χ² when the sample size n is large under an adequate condition of the design matrix. We extend this result by obtaining an asymptotic expansion under general condition. Next, asymptotic expansions of one- and two-way test statistics are obtained by using this general one. Numerical accuracies are studied for some approximations of percent points and actual test sizes of T for two-way ANOVA test case based on the limiting distribution and an asymptotic expansion.     

奇异线性模型最小二乘估计的相对效率

对于奇异线性模型引入了参数β的最小二乘估计相对与最佳线性无偏估计的一种新的相对效率，并讨论了它的下界。     

聚集数据线性模型参数估计的相对效率与广义相关系数

对于聚集数据的线性模型,本文给出了Peter—Karsten估计相对于最佳线性无偏估计的一个相对效率,得到了相对效率的下界,讨论了该相对效率与广义相关系数的关系.