ON THE ACCURACY OF THE LEAST SQUARES AND THE TOTAL LEAST SQUARES METHODS

Consider solving an overdetermined system of linear algebraic equations by both the least squares method (LS) and the total least squares method (TLS). Extensive published computational evidence shows that when the original system is consistent. one often obtains more accurate solutions by using the TLS method rather than the LS method. These numerical observations contrast with existing analytic perturbation theories for the LS and TLS methods which show that the upper bounds for the LS solution are always smaller than the corresponding upper bounds for the TLS solutions. In this paper we derive a new upper bound for the TLS solution and indicate when the TLS method can be more accurate than the LS method.Many applied problems in signal processing lead to overdetermined systems of linear equations where the matrix and right hand side are determined by the experimental observations (usually in the form of a lime series). It often happens that as the number of columns of the matrix becomes larger, the ra     

THE LAW OF ITERATED LOGARITHM FOR R／S STATISTICS

A law of iterated logarithm for R/S statistics with the help of the strong approximations of R/S statistics by functions of a Wiener process is shown.     

ASYMPTOTIC LIMITS OF ONE－DIMENSIONAL HYDRODYNAMIC MODELS FOR PLASMAS AND SEMICONDUCTORS

51. IntroductionIn mathematica1 modeling and numerical simulation for plasmas and semiconductorsdevices, the hydrodynamic model like the Euler-Poisson system is wildly used. Due tothe hyperbolic feature of the Euler equations, the study of weak solutions to the Euler-Poisson system is limited in one space dimension. In such situation, the existence of globalweak solutions can be proved under natural assumptions (see [22, 20, 17, 5, 18]). In aseries of papersl1l'l2'l31l4J l we are interested…     

A LAW OF THE ITERATED LOGARITHM FOR NONPARAMETRIC CONDITIONAL DENSITY ESTIMATORS

We establish a law of the itearted logarithm for a triangular array of indepentent random variables, and apply it to obtain sharp pointwise rates of strong consistency for a large class of nonparametric estimators of bivariate density and conditional density. We consider the case of double kernel estimators anal trigonometric series estimators in detail.     

A LAW OF THE ITERATED LOGARITHM FOR NEIGHBOR-TYPE REGRESSION FUNCTION ESTIMATOR

Let (X, Y) be a two-dimensional random variable. A law of the iterated logarithm is established for a smoothed neighbor-typo estimator of the regression function m(x)=E(Y|X=x) under conditions much weaker than needed for the Nadaraya-Watson estimator. Also the sharp pointwise rates of strong consistency of this estimator is discussed in detail.     

THE ASYMPTOTIC VALIDITY OF THE F-TEST IN A TWO-STAGE LEAST SQUARES MODEL

The usual F--test has been used to test a general linear hypothesis for a two--stage least squaresmethod in a system of economic equations. However, we find that this F--test is actuallyasymptotically invalid. Some suggestions are given for testing a general linear hypothesis in thissituation.     

THE LAW OF THE ITERATED LOGARITHM OF THE KAPLAN-MEIER INTEGRAL AND ITS APPLICATION

For right censored data, the law of the iterated logarithm of the Kaplan-Meier integral is established. As an application, the authors prove the law of the iterated logarithm for weighted least square estimates of randomly censored linear regression model.     

A STRASSEN LAW OF THE ITERATED LOGARITHM FOR PROCESSES WITH INDEPENDENT INCREMENT

ＡＳＴＲＡＳＳＥＮＬＡＷＯＦＴＨＥＩＴＥＲＡＴＥＤＬＯＧＡＲＩＴＨＭＦＯＲＰＲＯＣＥＳＳＥＳＷＩＴＨＩＮＤＥＰＥＮＤＥＮＴＩＮＣＲＥＭＥＮＴＷａｎｇＪｉａｇａｎｇＡｂｓｔｒａｃｔＬｅｔＸ＝｛Ｘ（ｔ），ｔ０｝ｂｅａｐｒｏｃｅｓｗｉｔｈｉｎｄｅｐ...     

GLOBAL BLOWUP AND BLOWUP RATE ESTIMATES OF SOLUTIONS FOR A CLASS OF NONLINEAR NON-LOCAL REACTION-DIFFUSION PROBLEMS

In this paper, the global blowup properties of solutions for a class of non-linear non-local reaction-diffusion problems are investigated by the methods of the priorestimates. Moreover, the blowup rate estimate of the solution is given.     

SYMMETRIC INTEGRAL AND CANONICAL EXTENSION FOR JUMP PROCESS SOME COMBINATORIAL RESULTS

Using approximation technique, we introduce the concepts of canonical extension and symmetrio integral for jump process and obtain some results in the chaotic form.     

Asymptotic normality and strong consistency of maximum quasi-likelihood estimates in generalized linear models

In a generalized linear model with q x 1 responses, the bounded and fixed (or adaptive) p × q regressors Zi and the general link function, under the most general assumption on the minimum eigenvalue of ZiZ'i,the moment condition on responses as weak as possible and the other mild regular conditions, we prove that the maximum quasi-likelihood estimates for the regression parameter vector are asymptotically normal and strongly consistent.     

On Berry-Esséen rates,a law of the iterated logarithm and an invariance principle for the proportion of the sample below the sample mean

Let F_n(x) be the empirical distribution function based on n independent random variables X₁,…,X_n from a common distribution function F(x), and let $\text{X}\text{= Σ}{}_{\mathrm{i=1}}{}^{\mathrm{n}}\text{X}{}_{\mathrm{i}}\text{n}$ be the sample mean. We derive the rate of convergence of $\text{F}{}_{\mathrm{n}}\text{(}\text{X}\text{)}$ to normality (for the regular as well as nonregular cases), a law of iterated logarithm, and an invariance principle for $\text{F}{}_{\mathrm{n}}\text{(}\text{X}\text{)}$.