摘要:

SummaryThis paper presents the limit distribution (as the number of time points increase) for the score vector of a growth curve model assuming both stationary and explosive autoregressive (A.R.) errors. Limit distributions of the score statistic and the likelihood‐ratio statistic for testing composite hypotheses about the regression parameters of several growth curves, when the autocorrelation parameters are treated as nuisance parameters, are presente

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01212.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummaryThe aim of this paper is to investigate the problems of estimating a smooth function of the parameters in a general linear model and to clarify some of the points raised by Hinkley (1977) in connection with this problem. An example of the type of problem at hand is that of estimating the maximum (or minimum) mean value in a quadratic regression model. The estimator based on the least squares estimator of the parameters in the linear model is compared to the jackknife estimator and the weighted jackknife estimator proposed by Hinkley (1977). The asymptotic properties of the estimators are examined and their small sample properties are compared through simulation studies.

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01213.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummarySeveral statistics based on the empirical characteristic function have been proposed for testing the simple goodness‐of‐fit hypothesis that the data come from a population with a completely specified characteristic function which cannot be inverted in a closed form, the typical example being the class of stable characteristic functions. As an alternative approach, it is pointed out here that the inversion formula of Gil‐Pelaez and Rosén, as applied to the data and the hypothetical characteristic function via numerical integration, is the natural replacement of the probability integral transformation in the given situation. The transformed sample is from the uniform (0, l) distribution if and only if the null hypothesis is true, and for testing uniformity on (0,1) the whole arsenal of methods statistics so far produced can b

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01214.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummaryThis note gives an alternative derivation of Sargan and Bhargava’ s results concerning the probability of observing on the unit circle a local maximum of the likelihood function of regression models with first order moving average errors. The note also discusses the relevance of these results for the computation of the exact maximum likelihood estimation of regression models with moving average error

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01215.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummaryIt is shown that a test for adequacy of a fitted Arma (p, 4) model based on forecast errors, has the same asymptotic expected value whether the null hypothesis is true or false. A sampling study supports the conclusion in small to moderately large samples and indicates that for sample sizes commonly used by practitioners, the power of the test is very low.

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01216.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummaryWe are concerned with estimators which improve upon the best invariant estimator, in estimating a location parameter θ. If the loss function is L(θ ‐ a) with L convex, we give sufficient conditions for the inadmissibility of δ0(X) = X. If the loss is a weighted sum of squared errors, we find various classes of estimators δ which are better than δ0. In general, δ is the convolution of δ1(an estimator which improves upon δ0outside of a compact set) with a suitable probability density in Rp. The critical dimension of inadmissibility depends on the estimator δ1We also give several examples of estimators δ obtained in this way and state some op

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01217.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummaryLet X = (X1, ‐ Xp)prime; ˜ Np(μ, Σ) where μ= (μ1, ‐, μp)′ and Σ= diag (Σ21, ‐, Σ2p) are both unknown and p3. Let (ni‐ 2) wi/Σ2i! X2ni, independent. of wi(I ≠ j = 1, ‐, p). Assume that (w1, ‐, wp) and X are independent. Define W = diag (w1, ‐, wp) and ¶ X ¶2w= X′W‐1Q‐1W‐1X where Q = diag (q1, ‐,n qp), qi>0, i = 1, ‐, p. In this paper, the minimax estimator of Berger&Bock (1976), given by δ (X, W) = [Ip‐ r(X, W) ¶ X ¶‐2wQ‐1W‐1] X, is shown to be minimax relative to the convex loss (δ ‐ μ)′[αQ + (1 ‐ α) Σ‐1] δ ‐ μ)/C, where C =α tr (Σ) + (1 ‐ α)p and 0 α 1, under certain condit

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01218.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummaryKhatri (1966) has derived a Wilks' s A test of a general linear hypothesis in the growth curve model. In this paper we give the direction and collinearity factors and their null distributions when the hypothesis is not true but the noncentrality matrix is of rank one. Interpretation of these tests and their usefulness in discrimination in growth curve models are discussed.

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01219.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummaryThe two populations considered for this study are two distinct time points. Samples consist of observations made at both the time points on every sampling unit. The unit to be classified is observed at one of the two time points. The observation vectors contain covariates, having same expectation at both the time points. In this set‐up admissibility of some likelihood ratio rules is establishe

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01220.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY

摘要:

SummaryUsing the marginal likelihood based on the signed ranks derived from matched pairs data, inferences are made for regression parameters. Both members of a given pair are subject to the same censoring time, while different pairs are subject to different censoring times. Censoring is independent of the response and on the right. Easily calculated logistic density scores are used to provide an approximate analysis so that inferences can be made about a regression parameter in the presence of a difference within the matched pairs. Inference for the survival times of matched skin grafts is considered.

ISSN:0004-9581    

DOI:10.1111/j.1467-842X.1983.tb01221.x

出版商:Blackwell Publishing Ltd    

年代:1983

数据来源: WILEY