摘要:

This paper is devoted to a model for analysis and forecasting of vector time series and the corresponding procedure of Bayesian sequential estimation. This model can also be viewed as a multivariate extension of the (univariate) seasonal growth multiplicative model(Harrison, 1965; Migon, 1984). The basic structure of this multivariate model consists of a locally linear trend component for each individual series and a shared multiplicative seasonal component, common to all marginal series.The procedure of sequential estimation is based on analytic approximations to obtain a conjugate analysis and represents a nonlinear extension of the algorithm presented by Barbosa and Harrison (1992). Details of the proposed procedure and its practical implementation are shown, and two numerical examples are provided.

ISSN:0361-0918    

DOI:10.1080/03610919908813550

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

A common theme among the many existing multivariate statistical process monitoring (MSPM) methods is the recommendation that process knowledge be used to select a suitable monitoring procedure. Several methods possess the property of directional invariance, with shift detection performance depending only on the distance of a shift away from the target mean vector. This property is of special importance when characterizing a new process, or when available process knowledge suggests that shifts may occur in virtually any direction away from the target mean. In other cases, it is possible and may be desirable to increase a control scheme's sensitivity by using knowledge of the process structure and possible upset mechanisms to ‘aim’ the control procedure. This paper identifies a potentially common MSPM scenario and extends the idea of using process knowledge to determine an appropriate control statistic for assignable cause detection and identification.

ISSN:0361-0918    

DOI:10.1080/03610919908813551

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

A method to resample the nonlinear least squares (NLS) estimator of the parameters of a regression model, which is nonlinear in the frequency domain, is proposed. The method uses the Fourier transform to remove the serial correlation that is present in the time domain. If the regressor series have seasonal variation or nonzero mean this creates additional problems for the resampling. A simple way to avoid these problems is proposed. The method is shown to give bootstrap replicates of the estimator that asymptotically have a distribution close to the true sampling distribution of the estimator. The proposed method is applied to a regression model that relates the inner and outer temperatures of a slab of insulation material to the heat flow through the slab

ISSN:0361-0918    

DOI:10.1080/03610919908813552

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

This paper introduces an alternative variable selection method for use in regression analysis that is based on the Tabu search procedure. The Tabu search was compared to traditional regression analysis procedures using various size data sets. The results indicate the superiority of the Tabu search procedure for model selection in multiple regression analysis.

ISSN:0361-0918    

DOI:10.1080/03610919908813553

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

When fitting a response surface model, the least squares estimates of the model's parameters will generally depend on how the response surface design is blocked. Then, the choice of a blocking arrangement for a response surface design can have a considerable effect on estimating the mean response, on the size of the prediction variance and on the variance of the least squares estimator of the model's parameters. These are all shown to be affected by the sizes of the blocks and the allocation of experimental runs to the blocks. In this paper, we propose a graphical method for evaluating the effect of blocking in response surface designs. This graphical method can be used to examine how blocking influences the variance of the least squares estimator of the model's parameters. and to compare the effect of blocking in the cases of the orthogonal and nonorthogonal block designs, respectively

ISSN:0361-0918    

DOI:10.1080/03610919908813554

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

In quality control the out‐of‐control detection problem is often one‐sided in the sense that quality decreases as one or more quality characteristics increase. Similarly in environmental monitoring the quality assessment is essentially one‐sided. Multivariate control charts like Hotelling's T2or Lowry's quadratic MEW MA are based on direction invariance. For the one‐sided multivariate problem I propose a new detector based on the restrictedMLEapplied to the MEW MA transform.

ISSN:0361-0918    

DOI:10.1080/03610919908813555

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

A covariance matrix structure that generalizes the single scale covariance matrix usually used in multinomial responses with extraneous variation is presented. The proposed covariance matrix allows for various levels of extraneous variation, and might be useful in modeling either extra variation or under dispersion. An explicit representation of the proposed covariance matrix, as well as a meaningful interpretation in terms of regression ideas, are provided. An example is presented for illustration

ISSN:0361-0918    

DOI:10.1080/03610919908813556

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

Sample size requirements that achieve a prespecified expected width or lower limit for a confidence interval about the intraclass kappa statistic are supplied for the case of two raters and a dichotomous outcome measure. These results should be useful in the planning stages of an interobserver agreement study in which the focus is on estimation rather than hypothesis‐testing. In order to quantify the loss of precision obtained when choosing a dichotomous trait for this purpose, corresponding results are also provided for the case of a continuous outcome measure

ISSN:0361-0918    

DOI:10.1080/03610919908813557

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

In this article we revisit the problem of pretest estimation for some discrete distributions, when a prior point estimate of an unknown parameter is available A general formula for bias and mean square error of a pretest estimator is derived for a class of discrete distributions. This leads to a refinement of results reported by Kumar et al. (1992), in which the expressions for the bias and mse appear to be incorrect Efficiency of the proposed estimator is plotted for Poisson and Binomial distributions. Based on the efficiency curves, optimum level of significance for the preliminary test is suggested.

ISSN:0361-0918    

DOI:10.1080/03610919908813558

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor

摘要:

This paper concerns the problem of estimating normalizing constants for multivariate densities. We first compare the well known technique of Importance Sampling (IS) with another technique that we call Importance Weighting (IW), which has been recently proposed by Gelfand and Dey (1994). Both techniques require the choice of a suitable density. Whereas it is quite well known that the asymptotic variance of an IS estimator is proportional to the chi‐square divergence of the IS density w.r.t. the density of interest, we point out that for the asymptotic variance of the corresponding IW estimator the same results holds, except that the arguments of the divergence are interchanged. This suggests how to adapt to the problem of choosing an IW density procedures which have been already proposed for the choice of the IS density. In particular we show this feature for the algorithms proposed by Geweke (1989) and West (1993). The resulting procedures are illustrated with some examples.

ISSN:0361-0918    

DOI:10.1080/03610919908813559

出版商:Marcel Dekker, Inc.    

年代:1999

数据来源: Taylor