Titlebook: Robust and Nonlinear Time Series Analysis; Proceedings of a Wor Jürgen Franke,Wolfgang H?rdle,Douglas Martin Conference proceedings 1984 Sp

Granular

Bmd955

The Problem of Unsuspected Serial Correlations,ations of the occurring phenomena are cited together with the first attempts to model them with the aid of self-similar processes. Various empirical features of a chemical measurement series given by Student are analysed in detail. A method for estimation and testing of the correlation parameter of

Angiogenesis

The Estimation of ARMA Processes, of the theory necessary for the validation of the method. The first stage of the method involves the fitting of an autoregression, of order h. determined by a criterion such as AIC. The asymptotic theory depends on the behaviour of . where ε?(t) is the residual from the autoregression and ε(t) is t

公司

How to determine the bandwidth of some nonlinear smoothers in practice, is familiar in the theory of M-estimators. The bandwidth of the kernel is chosen by a “crossvalidatory” device and asymptotic optimality properties are proven. The proposed method is compared with AIC and FPE and shown to be asymptotically equivalent. An application to Raman-Spectra and a Monte Car

RALES

Remarks on Nongaussian Linear Processes with Additive Gaussian Noise, and deconvolution were dealt with. We give the assumptions here. Let {v.} be a sequence of independent, identically distributed random var-iables with E v ≡ 0, E v. ≡ 1 and some higher order cumulant γ. ≠ 0 (s > 2). The real coefficients {α.} are in ?...

放大

Gross-Error Sensitivies of GM and RA-Estimates,ity (GESH) is the supremum of the norm of Hampel’s influence curve (ICH) with respect to an argument which represents an observation, or contamination, whose influence is being assessed. The GESH is a measure of the asymptotic bias caused by a vanishingly small fraction of contamination. This interp

gene-therapy

Some Aspects of Qualitative Robustness in Time Series,breakdown point and the sensitivity of robust operations are defined accordingly. Finally, saddle-point game theoretic formalizations are presented, that are consistent with the theory of qualitative robustness, and a class of robust operations is briefly discussed.

書法

MAUVE

Robust Nonparametric Autoregression,n estimation, and related methods, have been adapted by a number of authors to nonparametric estimation and prediction for time series. Indeed, Watson (1964) applied his estimator to some time series data, and Roussas (1969), Bosq (1980), Doukhan and Ghindes (1980), Pham Dinh Tuan (1981), Robinson (

潔凈

Robust Regression by Means of S-Estimators,mate autoregressive parameters in a robust way, and secondly, one sometimes has to fit a linear or nonlinear trend to a time series. In this paper we shall develop a class of methods for robust regression, and briefly comment on their use in time series. These new estimators are introduced because o