Functional Modelling and Classification of Longitudinal Data*

Abstract. We review and extend some statistical tools that have proved useful for analysing functional data. Functional data analysis primarily is designed for the analysis of random trajectories and infinite‐dimensional data, and there exists a need for the development of adequate statistical estimation and inference techniques. While this field is in flux, some methods have proven useful. These include warping methods, functional principal component analysis, and conditioning under Gaussian assumptions for the case of sparse data. The latter is a recent development that may provide a bridge between functional and more classical longitudinal data analysis. Besides presenting a brief review of functional principal components and functional regression, we develop some concepts for estimating functional principal component scores in the sparse situation. An extension of the so‐called generalized functional linear model to the case of sparse longitudinal predictors is proposed. This extension includes functional binary regression models for longitudinal data and is illustrated with data on primary biliary cirrhosis.     

Creating a Crisis:German Mass Media andOil Supply in 1973-74

In the winter of 1973-74, the German Federal Republic importedmore oil than in any other year before or since. Nevertheless,the mass media were warning that an energy crisis might occur.Thereupon the population became nervous andbought more crudeoil products than ever before. As a consequence, short-termdifficulties of supply from industrial producers seemed to confirmthe warnings.     

Critical values for unit root tests in seasonal time series

SUMMARY In this paper, we present tables with critical values for a variety of tests for seasonal and non-seasonal unit roots in seasonal time series. We consider (extensions of) the Hylleberg et al. and Osborn et al. test procedures. These extensions concern time series with increasing seasonal variation and time series with structural breaks in the seasonal means. For each case, we give the appropriate auxiliary test regression, the test statistics, and the corresponding critical values for a selected set of sample sizes. We also illustrate the practical use of the auxiliary regressions for quarterly new car sales in the Netherlands. Supplementary to this paper, we provide Gauss programs with which one can generate critical values for particular seasonal frequencies and sample sizes.     

CHANGE VERSUS CONTINUITY IN WEST GERMAN PUBLIC ATTITUDES ON NATIONAL SECURITY AND NUCLEAR WEAPONS IN THE EARLY 1980s

This article first describes trends of a few key data on publicopinion on national security in West Germany since 1970, andthen examines in some detail the development and structure ofpublic attitudes on NATO's double-track decision and its implementationin the early 1980s. It addresses the problems of measuring suchattitudes and interpreting relevant public opinion data in thelight of levels of public awareness and of the personal importanceof these matters for respondents. In that context, the resultsof some methodological experiments to ascertain the impact ofquestion formats and wordings on response distributions fordefense policy survey items are also presented. Generationalreplacement and partisan polarization hypotheses to accountfor the dynamics of these attitudes are compared. The main findinghere is that growing dissent among the major parties over missiledeployment has played a much greater role in realigning publicopinion than has the coming of age of a predominantly antinuclearand antidefense "successor generation."     

共识社群——简论中国乡村中的国家构造与地方社会

This article deals with the delicate relationship between vernacular practices and offi-cial discourse in rural China .In regards to geo-mancy (fengshui), rituals, gifting, and corruption discourse , f...     

Models,methods and tools for interorganizational logistics operations

Enterprise modelling is today one of the key techniques to improve the performances of an enterprise. This paper first defines enterprise modelling techniques as compared to BPR techniques. Then the latest developments in GRAI methodology are presented. Finally, examples of industrial applications are presented for three methods: GIM (GRAI Integrated Method) for re-engineering, GIMSOFT for the choice of an ERP software package and ECOGRAI for the design and implementation of performance indicator system.     

挪威统计局的系统质量工程

一、引言挪威统计局多年来一直致力于改善统计数据质量。过去传统的做法集中在数据的最后把关上,如避免数据报表和出版的错误,以及改善抽样误差估计值的准确性。为此我们的质量概念变得越来越广泛。十年前的数据主要是满足计划和研究用户的需求。但过去的十年,我们已经逐步改变     

Dynamic Prediction by Landmarking in Event History Analysis

Abstract.  This article advocates the landmarking approach that dynamically adjusts predictive models for survival data during the follow up. This updating is achieved by directly fitting models for the individuals still at risk at the landmark point. Using this approach, simple proportional hazards models are able to catch the development over time for models with time-varying effects of covariates or data with time-dependent covariates (biomarkers). To smooth the effect of the landmarking, sequences of models are considered with parametric effects of the landmark time point and fitted by maximizing appropriate pseudo log-likelihoods that extend the partial log-likelihood to cover the landmarking approach.     

LONG-RUN EQUILIBRIUM IN THE EMPIRICAL STUDY OF MONOPOLY AND COMPETITION

A long-run tendency of industry profit rate to converge to a single competitive level has been a fundamental tenet of the industrial organization approach to the study of competitiveness in a market economy. This paper shows that for the post World War II period a weak equalization can be econometrically identified with different reaction speeds by industry. However, persistent profit rate differences endure. Finally, a portfolio theory of risk is considered as an explanation of these differentials.     

GOVERNMENT DEBT‐THRESHOLD CONTRACTS

Politicians tend to push the amount of public debt beyond socially desirable levels in order to increase their reelection chances. We develop a model that provides a new explanation for this behavior: office holders undertake debt‐financed public projects, but postpone the timing of part of the output to the next term. This makes it difficult to replace them. As a consequence, the office holders' reelection chances rise—as does public debt. As a potential remedy for this inefficiency, we allow candidates for public office to offer government debt‐threshold contracts. Such a contract contains an upper limit for government debt and the sanction that an office holder violating this limit cannot stand for reelection. We show that such competitively offered contracts contain low debt levels that limit debt financing and improve the citizens' welfare. When negative macroeconomic events occur, government debt‐threshold contracts may be violated, and the economy is stabilized. (JEL: D7, D82, H4)