Forecasting Aggregated Vector ARMA Processes


Book Description

This study is concerned with forecasting time series variables and the impact of the level of aggregation on the efficiency of the forecasts. Since temporally and contemporaneously disaggregated data at various levels have become available for many countries, regions, and variables during the last decades the question which data and procedures to use for prediction has become increasingly important in recent years. This study aims at pointing out some of the problems involved and at pro viding some suggestions how to proceed in particular situations. Many of the results have been circulated as working papers, some have been published as journal articles, and some have been presented at conferences and in seminars. I express my gratitude to all those who have commented on parts of this study. They are too numerous to be listed here and many of them are anonymous referees and are therefore unknown to me. Some early results related to the present study are contained in my monograph "Prognose aggregierter Zeitreihen" (Lutkepohl (1986a)) which was essentially completed in 1983. The present study contains major extensions of that research and also summarizes the earlier results to the extent they are of interest in the context of this study.




Dynamic Modelling of Stochastic Demand for Manufacturing Employment


Book Description

In this book interrelated factor demand models are surveyed. New methods are developed and are analysed empirically using Dutch and U.K. time series data. New methods are discussed for obtaining closed form solutions of linear ratinal expectations models, providing deeper insights into the identification of structural parameters of underlying theoretical models; recently developed time series techniques are applied in order to estimate structural parameters and test for model specification, stationarity and stability through time; new models are developed in which the rather stringent and questionable restrictions of symmetry generally imposed upon stochastic adjustment models of labour demand are relaxed, the models are analysed empirically using time series data of Dutch and U.K. manufacturing production and nonproduction workers.




Methodology and Software for Interactive Decision Support


Book Description

These Proceedings report the scientific results of an International Workshop on Methodology and Software for Interactive Decision Support organized jointly by the System and Decision Sciences Program of the International Institute for Applied Sys tems Analysis (nASA, located in Laxenburg, Austria) and The National Committee for Applied Systems Analysis and Management in Bulgaria. Several other Bulgarian institutions sponsored the Workshop - The Committee for Science to the Council of Ministers, The State Committee for Research and Technology and The Bulgarian In dustrial Association. The workshop was held in Albena, on the Black Sea coast. More than 80 scientists from 15 countries attended the workshop; 50 lectures were presented and 17 computer demonstration sessions took place. This Workshop is one of a series of meetings organized by nASA with the collaboration of scientific institutions from the National Member Organization countries. The previous meetings took place in Austria (1983), Hungary (1984) and the German Democratic Republic (1985). All proceedings of these meetings have been published by Springer Verlag in the series Lecture Notes in Economics and Mathematical Systems.




Understanding Economic Behaviour


Book Description

may be related to another basic assumption in economic psychology: that the human capacity to process information from the environment is limited, and that the kind of optimal use of that information postulated in many economic theories is therefore not possible. The research methods used are mainly geared towards empirical research, and there mostly towards survey research and experimentation. Experimentation involves most often simulated behaviour in a laboratory, which allows the experimental manipulation of possible causes of behaviour which would not be possible in real life. Survey research is the most widely used instrument for investigating real-world behaviour, with all its caveats about establishing causal explanations. Several introductory books (e. g. , Fumham & Lewis, 1986; Lea, Tarpy, & Webley, 1987; van Raaij, van Veldhoven, & Wlimeryd, 1988) and articles (e. g. , van Raaij, 1979; Wiswede, 1988) have appeared recently, which try to give an overview of the field of economic psychology, and which, in varying degrees, demonstrate the three foundations of economic psychology just mentioned. Others have concentrated on certain subtopics, such as the psychology of the labour market (e. g. , Baxter, 1988; Pelzmann, 1986).




Unique Solutions for Strategic Games


Book Description

This book develops a general solution concept for strategic games which resolves strategic uncertainty completely. The concept is described by a mathematically formulated solution procedure and illustrated by applying it to many interesting examples. A long nontechnical introduction tries to survey and to discuss the more technical parts of the book. The book and especially the introduction provide firm and consistent guidance for scholars of game theory. There are many open problems which could inspire further research efforts.




Information Evaluation in Capital Markets


Book Description

An investor who wants to invest a certain amount and to whom a lot of more or less risky alternatives arise would divide this amount among several securities. He makes this portfolio decision because of his expectations with regard to these assets which result from the information available to him. If the investor obtains additional information, then his knowledge would improve and, therefore, the portfolio decision made by him. Accordingly, he will be ready to accept certain costs related to the information procurement. The value of information indicates the maximum tolerable information costs, and its knowledge, therefore, enables - by comparing with the actual information costs - to evaluate the profitability of an information procurement. In this book, the value of information for the problem of portfolio planning is explicitly determined, namely as well for the case of fixed prices not influenced by the information activity as within the scope of a market model. These explicit results allow several conclusions, in particular about the influence of preknowledge, risk aversion, information precision and information dissemination on their value. The Bayesian decision theory is the basis for this paper. Corres pondingly, a subjective concept of probability is underlying, and the information processing and evaluation is understood in a sta tistical sense. As one might expect, the question about the correct ness of an information is not treated, although manipulating the asset prices by deliberate dis information can be observed in prac tice and is, certainly, an interesting problem.