Notes on forecasting a chaotic series using regression

It is well known that a nonlinear recursive equation can produce a chaotic sequence at certain values of the parameter. Furthermore, in the chaotic regime, extremely small changes in the initial value or in the value of the parameter produce very large changes in the sequence. It is surprising therefore that a short segment of a chaotic sequence can be used to reconstruct large portions of the sequence and to forecast future values of the sequence over short ranges. Furthermore, while the accuracy of the forecasts is dependent on the precision of the data, the relationship is much less sensitive than might have been expected. This is demonstrated by fitting a two-parameter model to two different types of chaotic equations: one a polynomial and the other a trigonometric function. This leads to the expectation that under certain circumstances, it may be possible to forecast values in a chaotic series over limited ranges, even if initial data are somewhat degraded.     

Future S&T management policy issues—2025 global scenarios

This article presents four scenarios depicting science and technology (S&T) management dilemmas of the next two decades. The scenarios concern the balance between risk and promise, between the need to steer the directions of S&T, to minimize risk, and the need to maintain a free and unconstrained S&T agenda. These scenarios were constructed in the third year of the Millennium Project's study of this topic. The scenarios were formed in an interactive process with the project's international participants. The key policies that were found to be useful in all of the scenarios include (1) when considering the possibility of the misuse of weapons of mass destruction by terrorists, include the possibility of misuse by a single individual, acting alone; (2) establish mechanisms and techniques for making possible the explicit unintended consequences of scientific research and technology, including malicious uses; (3) for desirable technologies, where it may not be possible to avoid significant risks, develop mitigation strategies in parallel; (4) teach science ethics.     

Short-Run Output Response in the Western Canadian Cattle Industry

This paper present the results of recent empirical work on the short-run producetion flexibility of cow-calf producers in Western Canada. Several aspects of firm behaviour may be inferred from the econometric estimates, including short-run elasticities of supply and factor demand, and the total elasticity of cattle supply. The principal empirical findings are that many of the shourt-run supply and factor demand responses of firms, are elastic with respect to within-season price variability. The evidence does not support a vertical or negatively-sloped short-run supply curve for cattle, where one previously has been hypothesized in the theoretical literature.     

An empirical investigation of the sustainability of the public deficit in Portugal

In this paper, we investigate Portuguese government expenditures and revenues as an example for a long time series. Our hypothesis states that there may be periods when the deficit is sustainable and those when it is not. Usually, after a period of unsustainable deficits, a new regime takes over. These regime shifts call for an approach that takes into account a non-constant structure of the underlying data generating process. Consequently, we use different tests which we set up in a time-varying framework. We apply and compare the results of the Trace test, Breitung’s non-parametric test and the Bohn test. We identify several break points and find that the Trace test performs worst in this case while Breitung’s test and the Bohn test give similar results. Comparing the results with history, we find that the last two tests best reflect what happened historically.     

R&D Reporting Biases and Their Consequences*

The immediate expensing of research and development (R&D) expenditures is often justified by the conservatism principle. However, no accounting procedure consistently applied can be conservative throughout the firm's life. We therefore ask the following questions: (1) When is the expensing of R&D conservative and when is it aggressive, relative to R&D capitaliza‐tion? (2) What are the capital‐market implications of these reporting biases? To address these questions we construct a model of profitability biases (differences between reported profitability under R&D expensing and capitalization) and show that the key drivers of the reporting biases are the differences between R&D growth and earnings growth (momentum), and between R&D growth and return on equity (ROE). Companies with a high R&D growth rate relative to their profitability (typically early life‐cycle companies) report conservatively, while firms with a low R&D growth rate (mature companies) tend to report aggressively under current generally accepted accounting principles. Our empirical analysis, covering the period 1972‐2003, generally supports the analytical predictions. In the valuation analysis we find evidence consistent with investor fixation on the reported profitability measures: we detect undervaluation of conservatively reporting firms and overvaluation of aggressively reporting firms. These misvaluations appear to be corrected when the reporting biases reverse from conservative to aggressive and vice versa. This evidence is consistent with behavioral finance arguments about investor cognitive biases.     

The Relation Between Investor Uncertainty and Market Reactions to Earnings Announcements: Evidence from the Property‐Casualty Insurance Industry in the USA

Abstract:   This paper investigates the relationship between investor uncertainty, gauged by properties of analysts' forecasts, and the stock market response to earnings. We find that uncertainty is best characterized by a comprehensive measure recently proposed by Barron, Kim, Lim and Stevens (1998) , BKLS. The BKLS measure is related to uncertainty‐inducing events, as well as factors that affect the difficulty faced by analysts in forecasting earnings. We conclude that, first, pre‐disclosure uncertainty is a significant determinant of the price reaction to the earnings release, and second, BKLS is a more comprehensive measure of uncertainty than simple dispersion.     

National Vacancy Rates and the Persistence of Shocks in U.S. Office Markets

In this paper, we develop and estimate a model that decomposes the variance in office vacancy rates into market-specific, time-specific, and random components. The results indicate significant differences in natural vacancy rates across markets. We also find some persistence in deviations from these natural vacancy rates. The analysis is applied to both central business district (CBD) and suburban office markets. We find that natural vacancy rates differ across CBD markets and across suburban markets. Further, the persistence of disequilibrium in one CBD market seems to differ significantly from that in another. This is not shown to be true for suburban markets.     

EVIDENCE OF SHIFTS IN PORTFOLIO ASSET COMPOSITION AS A MARKET TIMING TOOL

Previous research has investigated portfolio timing success by analyzing possible shifts in the beta of professionally managed portfolios. The methodology used by these studies usually involves calculating the betas of portfolios under varing market conditions using ex post holding period yields. Since a portfolio's beta can shift for reasons other than timing efforts, the results and interpretation of this type of analysis are limited. This paper takes a more direct approach to the analysis of timing by analyzing shifts in the asset composition of professionally managed portfolios. The asset composition is first analyzed to determine if portfolio managers are attempting to adjust risk exposure. Any shifts that are identified are compared to the market conditions that existed subsequent to the shift to determine if the shift was appropriate in terms of correct timing.