Adaptive learning forecasting,with applications in forecasting agricultural prices

We introduce a new forecasting methodology, referred to as adaptive learning forecasting, that allows for both forecast averaging and forecast error learning. We analyze its theoretical properties and demonstrate that it provides a priori MSE improvements under certain conditions. The learning rate based on past forecast errors is shown to be non-linear. This methodology is of wide applicability and can provide MSE improvements even for the simplest benchmark models. We illustrate the method’s application using data on agricultural prices for several agricultural products, as well as on real GDP growth for several of the corresponding countries. The time series of agricultural prices are short and show an irregular cyclicality that can be linked to economic performance and productivity, and we consider a variety of forecasting models, both univariate and bivariate, that are linked to output and productivity. Our results support both the efficacy of the new method and the forecastability of agricultural prices.     

TACKLING FALSE POSITIVES IN BUSINESS RESEARCH: A STATISTICAL TOOLBOX WITH APPLICATIONS

Serious concerns have been raised that false positive findings are widespread in empirical research in business disciplines. This is largely because researchers almost exclusively adopt the ‘p‐value less than 0.05’ criterion for statistical significance; and they are often not fully aware of large‐sample biases which can potentially mislead their research outcomes. This paper proposes that a statistical toolbox (rather than a single hammer) be used in empirical research, which offers researchers a range of statistical instruments, including a range of alternatives to the p‐value criterion such as the Bayesian methods, optimal significance level, sample size selection, equivalence testing and exploratory data analyses. It is found that the positive results obtained under the p‐value criterion cannot stand, when the toolbox is applied to three notable studies in finance.     

Incorporating the effect of urbanization in measuring climate adaptive capacity

Measuring the ability of a community to face climatic changes, or its adaptive capacity, is necessary in order to plan and guide development as the global climate continues to warm. One factor that has not been thoroughly addressed by previous attempts at measuring adaptive capacity is urbanization. This study looks to measure adaptive capacity in relation to urbanization, as many areas of the world are undergoing this rapid transition. An indicator system was created with land-use sensitive measures and applied to three different land use projection scenarios (A, BAU, and B − high, medium, and low growth, respectively) to 2030 and 2050 for two case study areas, Tamsui, Taiwan and West Palm Beach, USA. In Tamsui, the adaptive capacity decreased in all scenarios, but most dramatically for the high growth scenario. The low growth scenario decreased more slowly through each time slice. For West Palm Beach, the high growth scenario had the highest score in 2030, but declined in 2050. The medium growth Scenario BAU, also had a higher adaptive capacity score in 2030 than in 2050. The low growth Scenario B had a score that improved less dramatically but continued to rise through 2050. Scenario A would be ideal for short term gains, but its benefits would plateau in the long term. Scenario B, with conservation measures and more restricted growth would be the most ideal alternative. This study shows that urbanization has short term socioeconomic gains, but long term environmental consequences. The results also successfully incorporates the effect of land use change into an adaptive capacity indicator system, and can be applied in other localities expecting significant increases in urbanization.     

Asset pricing with expectation shocks

This paper adds persistent shocks into the adaptive learning expectation formation process in stochastic growth asset pricing production and endowment economies. These expectation shocks, designed to capture psychological elements which can arise from news, changes in sentiment, herding and bandwagon effects, generate waves of optimism and pessimism in equity price forecasts. The paper estimates parameters of the expectation shock and adaptive learning process with the method of simulated moments, and compares simulation results to U.S. economic and financial market stylized facts. Numerical results for both the estimated production and endowment economies show that the expectation shock model matches several of the stylized facts better than does a model that assumes rational expectations or adaptive learning alone.     

Principles for integrated environmental management of military training areas

Military Training Areas (MTAs) cover an estimated 200–250 million hectares globally, occur in all major ecosystems, and are potentially significant conservation assets. In some jurisdictions, MTAs may be the largest terrestrial land use category that is owned and operated by a sovereign government. Despite this, MTAs are not recognised as either a conservation or environment protection resource. Further, no MTAs are managed for their environmental values, defined as aspects of the environment that are valued by society, nor is there any specific MTA management guidance that details how both the military training and environmental values of a MTA can be maintained.We conducted a desktop review of Australian and German MTA management documentation to determine whether they contained management principles that recognised both military training and environmental values. Management documentation from these two countries was chosen as they are considered to be among countries at the forefront of MTA management globally. Our review determined that both the Australian and German management regimes do not have specific management principles for these values. This is likely to be the case for the majority of MTAs globally.For the first time, we develop MTA management principles that integrate the management of both military training objectives and environmental values. Key to achieving this integration is an understanding of the intersection of the impacts of military training on the environment, and the known, or potential, environmental values of a particular training area.To assist with the implementation of the management principles, we developed a new conceptual framework for the management of MTAs. The framework contains two adaptive management loops. The first focuses on the management of environmental values of MTAs, the second targets the military training values of MTAs. These two management loops facilitate for the development of management practices that optimise MTA management for both military training and biodiversity conservation.     

Dynamic adaptive transport policies for handling deep uncertainty

Many long-term transport policy decisions are made by assuming that (1) the range of possible futures is known well enough to predict future changes to the transport system, (2) there is enough knowledge regarding the correct transport system model to estimate policy outcomes, and (3) there is enough knowledge regarding the importance stakeholders currently assign to the various outcomes or will assign in the future. However, for long-term transport policy decisions these assumptions can often not be made, since decision makers, analysts, and experts do not know or cannot agree on (1) how the future will develop, (2) the system models, and/or (3) the value system(s) to be used to rank alternative policies. This paper presents a ‘dynamic adaptive’ approach to policymaking for long-term transport policies that aims at overcoming the shortcomings of traditional approaches for handling deep uncertainty. It allows adaptations in time as knowledge is gathered. The approach is illustrated with dynamic adaptive policies for solving various long-term problems in the fields of road, rail, and air transport.     

Collaborative governance arrangements to deliver spatially coordinated agri-environmental management

Several studies show that agri-environment schemes (AES) are likely to be more effective if they are designed at the landscape scale. However, this requires spatial coordination of environmental management across multiple farm holdings and collaboration among governmental and other actors, including, possibly, groups of farmers. In this study we analyse alternative approaches to spatial coordination and collaboration. Through case studies from five EU member states in North West Europe we analysed collaborative governance arrangements, from the perspective of the distribution of governance tasks among collaborating actors and changes to these over time. Of these governance tasks, spatial coordination had our particular interest. The collaborative governance arrangements were shaped in various ways. In four out of five case studies a group of farmers had become involved in the performance of more governance tasks over time. In all cases a professional(ized) organisation (governmental organisation or a group of farmers) was responsible for spatial coordination, possibly due to the complexities inherent to a landscape approach. In relation to the change of schemes over time, we argue that adaptive collaborative governance, incorporating learning, monitoring and evaluation in the governance arrangements, is key to effective agri- environmental management.     

THE EVOLUTION OF STOCK MARKET EFFICIENCY OVER TIME: A SURVEY OF THE EMPIRICAL LITERATURE

Abstract This paper provides a systematic review of the weak‐form market efficiency literature that examines return predictability from past price changes, with an exclusive focus on the stock markets. Our survey shows that the bulk of the empirical studies examine whether the stock market under study is or is not weak‐form efficient in the absolute sense, assuming that the level of market efficiency remains unchanged throughout the estimation period. However, the possibility of time‐varying weak‐form market efficiency has received increasing attention in recent years. We categorize these emerging studies based on the research framework adopted, namely non‐overlapping sub‐period analysis, time‐varying parameter model and rolling estimation window. An encouraging development is that the documented empirical evidence of evolving stock return predictability can be rationalized within the framework of the adaptive markets hypothesis.     

Responding to climate and other change processes in complex contexts:: Challenges facing development of adaptive policy frameworks in the Ganga Basin

The Ganga Basin, one of the world's most densely populated and vulnerable regions, is also among the world's most dynamic hydrological systems. Rivers exiting the Himalaya deposit massive amounts of sediment in the plains and shift their courses regularly. The natural dynamics of this system have a direct impact on populations. On August 18th, 2008, for example, embankments on the Kosi River (a tributary to the Ganges), failed and the channel shifted by as much as 120 km (Sinha, 2008 [1]) displacing over sixty thousand people in Nepal and three and a half million in India. Transport and power systems disrupted across large areas. The embankment failure was not caused by an extreme event. Instead the breach represented a failure of interlinked physical and institutional infrastructure systems in an area characterized by complex social, political, and environmental relationships.Projected climate changes in the Ganga Basin are likely to greatly exacerbate vulnerability (Adaptation Study Team, 2008 [2]). While the Kosi breach had nothing to do with climate change, such events will increase if climatic variability, sediment transport, and extreme events increase. Understanding how populations can respond to the dynamic nature of rivers such as the Kosi is, as a result, essential to develop strategies for adapting to climatic change. Understanding is also essential at the policy level for building adaptive capacity. The challenge is to identify policy frameworks and their relationship to interlinked physical and institutional infrastructure combinations that create environments enabling adaptation within households, communities, and regions.This paper explores the challenges and opportunities facing the development of adaptive policy frameworks in the Ganga Basin. The characteristics of frameworks that are adaptive in themselves and enable adaptation along with their relationship to different types of interlinked institutional and infrastructure systems are explored first. Following this, the case of the Kosi embankment along with the projected impacts of climate change across the Ganga Basin is used to identify the key challenges and opportunities that are common in many regions. The paper concludes with specific observations on the development of adaptive policy frameworks for responding to climate change in complex developing country contexts.     

Simple agent-based dynamical system models for efficient financial markets: Theory and examples

We propose an agent-based framework, based on simple piecewise linear time-invariant continuous-time dynamical systems models, as a means for describing efficient financial markets. We show by examples that many of the common agent-specific trading strategies occurring in the academic literature, including chartists and fundamentalists of various kinds, can be described in the proposed framework. We present definitions for weak and strong market efficiency and provide necessary and sufficient conditions for them to hold. We present minimal examples of strongly and weakly efficient markets to show that these concepts are natural and easy to satisfy in agent-based models, and that the models can reproduce both statistical and behavioral stylized facts of real markets. We provide examples to demonstrate that the framework can be extended for agents with delays in information processing, as well as for agents with time-varying strategies and for nonlinear market impact functions. We also provide a counterexample to show that the proposed market efficiency concepts may require modification in generalizations for nonlinear trading strategies.