Linear combination of restrictions and forecasts in time series analysis

An important tool in time series analysis is that of combining information in an optimal way. Here we establish a basic combining rule of linear predictors and show that such problems as forecast updating, missing value estimation, restricted forecasting with binding constraints, analysis of outliers and temporal disaggregation can be viewed as problems of optimal linear combination of restrictions and forecasts. A compatibility test statistic is also provided as a companion tool to check that the linear restrictions are compatible with the forecasts generated from the historical data. Copyright © 2000 John Wiley & Sons, Ltd.     

Causal forces: Structuring knowledge for time-series extrapolation

This paper examines a strategy for structuring one type of domain knowledge for use in extrapolation. It does so by representing information about causality and using this domain knowledge to select and combine forecasts. We use five categories to express causal impacts upon trends: growth, decay, supporting, opposing, and regressing. An identification of causal forces aided in the determination of weights for combining extrapolation forecasts. These weights improved average ex ante forecast accuracy when tested on 104 annual economic and demographic time series. Gains in accuracy were greatest when (1) the causal forces were clearly specified and (2) stronger causal effects were expected, as in longer-range forecasts. One rule suggested by this analysis was: ‘Do not extrapolate trends if they are contrary to causal forces.’ We tested this rule by comparing forecasts from a method that implicitly assumes supporting trends (Holt's exponential smoothing) with forecasts from the random walk. Use of the rule improved accuracy for 20 series where the trends were contrary; the MdAPE (Median Absolute Percentage Error) was 18% less for the random walk on 20 one-year ahead forecasts and 40% less for 20 six-year-ahead forecasts. We then applied the rule to four other data sets. Here, the MdAPE for the random walk forecasts was 17% less than Holt's error for 943 short-range forecasts and 43% less for 723 long-range forecasts. Our study suggests that the causal assumptions implicit in traditional extrapolation methods are inappropriate for many applications.     

The use of encompassing tests for forecast combinations

This paper proposes an algorithm that uses forecast encompassing tests for combining forecasts when there are a large number of forecasts that might enter the combination. The algorithm excludes a forecast from the combination if it is encompassed by another forecast. To assess the usefulness of this approach, an extensive empirical analysis is undertaken using a US macroeconomic dataset. The results are encouraging; the algorithm forecasts outperform benchmark model forecasts, in a mean square error (MSE) sense, in a majority of cases. The paper also compares the empirical performance of different approaches to forecast combination, and provides a rule‐of‐thumb cut‐off point for the thick‐modeling approach. Copyright © 2009 John Wiley & Sons, Ltd.     

Against the empirical viability of the Deutsch–Wallace–Everett approach to quantum mechanics

The subjective Everettian approach to quantum mechanics presented by Deutsch and Wallace fails to constitute an empirically viable theory of quantum phenomena. The decision theoretic implementation of the Born rule realized in this approach provides no basis for rejecting Everettian quantum mechanics in the face of empirical data that contradicts the Born rule. The approach of Greaves and Myrvold, which provides a subjective implementation of the Born rule as well but derives it from empirical data rather than decision theoretic arguments, avoids the problem faced by Deutsch and Wallace and is empirically viable. However, there is good reason to cast doubts on its scientific value.     

The modal-Hamiltonian interpretation and the Galilean covariance of quantum mechanics

The aim of this paper is to analyze the modal-Hamiltonian interpretation of quantum mechanics in the light of the Galilean group. In particular, it is shown that the rule of definite-value assignment proposed by that interpretation has the same properties of Galilean covariance and invariance as the Schrödinger equation. Moreover, it is argued that, when the Schrödinger equation is invariant, the rule can be reformulated in an explicitly invariant form in terms of the Casimir operators of the Galilean group. Finally, the possibility of extrapolating the rule to quantum field theory is considered.     

Collinearity and the use of latent root regression for combining GNP forecasts

In combining economic forecasts a problem often faced is that the individual forecasts display some degree of dependence. We discuss latent root regression for combining collinear GNP forecasts. Our results indicate that latent root regression produces more efficient combining weight estimates (regression parameter estimates) than ordinary least squares estimation (OLS), although out-of-sample forecasting performance is comparable to OLS.     

Quantum probability from subjective likelihood: Improving on Deutsch's proof of the probability rule

I present a proof of the quantum probability rule from decision-theoretic assumptions, in the context of the Everett interpretation. The basic ideas behind the proof are those presented in Deutsch's recent proof of the probability rule, but the proof is simpler and proceeds from weaker decision-theoretic assumptions. This makes it easier to discuss the conceptual ideas involved in the proof, and to show that they are defensible.     

Everett and the Born rule

During the last 10 years or so, derivations of the Born rule based on decision theory have been proposed and developed, and it is claimed that these are valid in the context of the Everett interpretation. This claim is critically assessed and it is shown that one of its key assumptions is a natural consequence of the principles underlying the Copenhagen interpretation, but constitutes a major additional postulate in an Everettian context. It is further argued that the Born rule, in common with any interpretation that relates outcome likelihood to the expansion coefficients connecting the wavefunction with the eigenfunctions of the measurement operator, is incompatible with the purely unitary evolution assumed in the Everett interpretation.     

Invaders,weeds and the risk from genetically manipulated organisms

Invaders, weeds and colonizers comprise different but overlapping sets of species. The probability of successful invasion is low. The 10:10 rule state that 10% of introduced speices (those with feral individuals) become established, 10% of established species (those with self-sustaining populations) become pests. The rule gives an adequate fit to British plant data. The rule predicts that invaders will be rarer than natives. This is shown for British Anatidae. There is a continuous spectrum of perceived weediness. Although this spectrum is significantly related to Baker characters, neither those characters or any others can usefully predict which species will be weeds over a wide range of species. Characters tuned to sets of closely related species shown more promise. A study of BritishImpatiens shows that the characters responsible for critical ecological behaviour are still obscure. Small genetic changes can cause large ecological changes. GMOs will have characters entirely new to that species' evolutionary history. While most will have little ecological effect, a few may be ecologically and economically damaging. A sensible programme of field trials and monitoring is justified to minimize the risk.     

In defence of the self-location uncertainty account of probability in the many-worlds interpretation

We defend the many-worlds interpretation of quantum mechanics (MWI) against the objection that it cannot explain why measurement outcomes are predicted by the Born probability rule. We understand quantum probabilities in terms of an observer's self-location probabilities. We formulate a probability postulate for the MWI: the probability of self-location in a world with a given set of outcomes is the absolute square of that world's amplitude. We provide a proof of this postulate, which assumes the quantum formalism and two principles concerning symmetry and locality. We also show how a structurally similar proof of the Born rule is available for collapse theories. We conclude by comparing our account to the recent account offered by Sebens and Carroll.     

Evaluating the predictive accuracy of volatility models

Standard statistical loss functions, such as mean‐squared error, are commonly used for evaluating financial volatility forecasts. In this paper, an alternative evaluation framework, based on probability scoring rules that can be more closely tailored to a forecast user's decision problem, is proposed. According to the decision at hand, the user specifies the economic events to be forecast, the scoring rule with which to evaluate these probability forecasts, and the subsets of the forecasts of particular interest. The volatility forecasts from a model are then transformed into probability forecasts of the relevant events and evaluated using the selected scoring rule and calibration tests. An empirical example using exchange rate data illustrates the framework and confirms that the choice of loss function directly affects the forecast evaluation results. Copyright © 2001 John Wiley & Sons, Ltd.     

乘波布局高超声速飞行器纵向静稳定特性分析

高超声速滑翔飞行器稳定性设计方法的研究具有重要应用价值.乘波体构型滑翔飞行器由于没有平尾且飞行在高空、高超声速条件下,其纵向静稳定特性与常规飞机有很大不同,对此传统飞行力学并无相应设计依据.在相切锥乘波体理论基础上,本文建立了计及流向一阶导数和二阶导数的微元计算模型,结合牛顿法、活塞理论、切楔/切锥法的理论推导与CFD数值计算,研究了典型二维剖面在高超声速、宽攻角范围下的纵向静稳定特性,从理论角度证明了沿流向＂下凸＂的流线特征有利于保证纵向静稳定,而＂上凹＂形状特征不利于纵向静稳定,该结论通过二维和三维算例得到了验证.以上述分析为基础,解释了基于锥型流的乘波体难以满足纵向静稳定性的物理原因,以及俯仰配平舵面可能对纵向静稳定性带来的影响,并提出了相应解决方案.进一步分析表明该结论适用于宽马赫数和宽高度范围,且黏性作用并不改变上述规律,相关结论可作为高超声速滑翔飞行器气动设计的参考.     

Linear constraints and the efficiency of combined forecasts

Studies of combined forecasts have typically constrained the combining weights to sum to one and have not included a constant term in the combination. In a recent paper, Granger and Ramanathan (1984) have argued in favour of an unrestricted linear combination, including a constant term. This paper shows that for the purpose of prediction it may make sense to impose restrictions on the combining model because of potential increases in forecasting efficiency. Empirical results show that small gains in forecasting efficiency can be obtained by restricting the linear combination of GNP forecasts from four econometric models.     

The ecological rationality of explanatory reasoning

There is growing evidence that explanatory considerations influence how people change their degrees of belief in light of new information. Recent studies indicate that this influence is systematic and may result from people’s following a probabilistic update rule. While formally very similar to Bayes’ rule, the rule or rules people appear to follow are different from, and inconsistent with, that better-known update rule. This raises the question of the normative status of those updating procedures. Is the role explanation plays in people’s updating their degrees of belief a bias? Or are people right to update on the basis of explanatory considerations, in that this offers benefits that could not be had otherwise? Various philosophers have argued that any reasoning at deviance with Bayesian principles is to be rejected, and so explanatory reasoning, insofar as it deviates from Bayes’ rule, can only be fallacious. We challenge this claim by showing how the kind of explanation-based update rules to which people seem to adhere make it easier to strike the best balance between being fast learners and being accurate learners. Borrowing from the literature on ecological rationality, we argue that what counts as the best balance is intrinsically context-sensitive, and that a main advantage of explanatory update rules is that, unlike Bayes’ rule, they have an adjustable parameter which can be fine-tuned per context. The main methodology to be used is agent-based optimization, which also allows us to take an evolutionary perspective on explanatory reasoning.     

Neural map formation in the mouse olfactory system

In the mouse olfactory system, odorants are detected by ~1,000 different odorant receptors (ORs) produced by olfactory sensory neurons (OSNs). Each OSN expresses only one functional OR species, which is referred to as the “one neuron–one receptor” rule. Furthermore, OSN axons bearing the same OR converge to a specific projection site in the olfactory bulb (OB) forming a glomerular structure, i.e., the “one glomerulus–one receptor” rule. Based on these basic rules, binding signals of odorants detected by OSNs are converted to topographic information of activated glomeruli in the OB. During development, the glomerular map is formed by the combination of two genetically programmed processes: one is OR-independent projection along the dorsal–ventral axis, and the other is OR-dependent projection along the anterior-posterior axis. The map is further refined in an activity-dependent manner during the neonatal period. Here, we summarize recent progress of neural map formation in the mouse olfactory system.     

Forecasting and trading strategies based on a price trend model

In this paper, we consider the price trend model in which it is assumed that the time series of a security's prices contain a stochastic trend component which remains constant on each of a sequence of time intervals, with each interval having random duration. A quasi‐maximum likelihood method is used to estimate the model parameters. Optimal one‐step‐ahead forecasts of returns are derived. The trading rule based on these forecasts is constructed and is found to bear similarity to a popular trading rule based on moving averages. When applying the methods to forecast the returns of the Hang Seng Index Futures in Hong Kong, we find that the performance of the newly developed trading rule is satisfactory. Copyright © 2000 John Wiley & Sons, Ltd.     

From protein sequences to 3D-structures and beyond: the example of the UniProt Knowledgebase

With the dramatic increase in the volume of experimental results in every domain of life sciences, assembling pertinent data and combining information from different fields has become a challenge. Information is dispersed over numerous specialized databases and is presented in many different formats. Rapid access to experiment-based information about well-characterized proteins helps predict the function of uncharacterized proteins identified by large-scale sequencing. In this context, universal knowledgebases play essential roles in providing access to data from complementary types of experiments and serving as hubs with cross-references to many specialized databases. This review outlines how the value of experimental data is optimized by combining high-quality protein sequences with complementary experimental results, including information derived from protein 3D-structures, using as an example the UniProt knowledgebase (UniProtKB) and the tools and links provided on its website (). It also evokes precautions that are necessary for successful predictions and extrapolations.     

Combining ordinal forecasts with an application in a financial market

The literature on combining forecasts has almost exclusively focused on combining point forecasts. The issues and methods of combining ordinal forecasts have not yet been fully explored, even though ordinal forecasting has many practical applications in business and social research. In this paper, we consider the case of forecasting the movement of the stock market which has three possible states (bullish, bearish and sluggish). Given the sample of states predicted by different forecasters, several statistical and operation research methods can be applied to determine the optimal weight assigned to each forecaster in combining the ordinal forecasts. The performance of these methods is examined using Hong Kong stock market forecasting data, and their accuracies are found to be better than the consensus method and individual forecasts.     

Priority and privilege in scientific discovery

The priority rule in science has been interpreted as a behavior regulator for the scientific community, which benefits society by adequately structuring the distribution of intellectual labor across pre-existing research programs. Further, it has been lauded as an intuitively fair way to reward scientists for their contributions, as a special case of society’s “grand reward scheme”. However, we will argue that the current formal framework utilized to model the priority rule idealizes away important aspects of credit attribution, and does so in a way that impacts the conclusions drawn regarding its function in scientific communities. In particular, we consider the social dynamics of credit attribution in order to show that the priority rule can foster structural disadvantages in socially diverse science, as well as drive the distribution of intellectual labor away from optimal.     

Stock market volatility and the forecasting performance of stock index futures

This study attempts to apply the general equilibrium model of stock index futures with both stochastic market volatility and stochastic interest rates to the TAIFEX and the SGX Taiwan stock index futures data, and compares the predictive power of the cost of carry and the general equilibrium models. This study also represents the first attempt to investigate which of the five volatility estimators can enhance the forecasting performance of the general equilibrium model. Additionally, the impact of the up‐tick rule and other various explanatory factors on mispricing is also tested using a regression framework. Overall, the general equilibrium model outperforms the cost of carry model in forecasting prices of the TAIFEX and the SGX futures. This finding indicates that in the higher volatility of the Taiwan stock market incorporating stochastic market volatility into the pricing model helps in predicting the prices of these two futures. Furthermore, the comparison results of different volatility estimators support the conclusion that the power EWMA and the GARCH(1,1) estimators can enhance the forecasting performance of the general equilibrium model compared to the other estimators. Additionally, the relaxation of the up‐tick rule helps reduce the degree of mispricing. Copyright © 2008 John Wiley & Sons, Ltd.