Tests of Conditional Predictive Ability

We propose a framework for out‐of‐sample predictive ability testing and forecast selection designed for use in the realistic situation in which the forecasting model is possibly misspecified, due to unmodeled dynamics, unmodeled heterogeneity, incorrect functional form, or any combination of these. Relative to the existing literature (Diebold and Mariano (1995) and West (1996)), we introduce two main innovations: (i) We derive our tests in an environment where the finite sample properties of the estimators on which the forecasts may depend are preserved asymptotically. (ii) We accommodate conditional evaluation objectives (can we predict which forecast will be more accurate at a future date?), which nest unconditional objectives (which forecast was more accurate on average?), that have been the sole focus of previous literature. As a result of (i), our tests have several advantages: they capture the effect of estimation uncertainty on relative forecast performance, they can handle forecasts based on both nested and nonnested models, they allow the forecasts to be produced by general estimation methods, and they are easy to compute. Although both unconditional and conditional approaches are informative, conditioning can help fine‐tune the forecast selection to current economic conditions. To this end, we propose a two‐step decision rule that uses current information to select the best forecast for the future date of interest. We illustrate the usefulness of our approach by comparing forecasts from leading parameter‐reduction methods for macroeconomic forecasting using a large number of predictors.     

Forecasting demand for food in Libya—using confidence limits

Many developing countries are not self-sufficient in food production and they depend on food imports. In order to plan imports well in advance, the demand for food must be forecasted. If the forecasts are too low, the people suffer. On the other hand if the forecasts are too high—the food being a perishable commodity—resources of the country are wasted. The Food and Agricultural Organization of the United Nations (FAO) undertakes such forecasts occasionally. The FAO however links the food consumption to the income of a country and then just assume future income. Such forecasts have no scientific validity and could both fall short or be grossly excessive. In this study, the methodologies of Time Series and Regression Analysis are combined to avoid any guesses. Then confidence intervals are built so that it can be stated, e.g. with 95 per cent confidence that a nation will not eat more than the amount specified. A comparison of costs is made and it is shown that a country can save millions of dollars through the method of statistical confidence limits rather than by adding arbitrary quantities to means and averages. Finally savings possible in some other developing countries, by adopting the proposed method, are tabulated.     

Forecasting organizational changes

In this article the author argues that because of the difficulties associated with human behaviour such factors are frequently omitted from forecasts. Yet no organization can afford to disregard these factors if their forecasts are to be meaningful. The author includes illustrations of organizational change which he maintains will spread rapidly. Finally he discusses his own initial experiments in forecasting organizational change.     

Trend effects on perceived avalanche hazard

Hazard-level forecasts constitute an important risk mitigation tool to reduce loss of economic values and human life. Avalanche forecasts represent an example of this. As for many other domains, avalanche risk is communicated using a color-coded, categorical risk scale aimed at informing the public about past, current, and future risk. We report the results from three experiments in which we tested if an irrelevant past trend in forecasted avalanche danger affects perceptions of current and future avalanche risk. Our sample consisted of individuals from three different populations targeted by national avalanche warning services. All three experiments showed that the perception of avalanche risk is influenced by the trend, but that the effect is opposite for perceptions of current and expectations of future avalanche risk. While future avalanche risk is extrapolated in the same direction as the change from the previous day, we found that perceived current risk appears to be based on an average of past and current risk. These effects diminish when we provide participants with a scale indicating the exact level of avalanche danger. For most of our measurement instruments, however, the effects remain significant. These results imply that targeted populations may consider historic information more than was intended by the sender. As such, our results have implications for both avalanche warning services and risk communication in general.     

The future pattern of U.K. share ownership

This article reports the present pattern of ordinary share ownership in the U.K. and forecasts the future pattern of share ownership towards the end of the present century. The authors forecast that institutional shareholders will own 50 per cent of U.K. registered and managed companies by 1977 and that they will own 68 per cent by 1990. Holdings by individuals, executors and trustees will fall from 47·4 per cent in 1970 to 34 per cent in 1977 and 14 per cent in 1990.     

Post bureaucratic organisations and managers

Pressures to change in organizations administered on bureaucratic lines and using the production techniques of “scientific management” are deriving from certain intrinsic attributes of these systems and from changing attributes of the environment. These changes constitute attempts to introduce greater fluidity into organizational structures and attempts to diffuse power. To the extent that they are implemented they imply that future management will centre more on sociological and psychological data, will become more experimental and less directive in style, will focus more on organizational (as against departmental) concerns and will become more responsive to external groupings. They imply also that managers will be judged more by results than by the opinion of peers, that they will be more exposed to challenge and criticism, that they will be held responsible for the quality of the work experience of their subordinates and that their own careers will be less orderly.     

Careers after COVID-19: challenges and changes

ABSTRACT

There are few certainties in our visions of post-COVID-19 careers, but change is inevitable. This article will explore how HRD can be proactive in addressing the immediate needs of the post-pandemic workforce and workplaces, as they strive to recover and resume a productive future. Uncertainties about employment and employability, how workplaces will be configured, the future of some careers and the possibilities for new opportunities will weigh heavily on individuals as they navigate these challenges. Drawing on the career shock, resilience, and sustainable careers literature, we consider how both individual and contextual factors will impact people and their occupations moving forward.     

Satisfying values--yours and theirs: a talk with Manny Elkind. Interview by Richard L.Reece

Richard Reece, MD, interviewed Mansfield (Manny) Elkind on September 22, 1999 to talk about satisfying values and flexible thinking as keys to influencing physicians. Manny discusses why it's difficult for people to create lasting change in the workplace without recreating themselves. The effort to influence others often focuses on getting disciplined about changing behaviors, with the hope that feelings and attitudes will also change. This approach rarely works because behavior is changed only when values or beliefs change. People will get passionate and committed to achieving the organization's goals when they believe that their values will be satisfied as well. The leader's responsibility is to find ways of satisfying people's values, in addition to convincing them to use the organization's values as guides for behavior. A process is explored that helps people discover each other's values and preferences and transforms resistance to commitment.     

Future state visioning—A powerful leadership process

The process of conceptualizing and implementing significant change in complex organizations can be aided greatly through ‘future state visioning’, a set of processes for determining what and where you want to be by a future date. After developing ideas about the nature of the future environment facing the organization and the stakeholders who will be significant at that time, executives can articulate the values and principles which should guide actions leading to the future state vision. Examples from three organizations are used to illustrate the steps for successful use of the future state visioning procedure.     

Markov and renewal models for total manpower system

This study compares the predictive utility of three stochastic models for both total manpower system and cohort personnel movement. The models are all discrete time versions, including a first order Markov chain, a Markov chain with duration of stay (semi-Markov) and a vacancy model having both renewal and Markov properties. The analysis covers a continuous 20 year period: 1950–1970 for a state police (U.S.A.) internal labor market. The simple Markov chain model is inadequate for long term cohort forecasts, but reasonably adequate for long term organizational forecasts. The semi-Markov model outperforms the simple Markov model for cohorts, but is surprisingly less accurate for the total organization. The heuristic information it portrays for the cohort is, however, quite informative. The best model for intermediate (5 year) and long term (10 year) forecasts in both cohort and organizational tests is the renewal type vacancy model. This finding is viewed as particularly important both in terms of empirical performance, which we expect can be improved due to the initial simplifying assumptions used, and in terms of further theoretical explication of the underlying causal process since internal staff flows are conceptualized as contingent on the opportunities available.     

基于初始条件优化的GM(1,1）幂模型及其应用

针对GM(1,1)幂模型幂指数和初始条件优化问题,提出了一种基于初始条件和幂指数协同优化的方法。根据新信息优先原理,通过引入权重信息控制函数优化初始条件,表现新旧信息在初始条件构建中作用大小的变化规律,最大限度提取小样本序列中的有效信息,反应新旧信息共同对系统趋势变化的影响;以平均相对误差最小化为目标,参数间约束关系作为条件,构建非线性优化模型,实现GM(1,1)幂模型的幂指数和初始条件协同优化。最后,通过我国网络购物用户规模预测实例研究表明,优化的模型实现模型平均相对误差在理论上的最小化,其建模效果要优于其他对比模型,并将其用于2016-2020年网购用户规模预测,表明本文模型的实用性和有效性。     

The Use of Narrative Evidence and Explicit Likelihood by Decisionmakers Varying in Numeracy

Decisionmakers are often presented with explicit likelihood assessments (e.g., there is a 10% chance that an attack will occur over the next three months) and supporting narrative evidence in forecasting and risk communication domains. Decisionmakers are thought to rely on both numerical and narrative information to the extent that they perceive the information to be diagnostic, accurate, and trustworthy. In two studies, we explored how lay decisionmakers varying in numeracy evaluated and used likelihood assessments and narrative evidence in forecasts. Overall, the less numerate reported higher risk and likelihood perceptions. In simple probabilistic forecasts without narrative evidence, decisionmakers at all levels of numeracy were able to use the stated likelihood information, although risk perceptions of the less numerate were more affected by likelihood format. When a forecast includes narrative evidence, decisionmakers were better able to use stated likelihood in a percentage as compared to frequency or verbal formats. The more numerate used stated likelihood more in their evaluations whereas the less numerate focused more on the narrative evidence. These results have important implications for risk analysts and forecasters who need to report the results of their analyses to decisionmakers. Decisionmakers varying in numerical ability may evaluate forecasts in different ways depending on the types of information they find easiest to evaluate.     

REPORTING OF MANAGEMENT FORECASTS: AN EIGENVECTOR MODEL FOR ELICITATION AND REVIEW OF FORECASTS

Increasingly, business firms will be disclosing management forecasts in financial reports to investors. Single estimates based on a consensus view (e.g., Delphi estimates) may be used. It seems logical, however, to consider methods that seek formally to derive internally consistent subjective views regarding the sensitivity of assumptions and interacting events on forecasts. The major purpose of this paper is to extend micro-level cross-impact analysis to a macro-level eigenvalue analysis approach that elicits views of the effects of assumptions and interaction events on entire scenarios. Both methods are illustrated and contrasted. They are complementary rather than alternative methods. In particular, each method offers some potential in the development of operational guidelines for elicitation and reporting of management forecasts. In addition, the eigenvalue analysis offers several key advantages that make it potentially useful in preparing entire scenario forecasts.     

Nonstationary Brand Variables in Category Management: A Cointegration Perspective

Category‐management models serve to assist in the development of plans for pricing and promotions of individual brands. Techniques to solve the models can have problems of accuracy and interpretability because they are susceptible to spurious regression problems due to nonstationary time‐series data. Improperly stated nonstationary systems can reduce the accuracy of the forecasts and undermine the interpretation of the results. This is problematic because recent studies indicate that sales are often a nonstationary time‐series. Newly developed correction techniques can account for nonstationarity by incorporating error‐correction terms into the model when using a Bayesian Vector Error‐Correction Model. The benefit of using such a technique is that shocks to control variates can be separated into permanent and temporary effects and allow cointegration of series for analysis purposes. Analysis of a brand data set indicates that this is important even at the brand level. Thus, additional information is generated that allows a decision maker to examine controllable variables in terms of whether they influence sales over a short or long duration. Only products that are nonstationary in sales volume can be manipulated for long‐term profit gain, and promotions must be cointegrated with brand sales volume. The brand data set is used to explore the capabilities and interpretation of cointegration.     

What skills do physician leaders need now and in the future?

The role of the physician leader is moving beyond traditional medical staff issues. A recent national survey of physician leaders shows a growing need for education on specific technical, leadership, and practical skills. The results reveal the medical leadership skills that physician executives consider important today, and provide a window to the future about the skills that will be important tomorrow. Physicians say they need training now in quality assurance, clinical benchmarking, decision-making, and strategic planning. And when they gaze into the future and see the rapid changes throughout health care, they say they'll need more training in communication, organizational change, effective listening, and systems thinking.     

Wage Expectations for Higher Education Students in Spain

We assess students' ability to forecast future earnings by using data on expected wages self‐reported by college students with different graduation horizons. We find a significant gender gap, by which wage expectations are systematically lower for women than for men. However, women do not fully account for the gender gap in their future earnings. We also find that student performance, degree type, and graduation horizon play a relevant role in wage forecasts. In any case, students' expectations do not conform market wages but become more realistic as they approach graduation.     

Are you ready for virtual organizations?

Success, and maybe even survival, in the future will go to those health care organizations that can respond to constant and rapid change in a timely fashion. And timely doesn't mean what it once did. Years and months may no longer be a satisfactory response time. Even weeks may not always do. Opportunities will have to be seized quickly, or they will disappear forever. One possible answer to the leaden nature of most bureaucratic, hierarchical organizations may be a new kid on the block--the virtual organization. Formed solely to work on a single opportunity, these organizations can be used to position the parent organizations for almost any conceivable change.     

Discounting Across Generations: Necessary, not Suspect

Periodically, ethical objections are raised against the practice of discounting for future effects. Concerns about the potential effects on future generations from long-term nuclear waste disposal and global climate change have caused these ethical objections to recur. This article rebuts the various ethical objections to future discounting on practical, ethical, and analytic grounds. Discounting for future effects is a ubiquitous practice that cannot be practically prevented. In the event that public policy would dictate against future discounting in public decisions, such a constraint could never be successfully imposed on markets. Market values will always reflect the full, discounted streams of future effects even if governments prohibited the practice among individuals. Ethically, there is no basis for choosing an upper-bound time horizon beyond which discounting should be rejected. Any proposed horizon is arbitrary and has no obvious foundation. All decisions are fundamentally irreversible, so opponents of future discounting also must define a degree of irreversibility beyond which normal discounting should not apply, and defend on ethical grounds the basis for this demarcation. This task is further complicated by the likelihood that choices are rarely, if ever, as irreversible as opponents suggest. Typical examples given to prove future discounting is inappropriate overstate the degree of irreversibility actually present and understate subsequent opportunities for modifications. Finally, opposition to distant-future discounting on the ground that burdens are shifted to future generations must face the fact that such shifts are characteristic of intergenerational transfers now practiced widely and with great public support.     

Forecasting industrial production using structural time series models

Industrial production data series are volatile and often also cyclical. Hence, univariate time series models which allow for these features are expected to generate relatively accurate forecasts of industrial production. A particular class of unobservable components models — structural time series models — is used to generate forecasts of Austrian and German industrial production. A widely applied ARIMA model is used as a baseline for comparison. The empirical results show that the basic structural model generates more accurate forecasts than the ARIMA model when accuracy is measured in terms of size of error or directional change; and that the basic structural model forecasts better than the structural model with a cyclical component included on the basis of numerical measures, and tracking error for month-to-month changes.