Group-based forecasting?: A social psychological analysis

The potential of group (vs. individual) forecasting is analyzed from the perspective of the social psychology of groups. The social decision scheme theory (SDST) is summarized, and several simulations are presented to demonstrate the dependence of group aggregation accuracy upon factors such as group size, the accuracy and distribution of individual forecasts, and shared representations of the forecasting problem. Many advantages and disadvantages of group aggregation are identified and related to four generic methods of group aggregation (statistical aggregation, prediction markets, the Delphi method, and face-to-face discussion). A number of aspects of forecasting problems are identified which should govern whether or not group forecasting can be relied upon, and if so, what aggregation method should be used.     

Stock market volatility forecasting: Do we need high-frequency data?

The general consensus in the volatility forecasting literature is that high-frequency volatility models outperform low-frequency volatility models. However, such a conclusion is reached when low-frequency volatility models are estimated from daily returns. Instead, we study this question considering daily, low-frequency volatility estimators based on open, high, low, and close daily prices. Our data sample consists of 18 stock market indices. We find that high-frequency volatility models tend to outperform low-frequency volatility models only for short-term forecasts. As the forecast horizon increases (up to one month), the difference in forecast accuracy becomes statistically indistinguishable for most market indices. To evaluate the practical implications of our results, we study a simple asset allocation problem. The results reveal that asset allocation based on high-frequency volatility model forecasts does not outperform asset allocation based on low-frequency volatility model forecasts.     

General Election: How would the parties' plans impact the outlook?

• Our modelling suggests that, based upon the three main parties’ economic and fiscal plans, the outcome of the General Election would have a modest, but not immaterial, impact on the UK's economic and fiscal outlook. The Liberal Democrat plans would deliver the strongest GDP growth, followed by Labour, but both would also involve higher debt servicing costs and a higher level of government debt than the plans of the Conservatives.
• In our view these premiums on debt and borrowing costs are so small that it is very difficult to argue that the UK should pursue a more austere fiscal policy and reject the opportunity of stronger growth. But with the latest opinion polls suggesting that it is likely that the next government will be either a minority administration, or a coalition consisting of three or more parties, it is most likely that we will ultimately see some combination of the main parties' plans enacted.
• The experience of 2010 suggests that such political uncertainty could mean that we see several bouts of market nervousness between now and May 7th, particularly in equity markets. However, such turbulence is likely to be short‐lived, providing that the resulting government is perceived to be strong and durable. Even a multi‐party coalition may not be such a bad thing, particularly if it watered down the more contentious policies of the main parties. The worst‐case scenario would be a weak minority government which is both unable to pass any meaningful legislation and unable to seek a fresh mandate. Such a scenario could seriously undermine confidence amongst investors and firms.

     

What determines forecasters’ forecasting errors?

This paper contributes to the growing body of literature in macroeconomics and finance on expectation formation and information processing by analyzing the relationship between expectation formation at the individual level and the prediction of macroeconomic aggregates. Using information from business tendency surveys, we present a new approach of analyzing forecasters’ qualitative forecasting errors. Based on a quantal response approach with misclassification, we define forecasters’ qualitative mispredictions in terms of deviations from the qualitative rational expectation forecast, and relate them to the individual and macro factors that are driving these mispredictions. Our approach permits a detailed analysis of individual forecasting decisions, allowing for the introduction of individual and economy-wide determinants that affect the individual forecasting error process.     

Too much inventory? How do you know?

How much inventory does a company need to support its business goals? Companies must consider what effect their inventory investment decisions have on the strategic direction of their business. Too often, a company's investment decisions are carried out not by the company's strategists, but by individuals who are unaware of the strategic direction of the business.     

Unbounded exchange economies with satiation: How far can we go?

We unify and generalize the existence results in Werner [Werner, J., 1987. Arbitrage and the existence of competitive equilibrium. Econometrica 55 (6), 1403–1418], Dana et al. [Dana, R.-A., Le Van, C., Magnien, F., 1999. On the different notions of arbitrage and existence of equilibrium. Journal of Economic Theory 87 (1), 169–193], Allouch et al. [Allouch, N., Le Van, C., Page Jr., F.H., 2006. Arbitrage and equilibrium in unbounded exchange economies with satiation. Journal of Mathematical Economics 42 (6), 661–674], Allouch and Le Van [Allouch, N., Le Van, C., 2008. Erratum to “Walras and dividends equilibrium with possibly satiated consumers”. Journal of Mathematical Economics 45 (3–4), 320–328]. We also show that, in terms of weakening the set of assumptions, we cannot go too far.     

Post-script—Retail forecasting: Research and practice

This note updates the 2019 review article “Retail forecasting: Research and practice” in the context of the COVID-19 pandemic and the substantial new research on machine-learning algorithms, when applied to retail. It offers new conclusions and challenges for both research and practice in retail demand forecasting.     

Probabilistic electricity price forecasting with NARX networks: Combine point or probabilistic forecasts?

Recent electricity price forecasting studies have shown that decomposing a series of spot prices into a long-term trend-seasonal and a stochastic component, modeling them independently and then combining their forecasts, can yield more accurate point predictions than an approach in which the same regression or neural network model is calibrated to the prices themselves. Here, considering two novel extensions of this concept to probabilistic forecasting, we find that (i) efficiently calibrated non-linear autoregressive with exogenous variables (NARX) networks can outperform their autoregressive counterparts, even without combining forecasts from many runs, and that (ii) in terms of accuracy it is better to construct probabilistic forecasts directly from point predictions. However, if speed is a critical issue, running quantile regression on combined point forecasts (i.e., committee machines) may be an option worth considering. Finally, we confirm an earlier observation that averaging probabilities outperforms averaging quantiles when combining predictive distributions in electricity price forecasting.     

Are forecasting competitions data representative of the reality?

Forecasters typically evaluate the performances of new forecasting methods by exploiting data from past forecasting competitions. Over the years, numerous studies have based their conclusions on such datasets, with mis-performing methods being unlikely to receive any further attention. However, it has been reported that these datasets might not be indicative, as they display many limitations. Since forecasting research is driven somewhat by data from forecasting competitions, it becomes vital to determine whether they are indeed representative of the reality or whether forecasters tend to over-fit their methods on a random sample of series. This paper uses the data from M4 as proportionate to the real world and compares its properties with those of past datasets commonly used in the literature as benchmarks in order to provide evidence on that question. The results show that many popular benchmarks of the past may indeed deviate from reality, and ways forward are discussed in response.     

Are you running out of time?

In a perfect world we would all have a written daily plan of action that would be inviolate. Every task, every action, every conversation would be precisely timed to move us toward our ultimate personal goals. No one would trespass on our sacred schedule. But this is most definitely not a perfect world.     

Are low-frequency data really uninformative? A forecasting combination perspective

In this study, we investigate whether low-frequency data improve volatility forecasting when high-frequency data are available. To answer this question, we utilize four forecast combination strategies that combine low-frequency and high-frequency volatility models and employ a rolling window and a range of loss functions in the framework of the novel Model Confidence Set test. Out-of-sample results show that combination forecasts with GARCH-class models can achieve high forecast accuracy. However, the combination forecast methods appear not to significantly outperform individual high-frequency volatility models. Furthermore, we find that models that combine low-frequency and high-frequency volatility yield significantly better performance than other models and combination forecast strategies in both a statistical and economic sense.     

Do precious metal prices help in forecasting South African inflation?

In this paper we test whether the key metals prices of gold and platinum significantly improve inflation forecasts for the South African economy. We also test whether controlling for conditional correlations in a dynamic setup, using bivariate Bayesian-Dynamic Conditional Correlation (B-DCC) models, improves inflation forecasts. To achieve this we compare out-of-sample forecast estimates of the B-DCC model to Random Walk, Autoregressive and Bayesian VAR models. We find that for both the BVAR and BDCC models, improving point forecasts of the Autoregressive model of inflation remains an elusive exercise. This, we argue, is of less importance relative to the more informative density forecasts. For this we find improved forecasts of inflation for the B-DCC models at all forecasting horizons tested. We thus conclude that including metals price series as inputs to inflation models leads to improved density forecasts, while controlling for the dynamic relationship between the included price series and inflation similarly leads to significantly improved density forecasts.     

How does improved forecasting benefit detection? An application to biosurveillance

While many methods have been proposed for detecting disease outbreaks from pre-diagnostic data, their performance is usually not well understood. We argue that most existing temporal detection methods for biosurveillance can be characterized as a forecasting component coupled with a monitoring/detection component.In this paper, we describe the effect of forecast accuracy on detection performance. Quantifying this effect allows one to measure the benefits of improved forecasting and determine when it is worth improving a forecast method’s precision at the cost of robustness or simplicity. We quantify the effect of forecast accuracy on detection metrics under different scenarios and investigate the effect when standard assumptions are violated. We illustrate our results by examining performance on authentic biosurveillance data.     

How does inter-industry spillover improve the performance of volatility forecasting?

This study aims to investigate whether introducing inter-industry spillover information into the GARCH-MIDAS model improves out-of-sample forecasting attempts. We explore the transmission of volatility across sectors, as well as the reliance on inter-industry business links. Our findings demonstrate strong cross-industry volatility spillovers that are related to the degree of the industry-to-industry trading linkage. We compare the out-of-sample volatility forecasting performance of the spillovers-information-incorporated GARCH-MIDAS model with that of the traditional GARCH model. The empirical results show that the GARCH-MIDAS model outperforms traditional GARCH models. Notably, we discover that good (bad) news is always transferred from the back end of the production process to the front end, meaning that economic growth (decline) is driven by consumption expansion (shrinkage).     

On the M4.0 forecasting competition: Can you tell a 4.0 earthquake from a 3.0?

Twenty years on from the publication of the results of the celebrated M3 competition and we were just about used to the idea that there would be no more M-type competitions, when the M4 competition came along in 2019. A 4.0 earthquake is 10 times ‘stronger’ than a 3.0, and that was what M4.0 was aspiring to; so was its mission accomplished?     

Total quality and the abandonment of performance appraisal: Taking a good thing too far?

Proponents of total quality management often argue that performance appraisal is fundamentally at odds with quality-oriented management. This argument is made both on the basis of logical analysis and statistical demonstration. We show that neither of these arguments creates a compelling case against performance appraisal. We conclude that thoughtful organizations need to make decisions about performance appraisal in the same way that other business decisions are made, that is, in terms of a cost-benefit analysis.     

Last in,first out?: Estimating the effect of seniority rules in Sweden

In this paper we investigate whether a relaxation in seniority rules (the “last-in-first-out” principle) had any effect on firms' employment behaviour. Seniority rules exist in several countries, but consequences of seniority rules on firms' employment behaviour have not been examined previously. The “last-in-first-out” principle in Sweden was reformed in January 2001 such that employers with ten or fewer employees were allowed to exempt two workers from the seniority rule. Using an employer–employee unbalanced panel data for the period 1996–2005, we find that both hires and separations increased in small firms relative to large firms by 5%. This also implies that there were no effects on firms' net employment. Our results show that firms reacted to changes in the seniority rules, but we argue that the effects are not overwhelmingly large.