Mary E. Thomson

Do forecasts expressed as prediction intervals improve production planning decisions

A number of studies have shown that providing point forecasts to decision makers can lead to improved production planning decisions. However, point forecasts do not convey information about the level of uncertainty that is associated with forecasts. In theory, the provision of prediction intervals, in addition to point forecasts, should therefore lead to further enhancements in decision quality. To test whether this is the case in practice, participants in an experiment were asked to decide on the production levels that were needed to meet the following weeks demand for a series of products. Either underproduction cost twice as much per unit as overproduction or vice versa. The participants were supplied with either a point forecast, a 50% prediction interval, or a 95% prediction interval for the following weeks demand. The prediction intervals did not improve the quality of the decisions and also reduced the propensity of the decision makers to respond appropriately to the asymmetry in the loss function. A simple heuristic is suggested to allow people to make more effective use of prediction intervals. It is found that applying this heuristic to 85% prediction intervals would lead to nearly optimal decisions.

Feedback-labelling synergies in judgmental stock price forecasting

Research has suggested that outcome feedback is less effective than other forms of feedback in promoting learning by users of decision support systems. However, if circumstances can be identified where the effectiveness of outcome feedback can be improved, this offers considerable advantages, given its lower computational demands, ease of understanding and immediacy. An experiment in stock price forecasting was used to compare the effectiveness of outcome and performance feedback: (i) when different forms of probability forecast were required, and (ii) with and without the presence of contextual information provided as labels. For interval forecasts, the effectiveness of outcome feedback came close to that of performance feedback, as long as labels were provided. For directional probability forecasts, outcome feedback was not effective, even if labels were supplied. Implications are discussed and future research directions are suggested.

Influencing expert judgment: Attributions of crime causality

Purpose: The present research aimed to investigate the effects of attribution on expert clinical judgment in comparison to semi-experts and lay-people. Two research questions were addressed. Firstly, would experts be less subject to attributional manipulations, in terms of their perceived ratings of dangerousness, than would semi-experts or lay-people? Second, would experts be less subject to attributional manipulations, in terms of their assessments of offender responsibility, than would semi-experts or lay-people? Method: A 3x3x2 mixed groups design was implemented. Participants read nine crime scenarios that had been internally or externally manipulated. For each scenario, participants were asked to rate offender dangerousness, offender responsibility and the seriousness of the crime and to suggest a suitable sentence length. Targeted recruitment was employed, yielding 12 experts, 21 semi-experts and 22 lay-people. Results: Offenders were considered to be more responsible for their actions and more dangerous to others in the internal manipulations than in the external ones across all crime types and by all levels of expertise. Findings indicate that semi-experts are less subject to the influence of attributional manipulations than both experts and lay-people. Marked similarities in the pattern of expert and lay-person judgments can be observed from the present analyses Conclusions: The current findings lend support to previous research in the area in that similarities between expert and lay-person judgment were observed. However, through expanding and clarifying the levels of expertise investigated, the current findings highlight the need for greater research into the distinct ‘semi-expert’ group.

The influence of the forecast horizon on judgemental probability forecasts of exchange rate movements

An experiment is reported which compares directional forecasting performance of experts, novices and simple statistical models over three time horizons on a task involving probabilistic forecasts of exchange rate movements. Probability-judgement accuracy analyses illustrated no clear overall performance differences between experts and novices, but significant differences between the groups on various important components of judgement suggested that the groups obtained their similar overall scores using different cognitive strategies. Striking horizon effects and expertize–horizon interactions were also observed. The subjects performed better than a random walk forecaster, but worse than the random walk with constant drift and first-order autoregressive models. Composite human judgement, however, not only improved on individual judgement but, also, surpassed the simple statistical models in many instances. Possible explanations are offered for these results, suggestions are made for future research, and practical implications are emphasized.

Investigating the Influence of Causal Attributions on Both the Worksheet and Checklist Versions of the HCR-20.

Attribution theories suggest that when assessing an individuals actions, judgments are made about the cause of these behaviours and often these judgments focus on internal or external causal explanations. The current research investigated the effects of internal and external attribution on the scoring of the HCR-20 and the possibility of differences in scoring between two ways of using the HCR-20 (using the HCR-20 as a worksheet versus checklist). No differences were present in the scoring between the checklist versus worksheet. Attribution effects were present within the Historical Scale, Clinical Scale, and overall scoring of the HCR-20. Ratings were higher within the internal attribution condition than the external one, indicating that judgments made using the HCR-20 are subject to attribution effects in a similar manner as unaided violence risk assessments.

Evaluating strategic directional probability predictions of exchange rates

The current paper aims to examine strategic predictions (with forecast horizons greater than six months) via the empirical probability (EP) technique. This technique was proposed initially to examine short-term tactical predictions (with forecast horizons less than three months), as set out in Pollock et al. (2005). The proposed procedure is based on the hypothesis that changes in logarithms of daily exchange rates follow a normal distribution over short horizons (of 10 to 30 days), but longer term forecast evaluation requires consideration of cumulative parameters consistent with changing means and standard deviations arising from primary and secondary trends. It is shown that ex-post EPs can be obtained for any predictive horizon above 30 days (e.g., 180 days) by using a combination of shorter (e.g., 20-day) Student t distributions. The procedure is illustrated using daily Euro/USD series from 4 January 1999 to 29 January 2008 to evaluate a set of Euro/USD directional probability predictions.