Thursday, February 4, 2010
Back to the Future
Comparing Prediction Markets, Polls, and Their Biases
David Rothschild
Public Opinion Quarterly, Winter 2009, Pages 895-916
Abstract:
Using the 2008 elections, I explore the accuracy and informational content of forecasts derived from two different types of data: polls and prediction markets. Both types of data suffer from inherent biases, and this is the first analysis to compare the accuracy of these forecasts adjusting for these biases. Moreover, the analysis expands on previous research by evaluating state-level forecasts in Presidential and Senatorial races, rather than just the national popular vote. Utilizing several different estimation strategies, I demonstrate that early in the cycle and in not-certain races debiased prediction market-based forecasts provide more accurate probabilities of victory and more information than debiased poll-based forecasts. These results are significant because accurately documenting the underlying probabilities, at any given day before the election, is critical for enabling academics to determine the impact of shocks to the campaign, for the public to invest wisely and for practitioners to spend efficiently.
-----------------------
Adolescents' Perceived Risk of Dying
Baruch Fischhoff, Wändi Bruine de Bruin, Andrew Parker, Susan Millstein & Bonnie Halpern-Felsher
Journal of Adolescent Health, forthcoming
Purpose: Although adolescents' expectations are accurate or moderately optimistic for many significant life events, they greatly overestimate their chances of dying soon. We examine here whether adolescents' mortality judgments are correlated with their perceptions of direct threats to their survival. Such sensitivity would indicate the importance of ensuring that adolescents have accurate information about those threats, as well as the psychological support needed to deal with them.
Methods: Data from two separate studies were used: a national sample of 3,436 14-18-year-old adolescents and a regional sample of 124 seventh graders and 132 ninth graders, 12-16 years old. Participants were asked about their chance of dying in the next year and before age 20, and about the extent of various threats to their physical well-being.
Results: Adolescents in both samples greatly overestimated their chance of dying. Those mortality estimates were higher for adolescents who reported direct threats (e.g., an unsafe neighborhood). Thus, adolescents were sensitive to the relative size of threats to their survival, but not to the implications for absolute risk levels.
Conclusions: Contrary to the folk wisdom that adolescents have a unique sense of invulnerability, the individuals studied here reported an exaggerated sense of mortality, which was highest among those reporting greater threats in their lives. Such fears could affect adolescents' short-term well-being and future planning.
-----------------------
The Power of Voice: Managerial Affective States and Future Firm Performance
William Mayew & Mohan Venkatachalam
Duke University Working Paper, November 2009
Abstract: In this study, we measure managerial affective states during earnings conference calls by analyzing conference call audio files using vocal emotion analysis software. We hypothesize and find that when managers are scrutinized by analysts during conference calls, positive and negative affect displayed by managers are informative about the firm's financial future. In particular, we find that managers exhibiting positive (negative) affect are positively (negatively) related to contemporaneous stock returns and future unexpected earnings. However, analysts do not incorporate the information when determining short term earnings forecasts. When making stock recommendation changes, however, analysts incorporate positive affect but not negative affect. We observe market underreaction to negative affect as if market participants follow analyst recommendation changes. Together, this study presents new evidence that managerial vocal cues contain useful information about firms' fundamentals, incremental to both quantitative earnings information and qualitative "soft" information conveyed by the linguistic content.
-----------------------
Wishful Thinking in the 2008 U.S. Presidential Election
Zlatan Krizan, Jeffrey Miller & Omesh Johar
Psychological Science, January 2010, Pages 140-146
Abstract:
In elections, political preferences are strongly linked to the expectations of the electoral winner-people usually expect their favorite candidate to win. This link could be driven by wishful thinking (a biasing influence of preferences), driven by a biasing influence of expectations on one's wishes, or produced spuriously. To examine these competing possibilities in the 2008 U.S. presidential election, a longitudinal study assessed uncommitted young voters' electoral expectations and preferences over four time points during the month before the election. The findings indicated clear support for wishful thinking: Over time, people's preferences shaped their expectations, but the reverse was not the case. Moreover, these relations were larger among those more strongly identified with their political party and held even when perceptions of general candidate popularity were taken into account. Finally, changes in electoral expectations were consequential, as they shaped disappointment in the electoral results even after taking candidate preferences into account.
-----------------------
Role thinking: Standing in other people's shoes to forecast decisions in conflicts
Kesten Green & Scott Armstrong
University of Pennsylvania Working Paper, May 2009
Abstract:
Better forecasts of decisions in conflict situations, such as occur in business, politics, and war, can help protagonists achieve better outcomes. It is common advice to "stand in the other person's shoes" when involved in a conflict, a procedure we refer to as "role thinking." We tested this advice in order to assess the extent to which it can improve accuracy. Improvement in accuracy is important because prior research found that unaided judgment produced forecasts that were little better than guessing. We obtained 101 role-thinking forecasts from 27 Naval postgraduate students (experts) and 107 role-thinking forecasts from 103 second-year organizational behavior students (novices) of the decisions that would be made in nine diverse conflicts. The accuracy of the forecasts from the novices was 33% and of those from the experts 31%. The accuracy of the role-thinking forecasts was little different from chance, which was 28%. In contrast, when we asked groups of participants to each act as if they were in the shoes one of the protagonists, accuracy was 60%.
-----------------------
The Dynamics of Poll Performance During the 2008 Presidential Nomination Contest
Michael Traugott & Christopher Wlezien
Public Opinion Quarterly, Winter 2009, Pages 866-894
Abstract:
This analysis focuses on estimation difficulties pollsters had in the primaries in 2008 in light of recent trends in improved polling accuracy in general elections. We consider the series of polls that were conducted in New Hampshire and other states holding primaries, looking at how the dynamics of the primary contest affected polling accuracy in those contests. The data come from published state-level results of public pollsters from the week preceding each primary or caucus for which polls were conducted; all told, we used 258 polls in thirty-six different Democratic events and 219 polls in twenty-six Republican events. The results show that the winner's vote share almost always exceeded the poll share while the race remained competitive, particularly early on in the nomination process. In an unusual perspective made possible by the length of the contest on the Democratic side in particular, this could be observed through most of the primaries; it was not the case in the Republican events after John McCain became the presumptive nominee. The analysis shows there are contextual factors at work that can affect the quality of the estimates that public pollsters make. Measures of momentum and viability affect the estimates differently early in the process compared to later, and there are special factors associated with the insurgent candidacy of Barack Obama that may also have affected the accuracy of the polls. We model these factors, investigate their explanatory power, and discuss the implications for pollsters in future primary sequences.
-----------------------
A Field Test of the Influence of Pre-Game Imagery on Basketball Free Throw Shooting
Phillip Post, Craig Wrisberg & Stephen Mullins
Journal of Imagery Research in Sport and Physical Activity, 2010
Abstract:
This field study examined the influence of a pre-game imagery intervention implemented by a high school coach on the free throw shooting performance of his girls' basketball team. The coach conducted a systematic guided imagery exercise prior to half of the team's games over the course of an entire season. The coach employed the intervention with the whole team using a reversal design similar to the replication-reversal design used in some single-subject research (Hume, Martin, Gonzalez, Cracklen, & Genthon, 1985). A 2 x 2 chi-square analysis was used to evaluate the observed and expected frequencies of made and missed free throw shots under the two conditions (imagery and no-imagery). The results revealed a significantly higher than expected number of free throws made in games preceded by the intervention (p < .001). Social validation questionnaires completed by 11 of the 16 players suggested that the players devoted significant attention to the intervention and that they perceived it to be effective.
-----------------------
Does the Stock Market See a Zero or Small Positive Earnings Surprise as a Red Flag?
Edmund Keung, Zhi-Xing Lin & Michael Shih
Journal of Accounting Research, March 2010, Pages 91-121
Abstract:
This study shows that firms collectively incur a cost for managing earnings and analyst expectations to meet earnings forecasts. We compare the coefficient in the regression of abnormal stock returns on earnings surprise (the earnings response coefficient [ERC]) across ranges of earnings surprises. The ERC for earnings surprises in the range [0, 1¢] is significantly lower than ERCs for earnings surprises in adjacent ranges for firm-quarters in the early and mid 2000s, but not for those in the 1990s. The results are robust to controlling for the sign of estimated discretionary accruals and the trajectory of analyst earnings forecasts. We further find that investors are right to be skeptical about earnings surprises in the range [0, 1¢]. The relation of future earnings surprise with current earnings surprise is more negative for current earnings surprises in that range than for those in any other range. Evidence also suggests analysts react negatively to earnings surprises in that range.
-----------------------
Jared Ladbury & Verlin Hinsz
Group Dynamics, December 2009, Pages 235-254
Abstract:
Individuals experience numerous group decision situations during their lives. As a result, they may develop accurate expectations of the social processes and effects of context on group decision situations. Four decision-making situations were constructed that were expected to elicit different group decision processes. Individuals were presented with these hypothetical scenarios in which group size and the preferences of group members varied systematically. Participants' expectations were elicited from their predictions regarding which alternative the group would choose on the basis of the information presented. The comparison of these judgments with the predicted decision distributions derived from models of group decision making showed that participants had a general sensitivity to changes in contexts, but that they overestimated the effect of the majority opinion on the final decisions. Individuals may have general notions of how groups make decisions but are less sensitive to the subtleties involved in the process.
-----------------------
Thinking about the future moves attention to the right
Marc Ouellet, Julio Santiago, Maria Jesús Funes & Juan Lupiáñez
Journal of Experimental Psychology: Human Perception and Performance, February 2010, Pages 17-24
Abstract:
Previous studies have shown that past and future temporal concepts are spatially represented (past being located to the left and future to the right in a mental time line). This study aims at further investigating the nature of this space-time conceptual metaphor, by testing whether the temporal reference of words orient spatial attention or rather prime a congruent left/right response. A modified version of the spatial cuing paradigm was used in which a word's temporal reference must be kept in working memory whilst participants carry out a spatial localization (Experiment 1) or a direction discrimination, spatial Stroop task (Experiment 2). The results showed that the mere activation of the past or future concepts both oriented attention and primed motor responses to left or right space, respectively, and these effects were independent. Moreover, in spite of the fact that such time-reference cues were nonpredictive, the use of a short and a long stimulus onset asynchrony in Experiment 3 showed that these cues modulated spatial attention as typical central cues like arrows do, suggesting a common mechanism for these two types of cuing.
-----------------------
Analyzing Macroeconomic Forecastability
Ray Fair
Yale Working Paper, September 2009
Abstract:
This paper examines whether recessions and booms are forecastable under the assumption that equity prices, housing prices, import prices, exports, and random shocks are not. Each of the 214 eight-quarter periods within the overall 1954:1-2009:1 period is examined regarding predictions of output growth and inflation. The results for low output growth vary by recession - there is no common pattern. Of the eight recessions, three are forecast well. For four of the five that are not, the main reason for each is not knowing: 1) the random shocks, 2) import prices and equity prices, 3) exports, and 4) exports and equity prices. For the fifth - the last one - all five components are large contributors, including housing prices: a perfect storm.
