The Hot (Invisible?) Hand: Can Time Sequence Patterns of Success/Failure in Sports Be Modeled as Repeated Random Independent Trials?

Yaari, Gur; Eisenmann, Shmuel

doi:10.1371/journal.pone.0024532

Cited by 97 publications

(76 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…That is, the causal interpretation one might be tempted to draw from earlier research (i.e., because there is an average increase in grades for answer changes, it is profitable for me to change my answers when in doubt) is incorrect. A similar finding was reported by Wardrop (1995), who showed that the “hot hand” in basketball—the alleged phenomenon that sequential successful free throws increase the probability of subsequent throws being successful—disappears when taking into account varying proportions of overall success—i.e., differences in individual ability (see also Yaari and Eisenmann, 2011). Within players over time, the success of a throw depended on previous successes in different ways for different players, although the hot-hand pattern (increased success rate after a hit) did appear at the level of aggregated data.…”

Section: Simpson's Paradox In Individual Differencesmentioning

confidence: 99%

Simpson's paradox in psychological science: a practical guide

Kievit¹,

Frankenhuis²,

Waldorp³

et al. 2013

Front. Psychol.

428

299

View full text Add to dashboard Cite

The direction of an association at the population-level may be reversed within the subgroups comprising that population—a striking observation called Simpson's paradox. When facing this pattern, psychologists often view it as anomalous. Here, we argue that Simpson's paradox is more common than conventionally thought, and typically results in incorrect interpretations—potentially with harmful consequences. We support this claim by reviewing results from cognitive neuroscience, behavior genetics, clinical psychology, personality psychology, educational psychology, intelligence research, and simulation studies. We show that Simpson's paradox is most likely to occur when inferences are drawn across different levels of explanation (e.g., from populations to subgroups, or subgroups to individuals). We propose a set of statistical markers indicative of the paradox, and offer psychometric solutions for dealing with the paradox when encountered—including a toolbox in R for detecting Simpson's paradox. We show that explicit modeling of situations in which the paradox might occur not only prevents incorrect interpretations of data, but also results in a deeper understanding of what data tell us about the world.

show abstract

Section: Simpson's Paradox In Individual Differencesmentioning

confidence: 99%

Simpson's paradox in psychological science: a practical guide

Kievit¹,

Frankenhuis²,

Waldorp³

et al. 2013

Front. Psychol.

428

299

View full text Add to dashboard Cite

show abstract

“…It may surprise some categories (eg, tpse) have not appeared in the sequence of occurrences but must be taken into account that the timing of actual releases set to be random, always from the temporal approach on which rests the analysis tool heme (Magnusson, 2000;2005;2006). You might think that performing countries could increase the efectiveness of releases (Yaari & Eisenmann, 2011;Fernández., et al, 2009) however, it was not for any of the teams. Both teams were identiied making passes with efective and inefective releases, which could be interpreted as a search by the teams to get clear of rivals spaces, although releases not turn out always efective.…”

Section: Discussionmentioning

confidence: 99%

“…Failing to pay attention to this relational capacity with peers, would reduce the analysis of success in basketball (Courel, Suárez, Ortega, Piñar, & Cár-denas, 2013; Erčulj & Štrumbelj, 2015) to random factors in a particular motor situation. Although throw efectiveness (Fernández, Camerino, Anguera, & Jonsson, 2009;Yaari & Eisenmann, 2011) is an essential indicator to explain the outcome of a basketball game, even though this would not explain by itself how teams play, it does downplay the importance of having more ball possessions, since teams with few but efective possessions could prove themselves superior to opponents who do not have high percentages of efectiveness (Ibáñez, Feu, & Dorado, 2003 (Fernández., et al, 2009) or playing action (Garzón, Lapresa, Anguera, & Arana, 2011) was analyzed according to this methodology, to try to reveal regularities which took place during the games, but were hidden from an apparent look. Some analysis traditionally used by the well-established observational methodology (Anguera & Hernández-Mendo, 2014; Anguera & Hernández-Mendo, 2016) applied analysis which did not include the time dimension.…”

Section: Introductionmentioning

confidence: 99%

Detección de estructuras temporales en baloncesto

Pic¹

2017

sportk

View full text Add to dashboard Cite

Resumen: Resumir un partido de baloncesto a la efectividad en el lanzamiento, rebotes ofensivos y/o defensivos, entre otros indicadores; puede ser arriesgado, partiendo de la complejidad relacional existente en un partido de baloncesto. A pesar de ello, tradicionalmente ha sido investigado el éxito en baloncesto sobre datos sin una referencia temporal. La identiicación de regularidades temporales y conductuales puede ser un reto de investigación que ayude a concretar la planiicación de entrenamientos, así como la optimización estratégica de los equipos. El registro temporal de aciertos y fallos en el lanzamiento entre otros indicadores, puede ofrecer una dependencia temporal ineludible, invisible a una mirada aparente. Es este el propósito primordial del trabajo para optimizar las estrategias puestas en práctica en los partidos y con ello, la concreción de rutinas más ecológicas de acuerdo con las demandas de los partidos en los entrenamientos. Fue empleada una metodología observacional con un diseño nomotético, puntual y multidimensional para el registro de conductas motrices organizadas en torno a un sistema mixto de registro 'had oc'. Para el análisis de la dimensión temporal de los registros fue empleada la técnica T-patterns (Magnusson, 2000), posibilitando así, la identiicación de asimetrías motrices. Los resultados muestran regularidades temporales y estratégicas más relevantes. La identiicación de itinerarios estratégicos de los equipos revelan la acomodación funcional entre los equipos. Palabras Clave: baloncesto, metodología observacional, t-patterns, interacción motriz Abstract: Summarizing a basketball game to efectiveness at launch, ofensive rebounds and / or defensive, among other indicators; it can be risky, based on the relational complexity existing in a basketball game. However, traditionally; it has been investigated success in basketball on data without a time reference. Temporary identiication and behavioral regularities can be challenging research to help realize training planning and strategic optimization of equipment. he temporary record of successes and failures in launching among other indicators, can provide an unavoidable time dependence, invisible to an apparent look. his is the primary purpose of work to optimize strategies implemented in matches and thus the realization of greener routines according to the demands of the parties in training. It was an observational methodology used a nomothetic, punctual and multidimensional design for the registration of motor behavior organized around a mixed system of registration 'had oc'. For the analysis of the temporal dimension of the records it was used the technique T-patterns (Magnusson, 2000), thus enabling the identiication of motor asymmetries. he results show most relevant temporal and strategic regularities. he identiication of strategic pathways teams reveal functional accommodation between the teams.

show abstract

“…It is worth to note that the persistent long-range memory present in the diffusive process can be related the "hot hand" phenomenon in sports. Since the seminal work of Gilovich et al [20] there has been a historical debate on whether "success breeds success" or "failure breeds failure" in the scoring process of many sports [21,22]. Here, the long-range persistent behavior in the score evolution not only indicates the existence of this phenomenon in cricket, but also suggests that this phenomenon can act over a very long temporal scale.…”

Section: S(t)−⟨s(t)⟩ σ(T)mentioning

confidence: 97%

Anomalous diffusion and long-range correlations in the score evolution of the game of cricket

2012

View full text Add to dashboard Cite

We investigate the time evolution of the scores of the second most popular sport in world: the game of cricket. By analyzing the scores event-by-event of more than two thousand matches, we point out that the score dynamics is an anomalous diffusive process. Our analysis reveals that the variance of the process is described by a power-law dependence with a super-diffusive exponent, that the scores are statistically self-similar following a universal Gaussian distribution, and that there are long-range correlations in the score evolution. We employ a generalized Langevin equation with a power-law correlated noise that describe all the empirical findings very well. These observations suggest that competition among agents may be a mechanism leading to anomalous diffusion and long-range correlation. [3], and many other phenomena. One of the most common fingerprints of usual diffusion is the way that particles or objects in question spread. The spreading can be measured as the variance of the positions of the particles after a certain period of time. For usual diffusion, the variance grows linearly in time. There are two hypothesis underlying this behavior. The first one is the absence of memory along the particle trajectory, that is, the actual position of the particle can be approximated by a function of its immediately previous position (Markovian hypothesis). The second one is the existence of a characteristic scale for the position increments. When these two assumptions hold, we can show that distribution of the positions will approach a Gaussian profile (Central Limit Theorem).Naturally, there are situations in nature that do not fit these hypothesis and, consequently, deviations from the usual behavior appear. When this happens, researchers usually report on anomalous diffusion. A well understood case is when there is no characteristic length for the particle jumps. In this case, the variance is infinity and the distribution of the positions follows a Lévy distribution. Examples of Lévy processes include the animals movement during foraging [4], diffusion of ultracold atoms [5] and systems out of thermal equilibrium [6]. The situation is more complex when the diffusive process presents memory. We have many different manners of correlating the particle positions. Depending on this choice, diffusive properties such as the dependence of the variance in time can drastically change. In this context, a typical * Electronic address: hvr@dfi.uem.br behavior for the variance is a power-law dependence with an exponent α, where α < 1 corresponds to sub-diffusion and α > 1 to super-diffusion.Several approaches have been proposed to investigate anomalous diffusion in general. Fractional diffusion equations [7], Fokker-Planck equations [8], and Langevin equations [9] are just a few examples of frameworks used to describe this phenomenon. However, there is a lack of empirical studies aiming to verify situations where these models can be applied and the possible mechanisms that lead to anomalous diffusion. There are a few exc...

show abstract

The Hot (Invisible?) Hand: Can Time Sequence Patterns of Success/Failure in Sports Be Modeled as Repeated Random Independent Trials?

Cited by 97 publications

References 22 publications

Simpson's paradox in psychological science: a practical guide

Simpson's paradox in psychological science: a practical guide

Detección de estructuras temporales en baloncesto

Anomalous diffusion and long-range correlations in the score evolution of the game of cricket

Contact Info

Product

Resources

About