Do statisticians bet on sports

If you just play for 5 times, the uncertainty will be too high to decide on some statistics. Even then we can see that the mean of the amount. It is found that the point spreads and totals proposed by sportsbooks capture 86% and 79% of the variability do statisticians bet on sports the median outcome, respectively. Statistics and sport management departments at Rice look at how computational tools and big data change fan experiences through gambling. Odds in betting are phrased in terms of the payoff that a bet will yield. On a 36 number roulette wheel (excluding the house's 0 or 0s), placing.

Do Statisticians Take the Gamble in Sports Betting?

Sports betting has always been a realm where emotion, gut instinct, and sheer luck seem to rule the game. However, there is a growing trend among a certain group of individuals who are looking to analyze sports from a statistical perspective and make informed bets based on data rather than intuition. But do statisticians really find success in this unpredictable world of sports betting?

The thesis here is quite intriguing. While conventional wisdom suggests that sports betting is a game of chance, statisticians beg to differ. By utilizing complex statistical models, analyzing historical data, and applying mathematical principles, these individuals believe they can gain an edge in predicting sports outcomes and potentially turning a profit.

Statisticians often delve deep into player performances, team statistics, historical matchups, and various other factors to identify patterns and trends that could influence the outcome of a game. They view sports as a data-driven puzzle that can be solved through rigorous analysis and logical deduction.

In certain circles, these statisticians have gained a reputation for their meticulous approach to sports betting. While some may view their methods as too analytical or lacking the excitement of traditional gambling, others see it as a strategic and calculated way to participate in the sports betting landscape.

It is worth noting that success in sports betting as a statistician is not guaranteed. Even with all the data and analysis at their disposal, unforeseen variables can always come into play and influence the outcome of a game. However, the proponents of statistical sports betting argue that their approach minimizes risks and maximizes the chances of making profitable decisions over the long term.

Ultimately, the debate on whether statisticians can succeed in sports betting continues to divide opinions. While some believe in the power of data-driven analysis, others remain skeptical of straying too far from traditional forms of sports gambling that rely on luck and instinct.

As with any form of betting or gambling, there are risks involved, and individuals should always bet responsibly and within their means, regardless of the approach they choose to adopt.

Advantage of Statistics In sports betting

What game do most professional gamblers play? Most popular games are poker and blackjack. Advantage slot play and sports betting are two others. Technique will vary on what game you are playing. A game like blackjack is basically all math while poker is a combination of lots of skills.

Who is most likely to sports bet? Most sports bettors are male, white, wealthy, and younger. They are also likely to be committed sports fans and most often bet on the NFL or the NBA.

Can NFL analysts bet? NFL office staff is banned from gambling of any kind at any time, according to the memo. The league also reminded personnel to never share game, team or player “inside information,” and to report any requests for that data.

Why can't professional athletes bet? While fans are encouraged to give it a try, athletes and those associated with leagues are strictly prohibited from gambling due to the obvious concerns of insider trading and match fixing. Still, there have been several instances where players have been disciplined for sports betting.

What demographics bet on sports? Who is betting on sports the most? The demographic of sports bettors tends to be young, male and wealthy. According to Ipsos, 39% of bettors are under the age of 35, and 69% of bettors are male. Additionally, more than half (51%) of sports bettors are white and 44% have an income of $100k or more.

Are football managers allowed to bet? It is against FA rules and may be a criminal offence.

Do people bet sports professionally? A professional sports bettor is someone who makes a living betting on sports. That usually means doing intensive research, creating expert betting models, and in some cases, curating weekly picks for their fanbases.

Are pundits allowed to bet? No Participant can bet on a match or competition in which they are involved that season, or which they can influence, or any other football-related matter concerning the league that they play in. Participants are also prohibited from using or passing inside information for betting.

Can sports analysts bet on sports? Talent designated as Reporters and Insiders are prohibited from placing, soliciting, or facilitating any bet on the properties (e.g., NFL, college football, NBA) they regularly cover. Employees who learn Confidential Information from Reporters or Insiders should never use such information for betting-related purposes.

A statistical theory of optimal decision-making in sports betting

Daniel Kowal is a statistician and longtime baseball fan, two roles that can be difficult to distinguish. Fans can casually rattle off what sounds like a lot of obscure numbers but are actually an important part of the game. Sport analytics is being taken seriously not only by academics but by lawmakers across the country and a sub-category of sports fans — gamblers.

A growing number of states have in recent years legalized sports betting and others are expected to follow. Web sites are devoted to daily legislative updates. A sports fan though not a gambler, Ensor noted that data science when combined with profound knowledge of a sport has a significant impact on both the management of a team and the behavior of bettors.

Speakers looked at how computational tools and big data have an impact on sports and change fan experiences through gambling. The three types of wagers considered in this work—point spread, moneyline, and over-under—are the most popular bet types in North American sports. One unique aspect of American football is its scoring system, in which the points accumulated by each team increase primarily in increments of 3 or 7 points.

The structure of the scoring imposes constraints on the distribution of the margin of victory m. In the case of games in the National Basketball Association NBA , the most common margins of victory tend to occur in the interval, reflecting the overall higher point totals in basketball and its most common point increments 2 and 3.

In this fictitious example, the median is 7 but the mean is Assuming that one has committed to wagering on the match, the optimal decision is to bet on the visiting team, despite that fact that the home team has won the previous matches by an average of 15 points. The figures and tables in this manuscript may be reproduced by executing the notebook.

The latter was utilized for all analysis. In order to estimate quantiles of the distributions of margin of victory and point totals from heterogeneous data i. This permitted the estimation of the 0. Only spreads or totals with at least matches in the dataset were included, such that estimation of the median would be sufficiently reliable.

It is likely that the resulting error is negligible, however, due to the likelihood of the payout discrepancy being fairly balanced across the home and visiting teams. In order to overcome the discrete nature of the margins of victory and point totals, kernel density estimation was employed to produce continuous quantile estimates.

The KernelDensity function from the scikit-learn software library was employed with a Gaussian kernel and a bandwidth parameter of 2. For the margin of victory, the density was estimated over points ranging from to For the analysis of point totals, the density was estimated over points ranging from 10 to The regression analysis relating median outcome to sportsbook estimates Fig 1 was performed with ordinary least squares OLS.

In order to generate variability estimates for the 0. The confidence intervals were then constructed as the interval between the 2. Do statisticians bet on sports To quantify the relationship between a sportsbook bias and the associated upper bound on wagering performance, the empirical CDF of each stratified sample was converted into an expected profit, conditioned on a hypothetical spread or total that deviated from the true median by fixed increments of -3, -2, -1, 0, 1, 2, and 3 points.

More specifically, the expected values were first computed separately for the case of wagering on the home and visiting teams:. To model the idealized case of always placing the wager on the side with the higher probability of winning against the spread, the reported expected profit was taken as the maximum of the two expected values in The analogous procedure was conducted for the analysis of point totals.

The author would like to thank Ed Miller and Mark Broadie for fruitful discussions during the preparation of the manuscript. The author would also like to acknowledge the effort of the reviewers, in particular Fabian Wunderlich, for providing many helpful comments and critiques throughout peer review.

After careful consideration, we have decided that your manuscript does not meet our criteria for publication and must therefore be rejected. I am sorry that we cannot be more positive on this occasion, but hope that you appreciate the reasons for this decision.

I have now heard back from an expert reviewer on your paper titled "Statistical Principles of Optimal Decision-Making in Sports Wagering. The reviewer provided comments and suggestions which I believe will be valuable in improving your work and potentially finding a more suitable outlet for publication.

I regret to inform you of this disappointing decision. I wish you the best of luck with your research and future publications. The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes.

The conclusions must be drawn appropriately based on the data presented. The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception please refer to the Data Availability Statement in the manuscript PDF file.

The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e. PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous.

Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics.

Please upload your review as an attachment if it exceeds 20, characters. This paper analyzes the efficiency of betting markets for American professional football games from The analysis includes bets on the margin of victory point spread and on the total number of points scored. In each case, bets are analyzed that are approximately even money bets. The most common arrangement is that a bettor wins the amount bet if they win but loses 1.

The analysis is conducted non-parametrically. Games are placed in bins according to their point spread and again according to their point totals. Assuming that a bin ends up containing games or more, the paper calculates the This is equivalent to calculating the mean binary outcome for bets in each direction for the bin and comparing it to the profitability thresholds of 0.

The paper finds that many bins have sample means that are outside the 0. There is no analysis of whether we can reject a null hypothesis that the population means fall within the 0. Put another way, in order for a bettor to have earned a positive profit, they would have had to know in advance of the sample period which specific bins would yield outcome probabilities below 0.

That the probability of an outcome being above or below a specified point spread or total, and therefore the quantiles of the distribution of the point spread or total, is central to the profitability of sports betting strikes me as completely obvious to everyone. PLOS authors have the option to publish the peer review history of their article what does this mean?

If published, this will include your full peer review and any attached files. Do you want your identity to be public for this peer review. For information about this choice, including consent withdrawal, please see our Privacy Policy. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.

Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. We recommend that it should be revised by taking into account the changes requested by Reviewers. I want to give you a chance to revise your manuscript. The Academic Editor will only review the manuscript in the next round to speed the review process.

Please submit your revised manuscript by Jun 08 PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at gro. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work.

In your Data Availability statement, you have not specified where the minimal data set underlying the results described in your manuscript can be found. PLOS defines a study's minimal data set as the underlying data used to reach the conclusions drawn in the manuscript and any additional data required to replicate the reported study findings in their entirety.

All PLOS journals require that the minimal data set be made fully available. Any potentially identifying patient information must be fully anonymized. Important: If there are ethical or legal restrictions to sharing your data publicly, please explain these restrictions in detail. Is sports betting fixed Note that it is not acceptable for the authors to be the sole named individuals responsible for ensuring data access.

We will update your Data Availability statement to reflect the information you provide in your cover letter. We note that you have indicated that data from this study are available upon request. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly.

In your revised cover letter, please address the following prompts:a If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail e. Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. We will update your Data Availability statement on your behalf to reflect the information you provide.

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript.

Reviewer 2: Please remove the heading "Results" prior to problem formulation. All the subheadings with a question mark should be revised as normal heading page Subsections should be named without any a punctuation mark all over the paper. Materials and methods should be placed as appendix. Discussion should be named as discussion and conclusion.

Thank you for giving me the opportunity to review this manuscript. I would like to underline that — in my opinion — the manuscript has merit and I am very confident that it will be worth publishing if several revisions are made to the manuscript. I will only very briefly mention the positive aspects of the manuscript as this review is intended to put more effort on possibilities for improvement.

However, I would like to underline that I really enjoyed reading the manuscript. I like the fact that theoretical considerations are combined with empirical data. The theory is explained intuitively and is easy to follow, the results are well-explained and graphically represented. Please see my several critical comments as an effort to further improve the manuscript.

My major point of criticism is the integration of the present results into the existing literature. Please find more details on this point below. Please be more careful and precise here. Please also find more information on this point below. In my mind this is simplifying as the results of market efficiency papers can point into different directions.

So I would suggest to be more careful here by stating that market efficiency has been the subject of investigation or more precise by saying what the important insights were. Moreover, the author states three papers from , and Below, I have summarised some more recent papers that might be worth considering:. Do statisticians bet on sports Angelini, G. Efficiency of online football betting markets.

International Journal of Forecasting, 35 2 , Bernardo, G. Semi-strong inefficiency in the fixed odds betting market: Underestimating the positive impact of head coach replacement in the main European soccer leagues. The Quarterly Review of Economics and Finance, 71, Meier, P. Are sports betting markets semistrong efficient?

International Journal of Sport Finance, 16 3. From my point of view, this is overselling the novelty of the current manuscript. Kelly, J. A new interpretation of information rate. Snowberg, E. Explaining the favorite—long shot bias: Is it risk-love or misperceptions?. Journal of Political Economy, 4 , Moreover, it is well established in the forecasting literature to use and test several models for deciding on bets such as several stake sizes e.

Hvattum, L. Using ELO ratings for match result prediction in association football. International Journal of forecasting, 26 3 , Wunderlich, F. Are betting returns a useful measure of accuracy in sports forecasting?. International Journal of Forecasting, 36 2 , For example, Theorem 2 is highly related to the area of no profitable bet presented in the aforementioned paper.

In general, I see a lot of overlap between the two papers, both analysing betting decisions both from a theoretical point and based on real-world data. The author could also describe how the current manuscript is different from the aforementioned paper, e. Beating the market with a bad predictive model. International Journal of Forecasting, 39 2 , Results Problem formulation point spread: You mention the word point spread betting before giving an explanation on how such bets work.

You might want to give a very brief explanation on this before, particularly as a lot of literature in this domain is concentrated on European sports betting markets, where point spreads are not that pronounced. I am neither convinced that this is true nor convinced that this is false. But I am a bit sceptical as this is obviously a strong assumption needed for the further proof.

Could you discuss this issue and explain in more detail why this assumption is reasonable. This is also reflected in the literature, which for example in soccer is highly concentrated on home, draw, away betting. I would also suggest to state possible differences between European home, draw, away and North American moneyline betting. Koopman, S. Forecasting football match results in national league competitions using score-driven time series models.

Constantinou, A. Determining the level of ability of football teams by dynamic ratings based on the relative discrepancies in scores between adversaries. Journal of Quantitative Analysis in Sports, 9 1 , Is it data provided by a company or data openly available online. However, I would like to see this explained more clearly.

Same paragraph: This paragraph states means and medians from the data. While the manuscript generally correctly underlines the potential difference between mean and median e. I would highly like to see this aspect explained and acknowledged. This claim, in my mind, is at least misleading. While I agree that a high standard deviation indicated frequent blowouts, this has nothing to do with the mean margin of victory which is rather an estimate of home advantage.

If the data would show 0. I wonder and I would like to see discussed whether there might be additional incentives of the bookmaker that contradict perfect forecasting. Just as one example, bookmakers might chose higher odds than reasonable for marketing reasons in some specific games.

Might bookmakers in spread betting favour completely equal odds over slightly different odds, although not representing their true belief in the probabilities. To be very precise here, this is a true question from my side, i. This seems to be in contradiction to the data presented in the results section see three points before. Please adjust this statement or give a better explanation on why you think this is the case.

General point: Not related to any specific part of the manuscript, but you might want to discuss differences between American football and other sports. In terms of forecasting and statistical modelling American football is a very specific challenge as it has different possibilities to score field goal, touchdown, extra point etc. To use PACE, you must first register as a user.

Registration is free. Please note that Supporting Information files do not need this step. An invoice for payment will follow shortly after the formal acceptance. If you have any billing related questions, please contact our Author Billing department directly at gro. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact.

Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact gro. Your manuscript is now with our production department. If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact.

If they'll be preparing press materials, please inform our press team within the next 48 hours. For more information please contact gro. If we can help with anything else, please email us at gro. As a library, NLM provides access to scientific literature. PLoS One. Published online Jun Jacek P. Baogui Xin, Editor. Corresponding author. Competing Interests: The authors have declared that no competing interests exist.

Received Dec 19; Accepted Jun 8. This is an open access article distributed under the terms of the Creative Commons Attribution License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Abstract The recent legalization of sports wagering in many regions of North America has renewed attention on the practice of sports betting.

Introduction The practice of sports betting dates back to the times of Ancient Greece and Rome [ 1 ]. Wagering to maximize expected profit Consider first the question of which team to wager on to maximize the expected profit. Optimal estimation of the margin of victory In practice, the margin of victory must be estimated from available data.

Empirical results from the National Football League In order to connect the theory to a real-world betting market, empirical analyses utilizing historical data from the National Football League NFL were conducted. How accurately do sportsbooks capture the median outcome. Open in a separate window.

Fig 1. How accurately do sportsbooks predict the median outcome. Table 1 The relationship between sportsbook point spread and true margin of victory. Spread Level 0. Total 0. Do sportsbook estimates deviate from the 0. Fig 2. Do sportsbook point spreads deviate from the 0. Fig 3. Do sportsbook point totals deviate from the 0. How large of a discrepancy from the median is required for profit?

Fig 4. How large of a bias in the point spread is required for positive expected profit. Fig 5. How large of a bias in the point total is required for positive expected profit. Discussion The theoretical results presented here, despite seemingly straightforward, have eluded explication in the literature. The case for quantile regression Conventional ordinary least-squares OLS regression yields estimates of the mean of a random variable, conditioned on the predictors.

Bias-variance in sports wagering One may intuit that the goal of the sports bettor is to produce a closer estimate of the median outcome than the sportsbook. Sport-specific considerations The three types of wagers considered in this work—point spread, moneyline, and over-under—are the most popular bet types in North American sports.

Data stratification In order to estimate quantiles of the distributions of margin of victory and point totals from heterogeneous data i. Median estimation In order to overcome the discrete nature of the margins of victory and point totals, kernel density estimation was employed to produce continuous quantile estimates. Confidence interval estimation In order to generate variability estimates for the 0.

Expected profit estimation To quantify the relationship between a sportsbook bias and the associated upper bound on wagering performance, the empirical CDF of each stratified sample was converted into an expected profit, conditioned on a hypothetical spread or total that deviated from the true median by fixed increments of -3, -2, -1, 0, 1, 2, and 3 points.

Acknowledgments The author would like to thank Ed Miller and Mark Broadie for fruitful discussions during the preparation of the manuscript. Funding Statement The author received no specific funding for this work. References 1. Matheson V. Eastern Economic Journal.

Bloomberg Media. Wunderlich F, Memmert D. Forecasting the outcomes of sports events: A review. European Journal of Sport Science. Pankoff LD. Market efficiency and football betting. The Journal of Business. Testing market efficiency: Evidence from the NFL sports betting market. The Journal of Finance. Predicting the outcomes of National Football League games.

International Journal of forecasting. The value of statistical forecasts in the UK association football betting market. International journal of forecasting. McHale I, Morton A. A Bradley-Terry type model for forecasting tennis match results.