Modeling and forecasting the outcomes of NBA basketball games

This paper treats the problem of modeling and forecasting the outcomes of NBA basketball games. First, it is shown how the benchmark model in the literature can be extended to allow for heteroscedasticity and estimation and testing in this framework is treated. Second, time-variation is introduced into the model by introducing a dynamic state space model for team strengths. The in-sample results based on eight seasons of NBA data provide weak evidence for heteroscedasticity, which can lead to notable differences in estimated win probabilities. However, persistent time variation is only found when combining the data of several seasons, but not when looking at individual seasons. The models are used for forecasting a large number of regular season and playoff games and the common finding in the literature that it is difficult to outperform the betting market is confirmed. Nevertheless, a forecast combination of model based forecasts with betting odds can lead to some slight improvements.

[1]  Bradley P. Carlin Improved NCAA Basketball Tournament Modeling via Point Spread and Team Strength Information , 1996 .

[2]  Mark E. Glickman Paired Comparison Models with Time-Varying Parameters , 1993 .

[3]  William O. Brown,et al.  Does the Basketball Market Believe in the Hot Hand? Comment , 1993 .

[4]  L. Fahrmeir,et al.  Dynamic Stochastic Models for Time-Dependent Ordered Paired Comparison Systems , 1994 .

[5]  N. C. Schwertman,et al.  More Probability Models for the NCAA Regional Basketball Tournaments , 1991 .

[6]  Ian G. McHale,et al.  Time varying ratings in association football: the all‐time greatest team is.. , 2015 .

[7]  D. Harville,et al.  The Selection or Seeding of College Basketball or Football Teams for Postseason Competition , 2003 .

[8]  Garud Iyengar,et al.  Graphical Model for Baskeball Match Simulation , 2014 .

[9]  H. Stekler,et al.  Predicting the Outcomes of NCAA Basketball Championship Games , 2012 .

[10]  Marshall B. Jones,et al.  Home Advantage in the NBA as a Game-Long Process , 2007 .

[11]  A. Elo The rating of chessplayers, past and present , 1978 .

[12]  Erik Štrumbelj,et al.  Simulating a basketball match with a homogeneous Markov model and forecasting the outcome , 2012 .

[13]  A. Timmermann Forecast Combinations , 2005 .

[14]  Carl N. Morris,et al.  Predicting Overtime with the Pythagorean Formula , 2010 .

[15]  C. Varin,et al.  Dynamic Bradley–Terry modelling of sports tournaments , 2013 .

[16]  C. Reese,et al.  Using Box-Scores to Determine a Position's Contribution to Winning Basketball Games , 2007 .

[17]  Hal S. Stern,et al.  A Brownian Motion Model for the Progress of Sports Scores , 1994 .

[18]  David A. Harville,et al.  The Home-Court Advantage: How Large is it, and Does it Vary from Team to Team? , 1994 .

[19]  L. Knorr‐Held Dynamic Rating of Sports Teams , 2000 .

[20]  Badi H. Baltagi,et al.  Testing AR(1) against MA(1) disturbances in an error component model , 1995 .

[21]  Herman Stekler,et al.  Issues in Sports Forecasting , 2010 .

[22]  Herman Stekler,et al.  Are sports seedings good predictors?: an evaluation , 1999 .

[23]  Steven B. Caudill,et al.  Predicting discrete outcomes with the maximum score estimator: the case of the NCAA men's basketball tournament , 2003 .

[24]  Mark E. Glickman,et al.  Dynamic paired comparison models with stochastic variances , 2001 .

[25]  M. Glickman Parameter Estimation in Large Dynamic Paired Comparison Experiments , 1999 .

[26]  E. Štrumbelj,et al.  On determining probability forecasts from betting odds , 2014 .

[27]  H. A. David TOURNAMENTS AND PAIRED COMPARISONS , 1959 .

[28]  Peter Reinhard Hansen,et al.  The Model Confidence Set , 2010 .

[29]  Are the "Four Factors" Indicators of One Factor? An Application of Structural Equation Modeling Methodology to NBA Data in Prediction of Winning Percentage , 2012 .

[30]  David F. Percy,et al.  Strategy selection and outcome prediction in sport using dynamic learning for stochastic processes , 2015, J. Oper. Res. Soc..

[31]  Vu,et al.  A dynamic bivariate Poisson model for analysing and forecasting match results in the English Premier League , 2012 .

[32]  Mark E. GLICKMAN,et al.  A State-Space Model for National Football League Scores , 1998 .

[33]  Dylan S. Small,et al.  The Role of Rest in the NBA Home-Court Advantage , 2008 .

[34]  R. A. Bradley,et al.  Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons , 1952 .

[35]  Chad L. Cross,et al.  Relative Importance of Performance Factors in Winning NBA Games in Regular Season versus Playoffs , 2010 .

[36]  Colin Camerer Does the Basketball Market Believe in the 'Hot Hand'? , 1989 .

[37]  B. JonesMarshall A Note on Team-Specific Home Advantage in the NBA , 2008 .

[38]  Justin Kubatko,et al.  A Starting Point for Analyzing Basketball Statistics , 2007 .