We develop a Markov model of curling matches. This enables strategic and econometric analyses to be performed alongside computer simulation work.
We develop a Markov model of curling matches, parametrised by the probability of winning an end and the probability distribution of scoring ends. In practical applications, these end-winning probabilities can be estimated econometrically and are shown to depend on which team holds the hammer as well as the offensive and defensive strengths of the respective teams. Using a maximum entropy argument, based on the idea of characteristic scoring patterns in curling, we predict that the points distribution of scoring ends should follow a constrained geometric distribution.
We provide analytical results detailing when it is optimal to blank the end in preference to scoring one point and losing possession of the hammer. Statistical and simulation analysis of international curling matches is also performed.
Our work adds to the theory and application of sports analytics, especially Markov models, and to the econometric and strategic analysis of curling matches.
