A Method for Inferring Batting Conditions in ODI Cricket from Historical Data
This paper is part of a wider research programme using a dynamic-programming approach to modelling the choices about the amount of risk to take by batting and bowling teams in One Day International cricket. An important confounding variable in this analysis is the ground conditions (size of ground, nature of pitch and weather conditions) that affect how many runs can be scored for a given amount of risk. This variable does not exist in our historical data set and would regardless be very difficult to accurately observe on the day of a match. In this paper, we consider a way of estimating a distribution for the ground conditions using only the information contained in the first-innings score and the result of the match. The approach uses this information to estimate the importance of ground conditions in the determination of first innings total scores. We assume a functional form for a model of first innings scores and we estimate the parameters of our model using Monte Carlo methods. We test the impact of a significant rule change and we apply our findings to selected matches before and after the new rules came into play.
