A Statistical Exploration of Duckworth-Lewis Method Using Bayesian Inference

TL;DR

This paper applies Bayesian inference to improve the Duckworth-Lewis method for rain-affected cricket matches by creating a more accurate and monotonic resource table, enhancing prediction of first innings scores.

Contribution

It introduces a Bayesian approach to address non-monotonicity in the D/L resource table, resulting in better predictions for rain-affected cricket matches.

Findings

Bayesian inference produces a monotonic resource table.

Improved prediction accuracy for first innings scores.

More suitable for rain-affected limited overs cricket matches.

Abstract

Duckworth-Lewis (D/L) method is the incumbent rain rule used to decide the result of a limited overs cricket match should it not be able to reach its natural conclusion. Duckworth and Lewis (1998) devised a two factor relationship between the numbers of overs a team had remaining and the number of wickets they had lost in order to quantify the percentage resources a team has at any stage of the match. As number of remaining overs decrease and lost wickets increase the resources are expected to decrease. The resource table which is still being used by ICC (International Cricket Council) for 50 overs cricket match suffers from lack of monotonicity both in numbers of overs left and number of wickets lost. We apply Bayesian inference to build a resource table which overcomes the non monotonicity problem of the current D/L resource table and show that it gives better prediction for teams in first innings score and hence it is more suitable for using in rain affected matches.