A robust simulation study to compare measures for meaningful batting averages in cricket
Abstract
In cricket, the traditional batting average is the most common measure of a cricket player’s batting performance. However, the batting average can easily be inflated by a high number of not-out innings. Therefore, in this research eight alternative methods will be used and compared to the traditional batting average to estimate the true batting average. It is also known that there is a range of different batters within a cricket team, namely first order, middle order, tailenders and a special class of players who can both bat and bowl known as allrounders. There are also different formats of international cricket, namely Test, One-Day International (ODI), and Twenty20 International (T20I) cricket, where Test cricket has unlimited overs compared to the limited overs of ODI and T20I cricket. A method for estimating the batting average should be able to account for all of this variability. By using the smoothed bootstrap in this study, a distribution can be formed for each player and each estimation method so that the variability of each distribution can be compared. Despite increasing levels of participation and popularity in the cricket fraternity, women’s cricket has not received the same exposure compared to men’s cricket in terms of sports data analytics. Therefore, this study will look at measuring the batting ability of female batters. However, the methods considered and the conclusions reached in this study are also valid for men’s cricket.