The biggest problem I face in trying to work through rugby league analytics is a lack of useful, reliable, easy to source data to analyse. For this post, I had to do it myself.
I recorded 1,000 sets of six from the 2018 season so far, ranging from a Titans-Warriors pre-season game and finishing during the Titans-Bulldogs game in round 15. A thousand may sound like a lot but given there are about 80 sets of six per game, it’s about a dozen games worth of material. We are working with a relatively small sample size and that the probabilities we estimate may not precisely align with reality. If I had the time and patience (a salary could substitute for time and patience), I could go through the entire history of the NRL and do a better job. This site’s motto is “you get what you pay for”.
But today is not about solving problems once and forever. There are a number of ways to solve a given problem and the techniques and data presented here are hopefully what will be a foundation to build upon. This post is about demonstrating that rugby league can be analysed statistically and useful conclusions can be drawn.