Volume 10, Issue 4

An absorbing Markov chain was used to model the 2012 PGA Tour Golf Season. Expected number of steps until absorption was used to establish expected scores for different locations (fairway, primary rough, green, etc.) and distances from the hole. Strokes gained analysis was then performed to evaluate the quality of each shot hit by players on the 2012 PGA Tour. Skill rankings were developed, tradeoffs between distance and accuracy were assessed, and player strategy was analyzed for playing par 5s.

National Football League teams have complex drafting strategies based on college and combine performance that are intended to predict success in the NFL. In this paper, we focus on the tight end position, which is seeing growing importance as the NFL moves towards a more passing-oriented league. We create separate prediction models for 1. the NFL Draft and 2. NFL career performance based on data available prior to the NFL Draft: college performance, the NFL combine, and physical measures. We use linear regression and recursive partitioning decision trees to predict both NFL draft order and NFL career success based on this pre-draft data. With both modeling approaches, we find that the measures that are most predictive of NFL draft order are not necessarily the most predictive measures of NFL career success. This finding suggests that we can improve upon current drafting strategies for tight ends. After factoring the salary cost of drafted players into our analysis in order to predict tight ends with the highest value, we find that size measures (BMI, weight, height) are over-emphasized in the NFL draft.

We analyze the 2008 World Fly Fishing Championships data to examine two issues: (I) changes to scoring rules are proposed so that catching bigger fish is no longer a disadvantage; and (II) the relative role of chance versus competitor skill in determining the competition outcomes is investigated. For (I), a new quadratic polynomial formula for the number of points awarded for a fish of a certain length meant that the competitor who caught the biggest fish in one of the rivers was no longer disadvantaged, during the 20-min period it took to land the fish, compared to those anglers who caught many small fish. For (II), it was found that an angler A, who is actually better than angler B, has an approximate probability of 8.5% of having, overall, a worse score than angler B. By increasing the number of fishing sessions from five to seven, the probability of misclassification drops to about 7%. Other topics, such as the advantages of the proposed formula and the various fishing strategies, are also discussed.

A number of soccer officials have long debated whether to ban soccer games played at high altitude above sea level. This paper explores soccer player’s passing behavior when playing at high elevations using Copa Libertadores data. For this, I propose a range of direct indicators when playing at high altitude: the number of total passes, the number of passes in the opposition’s half, and the number of successful passes. I also review the effects on the percentage of successful passes and the percentage of successful passes in the opponents’ half of the field. Player’s passing abilities are compared for games played away above 2500 m (8202 feet) vis-à-vis those held below that threshold. The results show that the percentage of successful passes rises by about 5.6 percentage points, mostly driven by each player’s behavior in his own half. Following earlier findings by Romer (2006) and Palacios-Huerta (2014), who state that players behave conservatively under certain circumstances, I argue that players’ have prior believes about the effects of playing at high altitude and consequently their risk aversion to lose the ball increases.