In this paper, we will discuss a method of building a predictive model for Major League Baseball Games. We detail the reasoning for pursuing the proposed predictive model in terms of social popularity and the complexity of analyzing individual variables. We apply a coarse-grain outlook inspired by Simon Dedeos' work on Human Social Systems, in particular the open source website Wikipedia  by attempting to quantify the influence of winning and losing streaks instead of analyzing individual performance variables. We will discuss initial findings of data collected from the LA Dodgers and Colorado Rockies and apply further statistical analysis to find optimal betting points using a coarse-grain approach. We will apply Bayes' Theorem to add predictive power to a naive model using winning and losing streaks. We will discuss possible shortcomings of the proposed using Bayes' approach and address the question as to whether or not baseball wins and losses can be produced using a random process.
Date of Degree
Master of Science (MS)
Mathematics and Statistics
Science, Engineering and Technology
Tait, Jordan Robertson, "Building a Predictive Model for Baseball Games" (2014). All Graduate Theses, Dissertations, and Other Capstone Projects. 382.
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License