Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Unit
Browse By Session Type
Search Tips
Personal Schedule
Sign In
Session Type: Training Session
In this course we will learn how to write Monte Carlo simulations in R. Monte Carlo simulations are an essential tool of inquiry, useful both for small-scale investigations and for formal methodological research. Simulation can assess, for example, how much re-testing biases a regression discontinuity design due to undermining the measurement properties of a test score. Our focus is on the best practices of simulation design. Overall, we will show how a specific simulation framework allows for rapid exploration of the impact of different design choices, measurement qualities, and data concerns, and show how simulation can answer questions that are hard to answer using direct computation. For example, available algebraic formulas are often based on asymptotic approximations, which might not “kick in” if sample sizes are moderate; simulation can provide an answer.
In this session we will work through two simulation case studies, showcasing a modular programming approach for good design. Code, along with an on-line open-source textbook, will be provided and demonstrated. Students should bring laptops, with R and RStudio installed, to follow along. By the end, students will be able to adapt provided code to their own purposes moving forward. Some familiarity with R is assumed.