6) Outlook: What’s next?

Data Simulation with Monte Carlo Methods

Marko Bachl

University of Hohenheim

Outlook: What’s next?

Traktandenliste

1. Introduction & overview

2. Monte Carlo Simulation?

3. Proof by simulation — the Central Limit Theorem (CLT)

4. Errors and power — torturing the t-test

5. Misclassification and bias — Messages mismeasured

6. Outlook: What’s next?

Outlook: What’s next?

• Getting started with your own Monte Carlo simulation

  • … for (self-) teaching

  • … for a priori power calculation

  • … for your next methods study

Resources: For simulation experiments

• {SimDesign}: “Structure for Organizing Monte Carlo Simulation Designs”

  • Covers the whole simulation and analysis workflow

  • Extensive documentation

• Alternative: {paramtest}: Some similar capacities, less specialized.

Resources: For simulating data

• {simstudy}: Very flexible package for simulating data sets.

• {faux}: Simulate data for factorial designs.

• {simsem}: Simulate data from structural equation model specifications or objects.

Resources: Simulation for a priori power calculation

• DeclareDesign: “is a system for describing research designs in code and simulating them in order to understand their properties” — not ony power simulation, but also diagnosis of bias.

• {Superpower}: Calculate power for factorial designs, focus on ANOVA.

• Workshop by Niklas Johannes: Intro to power calculations using simulation.

Resources: Teaching with simulations

• A general framework by the author of {SimDesign}: Sigal, M. J., & Chalmers, R. P. (2016). Play It Again: Teaching Statistics With Monte Carlo Simulation. Journal of Statistics Education, 24(3), 136–156. https://doi.org/10.1080/10691898.2016.1246953

• Special section Using Simulation to Convey Statistical Concepts in Advances in Methods and Practices in Psychological Science

Resources: Faster simulation using parallel computing in R

• The Futureverse and, in particular, {furrr}: Simple way to parallelize any code written with {purrr}. Just replace map with future_map.

• datacolada blogpost on how to speed up simulations using parallel computing and convenient cloud computing services.

Resources: Reporting simulation studies

McNeish, D., Lane, S., & Curran, P. (2018). Monte Carlo Simulation Methods. In G. R. Hancock, L. M. Stapleton, & R. O. Mueller (Eds.), The Reviewer’s Guide to Quantitative Methods in the Social Sciences (2nd ed.). Routledge.

Happy simulating :)