Methods Bites

Blog of the MZES Social Science Data Lab

regplane3D: Plotting 3D regression predictions in R

2021-03-19 19 min read tutorials [Denis Cohen Nick Baumann]

The interpretation and presentation of empirical findings from (generalized) linear models has come a long way in the social sciences. Researchers increasingly visualize substantively meaningful quantities of interest such as expected values, first differences, and average marginal effects and consistently include uncertainty estimates in the form of analytical, simulation-based, or bootstrapped confidence intervals. However, existing interpretations and presentations are typically restricted to bivariate patterns which show (changes in) expected values as function of a single predictor, holding all else constant. This can be a significant limitation, especially when substantive inquiries focus on the interplay of two variables in predicting an outcome. To interpret and visualize such applications effectively, researchers must extend their presentations to include a third dimension. In this Methods Bites Tutorial, Denis Cohen and Nick Baumann introduce and showcase the regplane3D package, a tool for plotting 3D regression predictions in R. Continue reading

Applied Bayesian Statistics Using Stan and R

2020-01-30 64 min read tutorials [Denis Cohen]

Whether researchers occasionally turn to Bayesian statistical methods out of convenience or whether they firmly subscribe to the Bayesian paradigm for philosophical reasons: The use of Bayesian statistics in the social sciences is becoming increasingly widespread. However, seemingly high entry costs still keep many applied researchers from embracing Bayesian methods. Next to a lack of familiarity with the underlying conceptual foundations, the need to implement statistical models using specific programming languages remains one of the biggest hurdles. In this Methods Bites Tutorial, Denis Cohen provides an applied introduction to Stan, a platform for statistical modeling and Bayesian statistical inference. Continue reading