2 Preparation

2.1 The Model Comparisson Approach

This step by step resource follows closely the Model Comparison Approach (MCA) proposed by Charles Judd and colleagues1. The MCA is framework for understanding and reporting data analysis. It is grounded in just a few core concepts from statistical modeling and statistical inference and allows a common language to understand the most popular statistical tests in social sciences. If this is your first contact with the MCA you might miss the cookbook appeal of matching a specific research question with a specific statistical test. The main benefit form the MCA is that you will no longer be stuck to a specific data analysis recipe: i) it becomes clear that the different linear models all resort to the same model building principles (from linear regressions to ANOVAs/ANCOVAs and to mixed measure models) and that; ii) it also becomes clear what statistical inference is saying about your models and when it makes sense to actually listen to it.

2.2 Load the Dabase

This step by step uses a mock database for a Happiness Study with undergraduate and graduate students. The fist step before diving into each of the other chapters is to Download the data base load it in the R environment. The data base of the Happiness Study is available here. A the relevant code is here:

Happy <- read.csv("Happy.csv")

  1. Judd, C. M., McClelland, J. C., & Ryan, C. S. (2008). Data Analysis: A Model Comparison Approach. Routledge.↩︎