A Feature Extraction Tutorial Using the Titanic Dataset — Large data sets are often awash with data that is difficult to decipher. One may think of textual data, names, unique identifiers, and other sorts of codes. Frequently, people analyzing these datasets are quick to discard these variables. …

How to test your directional hypothesis with this ANOVA post-hoc test — It’s a situation many of us face: You just ran an ANOVA, and your results are significant… but what next? We basically know that something is going on, but what exactly? Which treatments are making the difference? This is where planned contrasts come in. They sound more complicated than they…

Or: Why do the OLS regression (lm) and ANOVA (aov) function sometimes differ, and how to fix it using the car package. — Imagine this scenario: You are running an ANOVA in R while controlling for other variables (technically, an ANCOVA). However, the results seem weird: The order of the independent variables matter and influence the results — how can that be? And if you try to enter the same model as a…

A guide to graphically presenting the marginal effects of key variables in datasets. — It’s a known dilemma: You know that your variable X1 impacts your variable Y, and you can show it in a regression analysis, but it is hard to show it graphically. The reason is that there is another variable impacting Y, namely X2, and only after the effect of X2…

How to test and report the impact of a categorical independent variable on an interval dependent variable. — Analysis of Variance, or ANOVA, is a frequently-used and fundamental statistical test in many sciences. In its most common form, it analyzes how much of the variance of the dependent variable can be attributed to the independent variable(s) in the model. It is most often used to analyze the impact…

How to test for and report mediated effects — This tutorial will explain what a mediation analysis is, show how to simulate data for mediation analysis, run the necessary statistical procedures, and write it up for publication. The introduction will be concerned with establishing what a meditation exactly is. If you know what mediation is and just want to…

The fastest & easiest way to extract sentiment from strings. — The Sentimentr package for R is beneficial in analyzing text for psychological or sociological studies. Its first big advantage is that it makes sentiment analysis simple and achievable within a few lines of code. …