Showing causality

Effects things have on other are sometimes indirect. Let’s take an example involving a soccer ball and a broken glass. Sometimes, you will break a glass by shooting the ball right onto it. But sometimes not. Sometimes, the ball will land next to a cat, a cat peacefully sleeping on someone’s lap. Sometimes, the cat will end up scared which will result in a jump right onto a table, table on which was the glass¹. Indirect.

And, sometimes, it is important to investigate how these indirect effets are chained. It is known that people are less likely to buy drugs with complex name². But why? What is the chain behind this effect?

Mediation analysis is a statistical tool that can be use to find out that the reason why people are less likely to buy drugs with complex name is because they percieved the drugs as more dangerous. While there are several ways to conduct mediation analysis, the JSmediation package implements the best one of them³: joint-significance.

Have a look at the documentation and give it a shot!