Wrapping it up
“Let the data speak” is a catchy and powerful slogan, but as we’ve seen earlier, data itself is not always enough. It’s worth remembering that in many cases “data cannot speak for themselves” (Hernán, Robins, 2020) and we might need more information than just observations to address some of our questions.
In this chapter, we learned that when thinking about causality, we’re not limited to observations, as David Hume thought. We can also experiment – just like babies.
Unfortunately, experiments are not always available. When this is the case, we can try to use observational data to draw a causal conclusion, but the data itself is usually not enough for this purpose. We also need a causal model. In the next chapter, we’ll introduce the Ladder of Causation – a neat metaphor for understanding three levels of causation proposed by Judea Pearl.
