From the course: The Data Science of Economics, Banking, and Finance

Unlock the full course today

Join today to access over 25,000 courses taught by industry experts.

Correlation and causality in economic data

Correlation and causality in economic data

From the course: The Data Science of Economics, Banking, and Finance

Start my 1-month free trial Buy for my team

Correlation and causality in economic data

“

- [Instructor] There's a saying in the data world that the plural of anecdote, or an interesting story, is not data, that data is more than just a collection of anecdotes. Now this particular saying, there's some dispute about exactly what they said and what it means, but this is said often enough. The idea here is a collection of potentially biased and non-representative stories does not make for a dataset. An extension of that is that the plural of correlation is not causation. A recommendation engine may be able to say, "I've got data about billions of book purchases, and I know that if a person purchases this book, they have a 47% chance of purchasing this book also." That's great. That's a correlation, and it may be useful, but it's not a causal relationship. They are fundamentally different things. I'm sure you're familiar with the related saying that correlation doesn't imply causation. It's not enough to simply know that when people stand at the back of the car and they put…

Contents