When academic experts like me try to share our knowledge on social media, we attract our own special kinds of reply guys (and gals!).

Here's my list of academic reply guys! 👇

The Traffic Cop. This type wants you to "Stay in your lane!". You can use social media or you can know what you're talking about but you can't do both! The traffic cop understands that democratic debate works best when everybody involved is ignorant.

The Trash Panda. The trash panda is very picky and will only consume information from unofficial sources. Everything else is fake news! People with PhDs, Government officials, World recognized experts. BAD! Facebook posts, WhatsApp viral videos, Youtube comments. GOOD!

The Conspiracy Theorist. This type assumes the only reason you're giving advice is you're trying to control them. So you want them to ask an expert how to solve a problem, then listen to the answer and then do what that person says? No sir! That sounds like mind control!

The Contrarian. There is nothing you can do to convince this type. If what you're saying is unpopular, they will side with you and once your opinion becomes popular, they will be on the other side. That's just how it is.

Statisticians like me say CORRELATION ISN'T CAUSATION but that's not the whole story.

There are at least FOUR different scenarios!

A thread. 🧵

1. CORRELATED BY CHANCE. There's always a possibility that variables will correlate by chance. If you have a lot of data, you're almost certain to get a few high correlations. You will know you're in this situation if the same variables are much less correlated in new data.

2. CORRELATED DUE TO STRUCTURE. Clocks are correlated with each other but there's nothing about Clock A that can be changed in order to cause a change in Clock B or vice versa. There is no third thing you can change that will cause both clocks to change. There is no causation.

You might be tempted to say that the clocks have the common cause of being created by humans. Imagine two random stars that have a cyclical change in brightness every 24 hours. They will be correlated as well. It's not about who created them. It's about their similar structure.

3. MURKY CAUSATION. In the simplest case, if A and B are correlated and there is some causation then this could mean that A causes B, B causes A or some third thing C causes both A and B. In the most complex case, there could be complicated feedback loops between A and B.

I've noticed a kind of tribal individualist that's common online. They move in mobs, make nearly identical objections, claim not be a group or believe in groups, and are extremely hostile to the identities of others.

They've also been REALLY BAD for online scientific discourse.

Many people believe in individualism so strongly that they seem incapable of perceiving anything to do with groups. They don't understand sociology as a category of knowledge or social problems as anything more than a collection of the unique challenges of individuals.

Many individualists don't believe in sociology. They see it as a false science. Since groups don't exist for them, only individuals, they don't think sociological can exist either. After all, how can one scientifically study groups when groups aren't real?

Many individualists don't understand public health. Inherent in the idea of public health is the idea that you personally might have to sacrifice for the well-being of others. That doesn't sit well with them so they reject public health as a false ideal.

Since many individualists claim not to be part of groups, they often substitute group identity with pledges of allegiance to ideas. They might say "I believe in logic and reason". They will say this even when they've long since abandoned logic and reason.

The Pandemic has got me thinking. On TV, people of the future are always very comfortable with data. They collect it. They analyze it. They adjust their strategies in real time. Not in days or hours or minutes but often literally in SECONDS.🧵👇

They run simulations of different outcomes. The simulations aren't always right but they seem to put them in the ballpark of what's reasonable. People take the simulations and data seriously. They factor them into their planning.

Even when the future government is evil, it's still smart. Even when the future government is rigid and uncreative in how it responds to stuff, it's responses are still logically related to the assumptions it has made, the data it has collected and the analyses it has performed.

Unfortunately, our civilization is NOT THAT. We collect data but usually haphazardly and in ways that make it hard to draw any conclusions. It often takes a long time for us to make sense of data. Politicians often throw out the numbers completely.

We don't seem to care what the probability of various outcomes are. We don't seem to use probabilities when making decisions. Perhaps, you're thinking about the election predictions and about how they were close but not quite right.