[DS Daily] Reverse Causality
It's like causation, but in reverse.
Reverse causality means that X and Y are associated, but not in the way you would expect. Instead of X causing a change in Y, it is really the other way around: Y is causing changes in X. In epidemiology, it’s when the exposure-disease process is reversed; In other words, the exposure causes the risk factor. “…one may be tempted to say that low social status causes schizophrenia, [but] another plausible explanation is that schizophrenia causes downward social mobility…” ~ Gerstman** Due to the fact that Y unexpectedly comes before X, reverse causality bias is sometimes called the “cart before the horse bias.” StatisticsHowTo.com
You may think your marketing spend is causing your revenue, but at some point your revenue might be causing your marketing spend. (Dang, low numbers yesterday → let’s pump up the spend.)
For example, you might jump to the conclusion that rain causes people to buy more of your product. But in reality, it could be that people buy more of your product when they know it's going to rain because they want to prepare for bad weather. This is an example of reverse causality.
Great blog post by Indeed on reverse causality. Down in the article they describe simultaneity.
While reverse causality and simultaneity have similar definitions, the two terms aren't the same. In reverse causality, only Y causes a behavior change. However, simultaneity is when variables on both sides of a model equation impact one another at the same time. Here, X causes a change in Y, and Y causes a change in X. In simultaneity, the flow moves right to left (X to Y) and left to right (Y to X), unlike reverse causality, which moves from left to right (Y to X). Simultaneity occurs in conditions with jointly determined variables.
The "Matthew effect" is a common example of simultaneity. This is the belief that intellects with high status tend to receive more credit for similar achievements than those with lower status. The high-status intellect then causes them to receive more rewards than those of lower status. As a result, the high status becomes magnified and continues the cycle of advantages, leading to more rewards.
Why do I care about reverse causality?
Reverse causality is a common issue that can lead to incorrect conclusions in decision-making. For example, if you invest in a certain type of stock because you think it's popular and the stock price goes up, you might be tempted to conclude that your investment caused the price to go up. However, it could be that the stock price went up because of some other factor, and your investment was just a coincidence. If you make decisions based on this incorrect conclusion, you could lose a lot of money.
Got more to say? Bring it on in the comments below and don’t forget to smash the ❤️ button!