# Base Rates and the Base Rate Fallacy: Definition, Examples

Probability > Base Rates and the Base Rate Fallacy.

## What are Base Rates?

The base rate for being struck by lightning: about 1 in 12,000. Image: NOAA.gov

The term “base rates” has a slightly different meaning depending on where you use it. In general, a base rate is the probability of some event happening. For example, your odds of being struck by lightning in your lifetime is currently about 1 in 12,000 and your odds of developing a brain aneurysm — 1 in 50. A more narrow definition of base rate: the probability of an event happening without intervention. You can stay indoors to avoid lightning strikes, or lower your blood pressure to reduce the risk of aneurysms. These reduce personal risk, but do not change base rates.

• In probability and statistics, “base rate” usually means the same thing as prior probabilities (used in Bayesian Probabilities). For example, let’s say 10% of people have visited an Orlando theme park in the last ten years and 90% had not. The base rate for the number of people who have visited an Orlando theme park in the last ten years: 10%.
• In epidemiology, a base rate is more specific. It is the prevalence of a disease, symptom, or characteristic in a specified population. For example, the prevalence of autism in the U.S. (as of 2014): 1 in 68 children.
• In banking, a base rate (also called the discount rate) means something entirely different. It’s the interest rate at which a central bank lends money and the level below which domestic banks cannot lend.

## The Base Rate Fallacy / Bias

When you ignore (or don’t understand) general statistical data and make a judgment based on specific data, you’re falling prey to the base rate fallacy. This happens all the time; People not well-versed in the technical rules of prior probability usually don’t take the prior statistical data into account, as it doesn’t seem relevant.

If you can’t wrap you’re head around Bayesian probabilities, you aren’t alone. When given data about a women’s chance of having breast cancer, given a positive mammogram result, an alarming 80% of physicians got the probabilities wrong. See: Even Physicians Don’t Understand Statistics.

------------------------------------------------------------------------------

If you prefer an online interactive environment to learn R and statistics, this free R Tutorial by Datacamp is a great way to get started. If you're are somewhat comfortable with R and are interested in going deeper into Statistics, try this Statistics with R track.