Our intuitions about probability are systematically broken. Not occasionally wrong. Systematically wrong, in predictable ways.

The birthday problem

How many people do you need in a room for there to be a 50% chance that two of them share a birthday?

Most people guess somewhere around 180. The real answer is 23.

The calculation: the probability that $n$ people all have different birthdays is

$$P(\text{no match}) = \frac{365}{365} \cdot \frac{364}{365} \cdot \frac{363}{365} \cdots \frac{365-n+1}{365}$$

So the probability of at least one shared birthday is $1 - P(\text{no match})$.

def birthday_probability(n):
    p_no_match = 1.0
    for k in range(n):
        p_no_match *= (365 - k) / 365
    return 1 - p_no_match

for n in [10, 23, 30, 50, 70]:
    p = birthday_probability(n)
    print(f"n={n:3d}: {p:.1%}")

Output:

n= 10: 11.7%
n= 23: 50.7%
n= 30: 70.6%
n= 50: 97.0%
n= 70: 99.9%

The reason this surprises us: we think about sharing our own birthday with someone else. But the question is about any pair sharing any birthday. With 23 people there are $\binom{23}{2} = 253$ pairs.

Bayes and base rates

Suppose a disease affects 1 in 1000 people. A test for it is 99% accurate. You test positive. What is the probability you have the disease?

Most people say about 99%. The actual answer is about 9%.

Using Bayes' theorem, with $D$ = disease and $+$ = positive test:

$$P(D \mid +) = \frac{P(+ \mid D) \cdot P(D)}{P(+)}$$

The denominator $P(+)$ includes the false positive rate. Even a very accurate test applied to a very rare condition produces mostly false positives.

Why this matters

Bad probability intuition leads to real mistakes: medical misdiagnoses, legal reasoning errors, poor risk assessment. Understanding that our gut feelings are calibrated wrong is the first step to correcting them.

The fix isn't to distrust intuition entirely. Build better habits: ask about base rates, count all the pairs, do the calculation.