What is Cauchy Distribution: What is the Ratio of Independent Standard Normals

Why the Ratio of Normals Is Cauchy

Submit Homework

The Cauchy distribution is a classic example in mathematical statistics tutoring because it behaves very differently from “nice” distributions. It has no mean, no variance, and extremely heavy tails. One of the most surprising facts is that the ratio of two independent standard normal variables is exactly Cauchy. This page explains why.

\(\text{If } X, Y \sim N(0,1) \text{ and independent, then } \frac{X}{Y} \sim \text{Cauchy}(0,1).\)

Why does this happen? Because the joint distribution of two independent standard normals is rotationally symmetric. When you convert to polar coordinates, the angle variable is uniformly distributed on \([0, 2\pi)\). The ratio \(X/Y\) is simply the tangent of that angle, and the tangent of a uniform angle is Cauchy. This geometric argument is the cleanest way to understand the result.

1. Start with two independent standard normals. \(X, Y \sim N(0,1)\).
2. Write their joint density. \(f(x,y) = \frac{1}{2\pi} e^{-(x^2 + y^2)/2}\).
3. Convert to polar coordinates. \(x = r\cos\theta,\; y = r\sin\theta\).
4. Use rotational symmetry. The angle \(\theta\) is uniform on \([0, 2\pi)\).
5. Form the ratio. \(\frac{X}{Y} = \frac{\cos\theta}{\sin\theta} = \cot\theta\).
6. Use the tangent identity. If \(\theta\) is uniform, then \(\tan\theta\) (or \(\cot\theta\)) is Cauchy.

Suppose you simulate two independent standard normals:

\(X = 0.84,\quad Y = -0.52\)

Then the ratio is:

\(\frac{X}{Y} = \frac{0.84}{-0.52} \approx -1.615\)

This value is typical of the heavy‑tailed Cauchy distribution.

• Thinking the Cauchy distribution has a mean or variance (it does not).
• Assuming the ratio of normals is normal (it is not).
• Forgetting that independence of \(X\) and \(Y\) is required.
• Confusing the Cauchy with the t‑distribution (t with 1 degree of freedom is Cauchy).

The Cauchy distribution is essential for understanding heavy‑tailed behavior, robustness, likelihood theory, and pathological examples in statistics. It appears in graduate exams because it breaks many standard assumptions and forces students to think carefully about distribution properties.

This idea connects directly to:

• Math Statistics & Probability Theory (parent spoke)
• Tutoring Services
• Question Hub
• Statistics Post Hub