What Is a Type II Error?
A Type II error occurs when a statistical test fails to reject a null hypothesis that is actually false. In plain terms, the test misses a real effect or difference that exists. It is also called a false negative, and its probability is usually denoted by the Greek letter beta.
Investors meet this idea when they test whether a backtest of a trading strategy, a fund manager's track record, or an academic finding reflects genuine skill. The null hypothesis is usually that there is no edge. If a real edge exists but the data are too noisy to show it, the researcher may conclude the strategy does not work when it actually does.
How It Relates to Other Errors
Hypothesis testing has two main kinds of mistakes. A Type I error rejects a true null hypothesis, which is a false positive. Its probability is set by the significance level, often called alpha. A Type II error is the opposite mistake. The two trade off against each other: making a test stricter to reduce false positives generally makes false negatives more likely, unless the sample is larger or the real effect is bigger.
Why It Happens
Several factors raise the chance of a Type II error:
- A small sample, which leaves the data noisy.
- A small true effect that is hard to separate from random variation.
- High volatility in the returns being measured.
- A very strict significance threshold.
The probability of avoiding a Type II error is called statistical power, and it equals one minus beta. Researchers often plan studies so power is high enough to detect effects of a meaningful size.
Why It Matters to Investors
A Type II error can lead an investor to dismiss a method that actually works. Because markets are noisy, many years of return data may be needed before a real edge becomes statistically visible. A result that is "not statistically significant" does not prove that something has no effect. It only means the evidence was not strong enough to show one. Keeping this distinction in mind helps readers interpret backtests, research papers and performance claims more carefully.
Updated November 2, 2026. For general education only; not financial, tax or legal advice.