Type II Error

Failing to detect something real—concluding there is no effect when one actually exists. A Type II error (false negative) means your test lacked the power to find a genuine signal. In business, this is killing a product that was actually working but measured with too small a sample, or dismissing a strategy that needed more time to show results. The cost is invisible: you never know what you missed.

When to use it

When interpreting 'negative' results from experiments, A/B tests, or pilot programs; when deciding to kill or continue a project that hasn't shown results yet; when sample sizes are small or test durations are short.

How it can help

Protects against premature abandonment. When an A/B test shows 'no significant difference,' a Type II error means the difference might exist but your sample was too small to detect it. Before killing a product, campaign, or strategy based on 'no results,' ask: did we have enough statistical power? Was the test duration sufficient? Many great ideas die from Type II errors disguised as data-driven decisions.