Type I and Type II Errors

“A test can raise a false alarm or miss a real signal; reducing both comes at a cost.”

01 / PLAINLY

What it means, plainly

In a test, the null hypothesis is the starting claim being challenged. A Type I error rejects it when it is true; a Type II error fails to reject it when it is false.

02 / CONTEXT

A little more

In hypothesis testing, Type I means rejecting a true null; Type II means failing to reject a false null. Their probabilities and consequences depend on the specific decision and scenario.

03 / WHY IT MATTERS

Why it matters

It makes you consider which kind of mistake has worse consequences before choosing a decision rule.

04 / EXAMPLE

A familiar example

A smoke alarm sounding without fire gives a false alarm; staying silent during a fire makes the opposite error.

05 / LIMIT

What it does not mean

Type I is not always the graver mistake, and non-rejection does not prove there is no effect.

06 / NOTICE

Notice it in your day

Draw a grid with ‘signal present’ and ‘signal absent’ against ‘test alerts’ and ‘test stays quiet.’ Label the two errors.

FINAL NOTE

The idea worth keeping

Define which error matters more before setting a decision threshold.

QUESTIONS / 02

Questions people still have

What is a Type I error?

Rejecting a null hypothesis that was actually true.

Does failing to reject the null prove there is no effect?

No. It only says the test did not reject it in that analysis.