# Type I error

An error that occurs in significance testing when the null hypothesis is rejected when it is actually true.

Also known as a 'false positive'.

The probability of a false positive is often known as the significance level.

For example a significance level of 5%: meaning in this case that there would only be a 5% probability that the observed result could have happened by chance alone.

However the significance level is also sometimes expressed as (1 - the probability of a false positive).

For example in the same situation the significance level might alternatively be quantified as (1 - 5%) = 95%.

Meaning that there is 95% confidence that the observed result did * not* happen by chance alone.

For the avoidance of doubt, it is therefore always best to be explicit about which basis the significance level is being quoted on.