Statistically significant

This is a simple explanation of what ‘statistically significant’ means.

This one minute animated video from TVNZ demystifies some of the technical language.

Transcript

What does ‘statistically significant’ mean?

In research, a result is ‘statistically significant’ if it is unlikely to have occurred by chance.

Scientists usually use the term if the odds of an event happening at random are less than one in twenty.

However, in research, the word ‘significant’ doesn’t necessarily mean ‘important’ – it just means that the finding may be true. When statisticians say a result is "highly significant" they mean it is very probably true. They don’t mean the results will be life-changing!

For example, a study might declare that South Islanders were more intelligent than North Islanders by one twentieth of an IQ point. The result could be ‘statistically significant’, meaning it’s probably true – but the difference would be so small it as to be utterly ‘insignificant’, in practice.

And that’s ‘statistically significant’.