Why use relative risks?

David Gordon

One of the key questions that readers of the perception of necessities graphs and reports want answered is: are the differences between groups (e.g. Men vs Women, older people vs young adults, etc) ‘significant’, that is whether the differences observed are likely to have occurred by chance or not.

To help answer this question, the PSE research team have used “relative risk” rather than “hypothesis testing”. This statistical note sets out the differences between the two approaches and the reasons for the choice.


Publication date: 
Dec 21 2012