Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
A strategic and statistically based experimental design is a key component of Reduction, and the backbone of reproducible research. Design basics consist of formal structuring of input variables and clearly defined experimental units. Formal designs can evaluate two or more input factors simultaneously, identify and prioritise the most important inputs, and identify interactions where most discovery occurs.
The 3R principles provide an ethical framework for animal research throughout the world. However, despite the increasing awareness of these principles, there is still a lot of room for improving their implementation, especially when it comes to reduction. By combining Bayesian statistics with a shift in experimental design, here we present an entirely new idea to reduce animal numbers within experiments.