What is it about?

In 1931 WS Gosset ("Student") offered his own analysis of The Lanarkshire Milk Experiment (LME) of 1931. The original analysis by Leighton and McKinlay and Student's reanalysis are considered from a more modern perspective and various lessons for the design and analysis of experiments are drawn.

Featured Image

Why is it important?

At the time of Student's analysis the modern theory of design of experiments as initiated by RA Fisher and continued by his successor at Rothamsted, Frank Yates, had not been fully developed. The LME is of a form that was subsequently referred to as 'an incomplete blocks design', with treatments varied both within and between schools. The implications of this for analysis are examined using this more modern perspective.

Perspectives

I was a member of the data safety monitoring board (DSMB) for the TARGET study. The design of this is strongly analogous to that of the LME, a fact I was not aware of when serving on the DSMB. When researching the history of the LME I then realised the similarity and the implication that the approach of the Rothamsted School to analysis of designed experiments would be valuable. This paper represents the result of applying that approach.

Professor Stephen J Senn
Consultant Statistician

Read the Original

This page is a summary of: Student and the Lanarkshire milk experiment, European Journal of Epidemiology, December 2022, Springer Science + Business Media,
DOI: 10.1007/s10654-022-00941-x.
You can read the full text:

Read

Contributors

The following have contributed to this page