Mill’s methods of causal inference (student stuff) .[embedded content] As we all know, R. A. Fisher was not too happy about Mill’s method of difference, since it, according to him, built on the impossible requirement of being able to compare identical units under different circumstances. Fisher instead favoured the experimental method of randomized treatment assignment. But if you cannot assign treatment randomly — as in most observational studies — there is much that supports Mill’s method of difference for making causal inferences.
Topics:
Lars Pålsson Syll considers the following as important: Theory of Science & Methodology
This could be interesting, too:
Lars Pålsson Syll writes How Einstein taught me a great lesson
Lars Pålsson Syll writes The Keynes-Ramsey-Savage debate on probability
Lars Pålsson Syll writes A philosopher’s look at science
Lars Pålsson Syll writes Why yours truly is a critical realist
Mill’s methods of causal inference (student stuff)
.
As we all know, R. A. Fisher was not too happy about Mill’s method of difference, since it, according to him, built on the impossible requirement of being able to compare identical units under different circumstances. Fisher instead favoured the experimental method of randomized treatment assignment. But if you cannot assign treatment randomly — as in most observational studies — there is much that supports Mill’s method of difference for making causal inferences.