PS: He wasn't a 'statistician'... his title read: "Senior Animal Husbandman in Animal Genetics, Bureau of Animal Industry, United States Department of Agriculture" !
Wright, S. (1921). Correlation and
causation. Part I Method of path coefficients. Journal
of agricultural research, 20(7), 557-585.
[CITED BY 2119, GOOGLE.SCOLAR; Aug.2018: 4,415 times!].
I just want to point out that this paper, to a large extent, also laid the foundation for today's trend in genetics - epigenetics/developmental genetics. He based his arguments on physiological and developmental pathways. Only Sewall Wright saw genetics more clearly than any of his contemporaires. This is sheer genius
ReplyDeleteFurther, to my surprise, most modern geneticists, particularly the ones dealing with humans are unaware of this approach, as well as the need for this way of thinking about genes, gene action and phenotype. Fortunatley, the landscape is changing, albeit slowly!
ReplyDeleteThanks, I know little about genetics research, of course; but I see in his paper some themes that are even broader reaching than I found initially, now that you mentioned his genius: he has the ingredients of the Latent Change Score modeling approach in it too, the "Gain 0-33 days", which 'causes' the "Weight at 33 days", along with Weight at birth", and there is a Rate of Growth" separate element too, which...I need to go back to the paper and understand better.
ReplyDeleteIn other words, another read of this almost a century old paper is worth our time!