Hi EricC I will drop out of this soon because of time conflicts. But an edit or two below:
> On Mar 31, 2026, at 15:47, Eric Charles <[email protected]> > wrote: > > I'll also note that "function" can't do the work on its own to explain > evolution. We still need to know why some functions are favored by selection > and others are not. EricS seemed to indicate that we assess "fit" by > determining if animals are "happy"…. In this case, no. Exactly not that. The long tedious first post from me was an objection to vague gestures at what “fit” means, using “happy” as an example of vagueness. The aim in the passage was to explain the role of Fisher’s supplying specific constructions of summary statistics defined on instances of population processes. Not to say that we have to do things Fisher’s way; I had other comments on that question. Rather, to say that one doesn’t generate a tautology by first providing a definition of what quantity you are pulling from data, to which you are trying to fit a regression model. > but the metaphor of "fit" is like a key in a lock. To explain evolution you > need the matching of form-and-function-to-a-particular-environment. That > matching *sometimes* increases reproductive success, and *sometimes* the > traits in question are hereditary. All the sometimeses and hedges are certainly right. I didn’t belabor them. But for sure, if one writes regression models, it is because there is supposed to be data scatter that the model isn’t trying to account for. Also the other comments here and there in the threads about all the things that one or another regression model will leave out; where they go in a Price equation decomposition, and the question of whether your regression model falls apart when some formerly-unconsidered dummy variables are added. I didn’t end up saying as much about flavor text in these threads as I guess the main thread would have motivated. I guess that is because I got sidetracked on trying to provide language for an account of what geneticists and others are doing, behind the various human-language terms, since it wasn’t clear to me that all that was familiar. > Population genetics combined with field research can be very powerful along > those lines, but the math of population genetics on its own, floating out in > the ether, can't do it at all. Again, yes. Both of the last two replies to Nick today were meant to say something specific about those limitations. There is _much_ more that can be said. A regression model at all is, only in a _very_ generous widening of the notion of “causation”, a “causal model”. But I have comments littered here and there in the messy posts about how other domains in functional biology go after those other forms of descriptions. Anyway, I agree with you; time for me to stop. I will hope that in there, there was some commentary on extant practice that Nick will at some point find useful. Eric .- .-.. .-.. / ..-. --- --- - . .-. ... / .- .-. . / .-- .-. --- -. --. / ... --- -- . / .- .-. . / ..- ... . ..-. ..- .-.. FRIAM Applied Complexity Group listserv Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom https://bit.ly/virtualfriam to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com FRIAM-COMIC http://friam-comic.blogspot.com/ archives: 5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/ 1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
