I think it's mostly about interpretation. The matching law basically is a GLM, and diffusion models are also applied in finance and physics, and many RL models are used in settings that have nothing to do with cognition. The RW mechanism is basically online gradient descent.
-
-
Replying to @macstrelioff @djnavarro and
Are you saying that because gray exists that black and white are "just shades of grey"? We can take each model on a case-by-case basis and situate it as being more one thing over another, because most models are.
2 replies 0 retweets 0 likes -
Replying to @o_guest @djnavarro and
I think so. So would you say "multiplying" is different from "scaling" or "weighting"? A really amazing thing about math for me is that an operation or model can be used to spot connections between otherwise unrelated phenomena.
1 reply 0 retweets 0 likes -
Replying to @macstrelioff @djnavarro and
I can't tell if we're on the same page. But yes, pragmatics of words is real, I agree.
1 reply 0 retweets 0 likes -
Replying to @o_guest @djnavarro and
I think there's two perspectives here. I'm not dogmatic about either one. I'm usually pragmatic when I teach or communicate ("this is black"), and focused on spotting connections between seemingly disparate phenomena when I lay awake at night ("any color - all light = black
")1 reply 0 retweets 1 like -
Replying to @macstrelioff @djnavarro and
That was my point. What's important here though is to understand that there are people out there who deny that there are coherent groupings of modelling. Those are who we need to reach.
1 reply 0 retweets 1 like -
Replying to @o_guest @macstrelioff and
The space of modelling and stats work is inherently structured around coherent types of modeling and stats. Those who run ANOVAs on their data and those who run cognitive models are different regardless of the spectrum between them.
1 reply 0 retweets 0 likes
I only do cog modelling and don't do data collection or stats analyses as inferential statistics, so I am like the total odd-one-out sometimes in psych/cogsci. In the same way modelling might seem strange to non-modellers, some of the assumptions like in NHST seem bonkers to me.
-
-
Replying to @o_guest @macstrelioff and
Unless those who do stats analyses of data think, for example, participants are like an ANOVA in a theoretically meaningful way (as opposed to seeing the ANOVA as a tool for understanding the data), there's a really important difference between that and cognitive modelling.
0 replies 0 retweets 1 likeThanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.