I am not sure if it’s the motivated reasoning speaking but I have a feeling that
if a distribution has 2 or more peaks it is customary to delineate in the valleys and have different words to indicate data points close to each peak [i.e. cleave reality at the joints] [e.g. autism]
If a distribution only has 1 peak, then you would have words for [right of peak] and [left of peak] and maybe [normal (stuff around the peak)] [e.g. height]
If I understand correctly Duncan is saying that the current word definition cleaving using the above rules in certain cases adheres to a false distribution leading to false beliefs.
Without having empirical data to back this claim, my guess would be that the autism distribution has a single peak at “no symptoms”. that is, the majority of the population has no symptoms, there are lots of people with mild symptoms, and the severe symptoms are down in the tail of the distribution.
I would not guess this. I would guess instead that the majority of the population has a few “symptoms”. Probably we’re in a moderate dimensional space, e.g. 12, and there is a large cluster of people near one end of all 12 spectrums (no/few symptoms), and another, smaller cluster near the other end of all 12 spectrums (many/severe symptoms) but even though we see those two clusters it’s far more common to see “0% on 10, 20% on 1, 80% on 1″ than “0% on all”. See curse of dimensionality, probability concentrating in a shell around the individual dimension modes, etc.
research found the autism distribution to mathematically have 2-5 peaks if I am parsing the study correctly with 1 corresponding to normal population and the other peaks gathered to the right
I am not sure if it’s the motivated reasoning speaking but I have a feeling that
if a distribution has 2 or more peaks it is customary to delineate in the valleys and have different words to indicate data points close to each peak [i.e. cleave reality at the joints] [e.g. autism]
If a distribution only has 1 peak, then you would have words for [right of peak] and [left of peak] and maybe [normal (stuff around the peak)] [e.g. height]
If I understand correctly Duncan is saying that the current word definition cleaving using the above rules in certain cases adheres to a false distribution leading to false beliefs.
Without having empirical data to back this claim, my guess would be that the autism distribution has a single peak at “no symptoms”. that is, the majority of the population has no symptoms, there are lots of people with mild symptoms, and the severe symptoms are down in the tail of the distribution.
I would not guess this. I would guess instead that the majority of the population has a few “symptoms”. Probably we’re in a moderate dimensional space, e.g. 12, and there is a large cluster of people near one end of all 12 spectrums (no/few symptoms), and another, smaller cluster near the other end of all 12 spectrums (many/severe symptoms) but even though we see those two clusters it’s far more common to see “0% on 10, 20% on 1, 80% on 1″ than “0% on all”. See curse of dimensionality, probability concentrating in a shell around the individual dimension modes, etc.
research found the autism distribution to mathematically have 2-5 peaks if I am parsing the study correctly with 1 corresponding to normal population and the other peaks gathered to the right
the study I found
https://molecularautism.biomedcentral.com/articles/10.1186/s13229-019-0275-3
I have not read it in depth, just skimming. [no energy to actually give it the attention]
but the relevant image seems to be this:
so it seems to me that it is bi-modal, but not in the sense of male-female bi-modal. and it can mostly be simplified as a slightly skewed bell curve.
You tried to embed a hotlinked image from your gmail, which doesn’t display. You want to download it and then upload it to our editor.