141 reputation
15
bio website
location
age
visits member for 1 year, 10 months
seen Apr 10 '13 at 14:40

Jun
8
awarded  Necromancer
Jun
8
awarded  Editor
Jun
8
revised Are IQ tests “biased” against individuals with Asperger's Syndrome?
deleted 17 characters in body
Jun
7
awarded  Revival
Jun
7
awarded  Teacher
Jun
7
awarded  Supporter
Jun
7
answered Are IQ tests “biased” against individuals with Asperger's Syndrome?
Jun
4
comment Fitting a psychometric function when data does not lend itself to a sigmoidal fit [pypsignifit]
let us continue this discussion in chat
Jun
4
comment Fitting a psychometric function when data does not lend itself to a sigmoidal fit [pypsignifit]
Upon reflection, that was obvious. Sorry! Seeding with values close to 0.5 does not help, nor does changing function - the obscure slope from the first data-point is still there. Ideally I'd just not use that data in my analyses, but seeing as the whole point of this venture is to compare those who are 'good' as the task compared to those who are not...
Jun
3
comment Fitting a psychometric function when data does not lend itself to a sigmoidal fit [pypsignifit]
Makes sense, but the main issue I have is I'd have to arbitrarily choose when to use this alternative fit. The same participant appeared to perform at chance on another condition, but the cumulative gaussian fitted well and showed a not-immediately-apparent slope.
Jun
3
comment Fitting a psychometric function when data does not lend itself to a sigmoidal fit [pypsignifit]
That's exactly what happened. It may be counterintuitive to try to fit the data, but I really want to be able to compare the slope of these participants with ones who performed better using something like a t-test. Hence the 'need' to fit.
Jun
3
awarded  Student
Jun
3
asked Fitting a psychometric function when data does not lend itself to a sigmoidal fit [pypsignifit]