Re:The Sigmoid Function in Logistic Regression
by thanatropism on Tuesday May 17, 2016 @10:23AM
(#11713871)
In this interpretation we expect decision-makers to be utility-maximizers - for example, as whether I buy or not Thing X; so, we expect Gumbel (an extreme value distribution) errors. But we're looking for Utility(1) minus Utility(0) (buying vs. not buying) and the difference between two Gumbels is a logistic.
More detail: http://fisher.osu.edu/~schroeder.9/AMIS900/ch5.pdf
Re:The Sigmoid Function in Logistic Regression
by MidsizeBlowfish on Tuesday May 17, 2016 @10:49AM
(#11714090)
Ah, right you are! Thanks for correcting my mistake :)
This interpretation is also nice as it shows the natural relationship between logistic and probit regression. Probit regression arises when the unobserved utility is modeled with a Gaussian distribution.