Showing posts with label bias correction. Show all posts
Showing posts with label bias correction. Show all posts

Wednesday, October 7, 2020

Heckman correction

 

https://en.wikipedia.org/wiki/Heckman_correction

"Conceptually, this is achieved by explicitly modelling the individual sampling probability of each observation (the so-called selection equation) together with the conditional expectation of the dependent variable (the so-called outcome equation)" 

The Heckman used Mills ratio to model right-censored data as 'selection bias'. 

selection bias corrected by Mills ratio (inverse of Gompertz mortality rate?)


https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3659766  

`selection bias' using the inverse Mills ratio neglected by epidemiologists.


https://en.wikipedia.org/wiki/Mills_ratio

Mills ratio is the Survival function / pdf, 

The Gompertz function is u = - dS/dt * 1/S, so, HQ thinks Mills ratio is the inversion of the Gompertz mortality rate. 


related to 

https://en.wikipedia.org/wiki/Heckman_correction