[R] Numerical Inversion of Cumulative Distribution Function

David Winsemius dwinsemius at comcast.net
Tue Mar 6 23:35:00 CET 2012


On Mar 6, 2012, at 1:47 PM, Gildas Mazo wrote:

> Dear R users,
>
> Given a user-defined cumulative distribution function F, I want to  
> compute F^{-1}(x).

Isn't this quantile()?  (But pay attention to the type ....  some say  
to use type=1.)

Alternatively: If  q = CDF(x) then generate a matrix of independently  
random (q,x) pairs  on a large sample. Wouldn't the matrix of (x,q)  
pairs then be something to work with?

(This has been asked several many times on R-help, so you could  
practice your use of the search facilities. Here's a MarkMail link:

http://markmail.org/search/?q=list%3Aorg.r-project.r-help+inverse+cumulative+distribution

-- 

David Winsemius, MD
West Hartford, CT



More information about the R-help mailing list