Name

nisp_lognormalinv — Computes the Lognormal quantile.

Calling Sequence

   x = nisp_lognormalinv ( p )
   x = nisp_lognormalinv ( p , mu )
   x = nisp_lognormalinv ( p , mu , sigma )
   
   

Parameters

p:

a matrix of doubles, the probability. Must be in the range [0,1].

mu:

a matrix of doubles, the mean of the underlying normal variable (default mu = 0).

sigma:

a matrix of doubles, the variance of the underlying normal variable (default sigma = 1).

x:

a matrix of doubles

Description

This function computes the Lognormal quantile.

Any scalar input argument is expanded to a matrix of doubles of the same size as the other input arguments.

Any optional input argument equal to the empty matrix will be set to its default value.

TODO : improve implementation (check inf, nan, etc...)

Examples

//
// Check the inverse lognormale
mu = 1;
sigma=10;
x=2;
p = nisp_lognormalcdf ( x , mu , sigma ); // 0.4877603
x = nisp_lognormalinv ( p , mu , sigma ) // Must be 2

   

Authors

Copyright (C) 2008-2011 - INRIA - Michael Baudin

Bibliography

Dider Pelat, "Bases et méthodes pour le traitement de données", section 8.2.8, "Loi log-normale".

Wikipedia, Lognormal probability distribution function, http://en.wikipedia.org/wiki/File:Lognormal_distribution_PDF.png

Wikipedia, Lognormal cumulated distribution function, http://en.wikipedia.org/wiki/File:Lognormal_distribution_CDF.png