Talk:Hypoexponential distribution

Looks like the pdf and cdf are incorrect...they're constants. f(x) = μ1μ2 ( e-μ2 - e-μ1 ) / ( μ1 - μ2 ) — Preceding unsigned comment added by 173.8.242.41 (talk) 23:41, 7 February 2012 (UTC)[reply]

I think there is an error in the table. The "variance"-row shows only the second raw moment, and one should subtract the square of mean from it in order the get the actual variance, i.e., the second central moment.

done. --Uschilch (talk) 15:51, 3 December 2010 (UTC)[reply]

The two parameter case supposedly states the coefficient of variation. However it doesn't make sense, as that expression can be greater than 1. (It also doesn't match when I enter EV and SD in a spreadsheet and just divide appropriately.) So the expression must be wrong. — Preceding unsigned comment added by 129.105.194.96 (talk) 21:27, 1 May 2014 (UTC)[reply]

median

The formula for median is incorrect. 134.197.116.233 (talk) 18:14, 19 January 2012 (UTC)[reply]

First use of the term

When was the term hypoexponential first coined? The earliest reference I can find is this book

Ruiz-Palá, Ernesto, Carlos Avila-Beloso, and William W. Hines. Waiting-line models: an introduction to their theory and application. Reinhold Publishing Corporation, 1967

where on page 11 the term is used

"Distributions with variability greater or less than that of the exponential distribution are called hyperexponential and hypoexponential distributions, respectively."

Is anyone aware of earlier references or who coined the term? Gareth Jones (talk) 16:35, 13 December 2013 (UTC)[reply]

Definition of Psi

As far as I can see, the function $\Psi _{k,l}$ is not defined in the section "General Case". 128.103.224.4 (talk) 16:26, 17 November 2014 (UTC)[reply]