# Talk:Diversity index

WikiProject Ecology (Rated C-class, Low-importance)
C  This article has been rated as C-Class on the quality scale.
Low  This article has been rated as Low-importance on the importance scale.
WikiProject Statistics (Rated C-class, Low-importance)

This article is within the scope of the WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page or join the discussion.

C  This article has been rated as C-Class on the quality scale.
Low  This article has been rated as Low-importance on the importance scale.

This page is inconsistent with Simpson's diversity index, but this one is correct. Perhaps the other page should be deleted/merged? 128.42.145.156 (talk) 06:11, 10 November 2009 (UTC)

"Diversity of population" should be "diversity of community" since a population refers to one species - therefore, a measure of species richness cannot be applied to a population and instead must be applied to a community of species. 82.19.72.160 (talk) 17:08, 7 January 2010 (UTC)

## Introduction

"A diversity index is a quantitative measure that increases when the number of types into which a set of entities has been classified increases, and obtains its maximum value for a given number of types when all types are represented by the same number of entities"

errr.. what? i think a simpler introduction is needed. --128.250.5.249 (talk) 07:48, 21 August 2012 (UTC)

## Definition Shannon-Index

I think the definition is wrong, in my opinion it should be "ln" instead of "log". Maybe someone could check? --93.133.255.155 (talk) 16:54, 10 December 2012 (UTC)

## True diversity (The effective number of types)

Why does the definition of qD have the term p_i*p_i^(q-1), when this is simply equal to p_i^q? It seems these two p's may be slightly different, however this is not clear in the text. — Preceding unsigned comment added by Bbeckerman (talkcontribs) 21:51, 23 September 2013 (UTC)

## Generalized diversity

The article focuses on weighted generalized means, where the generalized mean is restricted to the form ${\displaystyle M_{q-1}=\left(\sum _{i}w_{i}p_{i}^{q-1}\right)^{1/(q-1)}}$ for any q≥0, and where the weight wi is required to be simply pi. However, for any weighting function w(p) and any strictly monotonic function f(p), there is a more general mean

${\displaystyle M_{w,f}=f^{-1}\left({\frac {\sum _{i}w(p_{i})f(p_{i})}{\sum _{i}w(p_{i})}}\right)=1/D^{w,f}\,.}$

That is, one takes the weighted average of the f(pi) values, where the denominator in the definition of Mw,f normalizes the weights to sum to 1, and then uses the inverse of f to bring that weighted average back to the same space that the pi values live in. If you have citations to the literature for this general diversity index, would you add them and a discussion to the article? Leegrc (talk) 14:30, 13 February 2015 (UTC)