[Vegan-commits] r2948 - www

[noreply at r-forge.r-project.org]

Author: jarioksa
Date: 2015-05-20 14:05:48 +0200 (Wed, 20 May 2015)
New Revision: 2948

Modified:
   www/NEWS.html
Log:
Updated NEWS


Modified: www/NEWS.html
===================================================================
--- www/NEWS.html	2015-05-20 12:03:35 UTC (rev 2947)
+++ www/NEWS.html	2015-05-20 12:05:48 UTC (rev 2948)
@@ -55,7 +55,7 @@
  
 
 
-<h4>NEW FEATURES</h4>
+<h4>NEW FEATURES AND FUNCTIONS</h4>
 
 
 <ul>
@@ -87,6 +87,41 @@
 programs, such as Illustrator and Inkscape.
 </p>
 </li>
+<li><p> Rarefaction curve (<code>rarecurve</code>) and species
+accumulation models (<code>specaccum</code>, <code>fitspecaccum</code>)
+gained new functions to estimate the slope of curve at given
+location. Originally this was based on a response to an
+<a href="https://stat.ethz.ch/pipermail/r-sig-ecology/2015-May/005038.html">R-SIG-ecology</a>
+query. For rarefaction curves, the function is <code>rareslope</code>,
+and for species accumulation models it is <code>specslope</code>.
+</p>
+<p>The functions are based on analytic equations, and can also be
+evaluated at interpolated non-integer values. In
+<code>specaccum</code> models the functions can be only evaluated for
+analytic models <code>"exact"</code>, <code>"rarefaction"</code> and
+<code>"coleman"</code>. With <code>"random"</code> and <code>"collector"</code>
+methods you can only use finite differences
+(<code>diff(fitted(<result.object>))</code>). Analytic functions for
+slope are used for all non-linear regression models known to
+<code>fitspecaccum</code>.
+</p>
+</li>
+<li><p> Species accumulation models (<code>specaccum</code>) and
+non-liner regression models for species accumulation
+(<code>fitspecaccum</code>) work more consistently with weights. In
+all cases, the models are defined using the number of sites as
+independent variable, which with weights means that observations
+can be non-integer numbers of virtual sites. The <code>predict</code>
+models also use the number of sites with <code>newdata</code>,
+and for analytic models they can estimate the expected values
+for non-integer number of sites, and for non-analytic randomized
+or collector models they can interpolate on non-integer values.
+</p>
+</li>
+<li> <p><code>fitspecaccum</code> gained support functions <code>AIC</code>
+and <code>deviance</code>.
+</p>
+</li>
 <li><p> The <code>varpart</code> plots of four-component models were
 redesigned following Legendre, Borcard & Roberts <em>Ecology</em>
 93, 1234–1240 (2012), and they use now four ellipses instead of