[Distr-commits] r1294 - in branches/distr-2.8/pkg: distr/inst distrMod/inst

noreply at r-forge.r-project.org noreply at r-forge.r-project.org
Fri Mar 1 11:43:48 CET 2019

Author: ruckdeschel
Date: 2019-03-01 11:43:41 +0100 (Fri, 01 Mar 2019)
New Revision: 1294

updated NEWS 

Modified: branches/distr-2.8/pkg/distr/inst/NEWS
--- branches/distr-2.8/pkg/distr/inst/NEWS	2019-02-27 15:32:12 UTC (rev 1293)
+++ branches/distr-2.8/pkg/distr/inst/NEWS	2019-03-01 10:43:41 UTC (rev 1294)
@@ -39,7 +39,18 @@
 + fixed a (newly introduced) bug in exp() for DiscreteDistribution -- forgot to return obj ...
 + Bernhard discovered a bug in devNew() -- it opened new devices even if option("newDevice"==FALSE)  
 + detected that the initialize method of Weibull lacked a .withArith argument to capture the scale structure
++ unknown variable p in S4method to Minimum(absCont,absCont)
+under the hood:
++ in reaction to mail by B.Ripley Feb 20, 19/ explanation by T. Kalibera, that our code to 
+  look into system.call() stack was buggy and failed in staged installation, we revised code to .modifyqgaps completely;
+  we now compute p(obj)(gaps) and check if any argument p of q(obj) falls within the gap range and then shift it to either 
+  the left or right endpoint of the gap acc. to args lower.tail and leftright. To avoid redoing this whenever slot gaps 
+  is changed, we store the unmodified q(obj) function in an internal variable ..q0fun which can also be used 
+  (if existant in the env() of q(obj)) to revert the gaps modification, and any gaps modification, instead of starting 
+  from q(obj) starts with ..q0fun (if this exists); otherwise, i.e., if ..q0fun does not exist, it uses q(obj) and 
+  afterwords stores the old q(obj) as ..q0fun ... 
 v 2.7

Modified: branches/distr-2.8/pkg/distrMod/inst/NEWS
--- branches/distr-2.8/pkg/distrMod/inst/NEWS	2019-02-27 15:32:12 UTC (rev 1293)
+++ branches/distr-2.8/pkg/distrMod/inst/NEWS	2019-03-01 10:43:41 UTC (rev 1294)
@@ -44,6 +44,9 @@
   the help files to generator L2ParamFamily and to L2ParamFamily-class.
 + E() methods with signature(object = "L2ParamFamily" , ...) gain argument diagnostic
   (like E()-methods in distrEx v 2.8.0)
++ triggered by a mail by K. Hornik who spotted output in checking the centering of L2deriv varying from 
+  architecture to architecture, (which is below machine accuracy hence to be ignored) we now delete 
+  non-significant digits in centering 
 bug fixes
 + discovered some issues with local variables in L2Families (global values were used instead...)  

More information about the Distr-commits mailing list