[Caic-commits] r84 - pkg/inst/doc

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

Author: petzoldt
Date: 2008-10-31 12:34:45 +0100 (Fri, 31 Oct 2008)
New Revision: 84

Modified:
   pkg/inst/doc/caic-benchmarks.rnw
Log:
[cosmetics] missing spaces after comma (prevented line break)

Modified: pkg/inst/doc/caic-benchmarks.rnw
===================================================================
--- pkg/inst/doc/caic-benchmarks.rnw	2008-10-22 11:06:19 UTC (rev 83)
+++ pkg/inst/doc/caic-benchmarks.rnw	2008-10-31 11:34:45 UTC (rev 84)
@@ -83,7 +83,7 @@
 crunch.CrPl657.tab <- caic.table(crunch.CrPl657, CAIC.codes=TRUE)
 @
 
-The outputs of contrast calculations in CAIC are saved as the data frames \texttt{CAIC.CrDi213},\texttt{CAIC.CrDi657},\texttt{CAIC.CrPl213},\texttt{CAIC.CrPl413} and \texttt{CAIC.CrPl657} in the data file \texttt{benchCrunchOutputs.rda}. Each of the data frames contains the standard CAIC contrast table consisting of: the CAIC code for the node, the contrast in each variable, the standard deviation of the contrast, the height of the node, the number of subtaxa descending from the node; and the nodal values of the variables. The CAIC codes can now be used to merge the datasets from the two implementations in order to compare the calculated values. The contrasts in the response variable are plotted in Fig. \ref{crunch}, with data from CAIC shown in black and overplotting of data from \texttt{crunch()} in red. The range in the differences between these values is shown in Table \ref{crunchDiffs}, where the maximum differences of around $\pm1e-5$ arise from the limited precision of the values saved in the CAIC output. The exceptions occur in the case of variables with no variance at a polytomy --- these values are identical but currently have  opposite signs between the two implementations.
+The outputs of contrast calculations in CAIC are saved as the data frames \texttt{CAIC.CrDi213}, \texttt{CAIC.CrDi657}, \texttt{CAIC.CrPl213}, \texttt{CAIC.CrPl413} and \texttt{CAIC.CrPl657} in the data file \texttt{benchCrunchOutputs.rda}. Each of the data frames contains the standard CAIC contrast table consisting of: the CAIC code for the node, the contrast in each variable, the standard deviation of the contrast, the height of the node, the number of subtaxa descending from the node; and the nodal values of the variables. The CAIC codes can now be used to merge the datasets from the two implementations in order to compare the calculated values. The contrasts in the response variable are plotted in Fig. \ref{crunch}, with data from CAIC shown in black and overplotting of data from \texttt{crunch()} in red. The range in the differences between these values is shown in Table \ref{crunchDiffs}, where the maximum differences of around $\pm1e-5$ arise from the limited precision of the values saved in the CAIC output. The exceptions occur in the case of variables with no variance at a polytomy --- these values are identical but currently have  opposite signs between the two implementations.
 
 \begin{figure}[htbp]
   \begin{center}