aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2007-10-01Imported revision 18, because this was last released on CRANranke36-0/+7720
with version number 0.1-18 git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@24 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2007-10-01Further work on the new repository layoutranke38-0/+0
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@23 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2007-10-01Moved everything into the trunk directory, in order to enable branchingranke39-0/+0
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@22 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2007-06-20Replaced the URL of my homepage by the address of the chemCal package on my ↵ranke1-1/+1
homepage git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@21 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2007-03-23Documentation fixranke2-4/+4
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@20 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2007-03-22Start of the integration of nonlinear calibration modelsranke5-3/+120
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@19 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-06-23Added the data from Massart example 1, and one moreranke15-4358/+4312
tests showing the validity of inverse.predict. git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@18 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-06-23Some cosmetic changes, and the vignette created during package building.ranke13-5845/+5955
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@17 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-06-23- inverse.predict now has a var.s argument instead of the neverranke25-271/+355
tested ss argument. This is documented in the updated vignette - loq() now has w.loq and var.loq arguments, and stops with a message if neither are specified and the model has weights. - calplot doesn't stop any more for weighted regression models, but only refrains from drawing prediction bands - Added method = "din" to lod(), now that I actually have it (DIN 32645) and was able to see which approximation is used therein. - removed the demos, as the examples and tests are already partially duplicated - The vignette is more of a collection of various notes, but should certainly be helpful for the user. - Version bump to 0.1-xxx git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@16 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-24Tested my new Makefile distributed with 0.05-62 of the R vim plugin for ↵ranke8-2758/+2765
Linux/Unix. git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@15 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-23First version published on my website.ranke18-3919/+4751
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@14 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-23Don't do calplot and lod for linear models from weightedranke18-50/+262
regression any more, since this is not supported (PR#8877). git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@13 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-16Tried to fix the return value of lod, but not yet.ranke1-1/+1
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@12 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-16- Took loq and lod apart again. lod is now an implemantation of Massart, loq isranke11-68/+153
an own variant of DIN 32645 (relative error on x axis). - Partly make functions work on models where x and y are named different from "x" and "y" (loq to be done). git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@11 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-15A trial to improve the lod function, I don't really understandranke6-21/+26
the predict.lm function unfortunately git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@10 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-15Splitted the lod and loq functions. Documentation stillranke5-15/+33
must be updated git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@9 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-12- Fixed the inverse predictionranke17-55/+167
- Now I have a working approach for the calculation of LOD and LOQ, but it seems to be different from what everybody else is doing (e.g. Massart chaper 13). I like it, however. Maybe it even yields a paper. git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@8 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-11- The vignette is in a publisheable stateranke16-111/+263
- In addition to the Massart examples, the sample data from dintest (DIN 32645) has been tested - inverse.predict and calplot now also work on glm objects git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@7 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-10The inverse prediction works in a variety of cases and isranke24-262/+6067
tested with Examples 7 and 8 from Massart! I need to compare with the DIN and draper examples, and finish the package vignette. git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@6 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-09Added the example data, and validated it by writingranke6-4/+48
a demo producing the first four columns from Table 8.5 and the weighted regression. git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@5 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-09Removed the chm files, not necessary for a source package.ranke10-411/+0
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@4 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2006-05-09Started a new approach, namely just adding a inverse.predictranke1-0/+40
method for univariate lm models. This will be based on Massart, p. 200. git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@3 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2005-02-15Cleaned up version, only containing very basic stuff.ranke13-309/+146
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@2 5fad18fb-23f0-0310-ab10-e59a3bee62b4
2005-02-15First import, for archiving purposes.ranke22-0/+834
git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@1 5fad18fb-23f0-0310-ab10-e59a3bee62b4

Contact - Imprint