mkin/tests/testthat/setup_script.R, branch v0.9.50.3Fitting kinetic models to chemical degradation data (also on github)https://erac.jrwb.de/mkin/atom?h=v0.9.50.32020-05-29T13:03:04ZWarn if standardized residuals are unlikely normal2020-05-29T13:03:04ZJohannes Rankejranke@uni-bremen.de2020-05-29T13:03:04Zurn:sha1:510436646b1bdd5b8cfab70be29334bd3cc9c828
This revealed a bug in the data returned in mkinfit$data in the case
of the d_3 algorithm, which also affected the residual plot - the
data from the direct fitting was not returned even if this was
the better method.
Add analytical solution for DFOP-SFO2020-05-11T13:20:53ZJohannes Rankejranke@uni-bremen.de2020-05-11T13:00:25Zurn:sha1:6308e7d7898d4f064d321d97d162c6752c22b362
This is about twice as fast as deSolve compiled in the case of FOCUS D
Analytical solutions for all SFO variants2020-05-11T11:43:40ZJohannes Rankejranke@uni-bremen.de2020-05-11T11:43:40Zurn:sha1:b36ae3d710858ee3ff2907eb2d780e0dff48a4f3Roxygenize, adapt tests2020-05-08T07:00:20ZJohannes Rankejranke@uni-bremen.de2020-05-08T07:00:20Zurn:sha1:f6f8ca5142020c2c5b0628bdcae1e2d00b80c6d5Add a lack-of-fit test2019-11-09T00:05:51ZJohannes Rankejranke@uni-bremen.de2019-11-09T00:05:51Zurn:sha1:20b9c584e7c43ecbb708459e531c24a1a4751e17
- Switch an example dataset in the test setup to a dataset with
replicates, adapt tests
- Skip the test for lrtest with an update specification as it does not
only fail when pkgdown generates static help pages, but also in testthat
Reorganize tests to reduce time on winbuilder2019-10-31T10:47:23ZJohannes Rankejranke@uni-bremen.de2019-10-31T10:47:23Zurn:sha1:99947961be1cf0a7eed80426bc3d8cc6daa6d106Add likelihood ratio test and other methods, fixes2019-10-31T00:59:05ZJohannes Rankejranke@uni-bremen.de2019-10-31T00:55:01Zurn:sha1:7091d3738e7e55acb20edb88772b228f6f5b6c98
The likelihood ratio test method is lrtest, in addition,
methods for update and residuals were added.
Address some check and test failures2019-10-26T20:38:11ZJohannes Rankejranke@uni-bremen.de2019-10-26T20:38:11Zurn:sha1:cb03bf1fb1e6326f06029969663f3399af96b05dparms and confint methods2019-10-26T18:50:09ZJohannes Rankejranke@uni-bremen.de2019-10-26T18:50:09Zurn:sha1:7b7729694363515007193d1c3e29e9b76271abb3
The confint method can do profile likelihood based confidence intervals!
Improved visual testing2019-10-22T08:13:16ZJohannes Rankejranke@uni-bremen.de2019-10-22T08:13:16Zurn:sha1:f8d45402477a588f773f6fd300f3d4e914648773