Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2019-06-05 | Adapt tests to new algorithms and output | Johannes Ranke | 4 | -381/+14 | |
One of the tests exceeded the number of iterations when using the d_3 error model algorithm, so only use "direct" in this case. | |||||
2019-06-05 | Add error model algorithm to output | Johannes Ranke | 17 | -110/+198 | |
2019-06-04 | Fix a bug introduced in the last commit | Johannes Ranke | 2 | -3/+5 | |
2019-06-04 | For the d_3 algorithm, report which was better, if any | Johannes Ranke | 1 | -2/+13 | |
2019-06-04 | Add sources for test data for better transparency | Johannes Ranke | 1 | -0/+55 | |
2019-06-04 | Also wait for codecov... | Johannes Ranke | 1 | -1/+1 | |
2019-06-04 | Fix travis configuration (hopefully) | Johannes Ranke | 1 | -1/+1 | |
2019-06-04 | Let travis wait longer for the check to finish | Johannes Ranke | 1 | -0/+4 | |
2019-06-04 | Additional algorithm "d_c", more tests, docs | Johannes Ranke | 156 | -528/+1233 | |
The new algorithm tries direct optimization of the likelihood, as well as a three step procedure. In this way, we consistently get the model with the highest likelihood for SFO, DFOP and HS for all 12 new test datasets. | |||||
2019-06-04 | Algorithms direct, two-, three-, fourstep, IRLS | Johannes Ranke | 2 | -14/+86 | |
All of them are working now and allow for comparison Based on SFO, DFOP and HS fits to twelve test datasets, only the combination of direct and threestep is needed to find the lowest AIC | |||||
2019-06-03 | Status von Samstag morgen - untested | Johannes Ranke | 2 | -37/+105 | |
2019-05-31 | Experimental data for finding error model algorithm | Johannes Ranke | 2 | -0/+65 | |
2019-05-24 | Typo | Johannes Ranke | 1 | -1/+1 | |
2019-05-23 | Fix a bug that could lead to wrong chi2 error levels | Johannes Ranke | 5 | -29/+32 | |
2019-05-21 | Clarify the relation of the two-component error model | Johannes Ranke | 1 | -2/+3 | |
in relation to the original version by Rocke and Lorenzato | |||||
2019-05-20 | Only use colors for error model "obs" | Johannes Ranke | 1 | -3/+3 | |
2019-05-14 | Don't use remote CRAN incoming checks | Johannes Ranke | 1 | -1/+1 | |
2019-05-08 | Add functionality to plot the error model | Johannes Ranke | 37 | -129/+600 | |
by plotting squared residuals against predicted values, and showing the variance function used in the fitted error model. Rebuild docs | |||||
2019-05-07 | Fix hessian calculations | Johannes Ranke | 27 | -1164/+963 | |
Static documentation rebuilt by pkgdown | |||||
2019-05-07 | After the OLS step, use OLS parameter estimates | Johannes Ranke | 31 | -1073/+1025 | |
- Fix the respective error in the code - Static documentation rebuilt by pkgdown | |||||
2019-05-03 | Improve error model fitting | Johannes Ranke | 49 | -592/+622 | |
Now we have a three stage fitting process for nonconstant error models: - Unweighted least squares - Only optimize the error model - Optimize both Static documentation rebuilt by pkgdown | |||||
2019-05-02 | Build log | Johannes Ranke | 1 | -1/+3 | |
2019-05-02 | Remove reference to archived kinfit package | Johannes Ranke | 16 | -360/+1739 | |
from vignettes/mkin.Rmd Static documentation rebuilt by pkgdown | |||||
2019-05-02 | Prepare for CRAN release | Johannes Ranke | 18 | -98/+103 | |
- Skip long running tests on CRAN as well to avoid timeout on winbuilder - Don't install benchmark results in the package, they are only needed in the git repository - Don't run example in man/add_err.Rd as it takes > 10 s on winbuilder - Rebuild docs | |||||
2019-05-02 | Improve tests | Johannes Ranke | 5 | -34/+45 | |
- Improve control of the number of cores - Reduce the precision of the correlation matrix in the test summary output, as the exact results are platform dependent | |||||
2019-05-02 | Better initials for error model parameters | Johannes Ranke | 78 | -424/+450 | |
- Also make it possible to specify initial values for error model parameters. - Run tests - Rebuild docs | |||||
2019-04-24 | Improve output and update tests | Johannes Ranke | 7 | -112/+70 | |
Remove skipped tests as I do not intend to reactivate them | |||||
2019-04-10 | Address failure on travis | Johannes Ranke | 4 | -3/+4 | |
Also reduce the digits in the representative half-live given by nafta() | |||||
2019-04-10 | Adapt tests, vignettes and examples | Johannes Ranke | 139 | -2333/+6813 | |
- Write the NEWS - Static documentation rebuilt by pkgdown - Adapt mkinerrmin - Fix (hopefully all) remaining problems in mkinfit | |||||
2019-04-08 | Remove zero observations, adapt logLik | Johannes Ranke | 2 | -24/+11 | |
Zero observations at time zero made fitting the two-component error model fail. A concentration of exactly zero does not make sense anyways, as we generally have a limit of detection | |||||
2019-04-05 | Report negative log-likelihood during fits | Johannes Ranke | 1 | -4/+10 | |
If not quiet = TRUE | |||||
2019-04-04 | Direct error model fitting works | Johannes Ranke | 10 | -666/+1876 | |
- No IRLS required - Removed optimization algorithms other than Port - Removed the dependency on FME - Fitting the error model 'obs' is much faster for the FOCUS_2006_D dataset and the FOMC_SFO model (1 second versus 3.4 seconds) - Vignettes build slower. Compiled models needs 3 minutes instead of 1.5 - For other vignettes, the trend is less clear. Some fits are faster, even for error_model = "const". FOCUS_Z is faster (34.9 s versus 44.1 s) - Standard errors and confidence intervals are slightly smaller - Removed code for plotting during the fit, as I hardly ever used it - Merged the two cost functions (using transformed and untransformed parameters) into one log-likelihood function | |||||
2019-03-19 | Set URL to documentation page | Johannes Ranke | 1 | -1/+1 | |
2019-03-04 | Update README.html for cgit.jrwb.de | Johannes Ranke | 1 | -1/+1 | |
2019-03-04 | Make some example output more reproducible | Johannes Ranke | 17 | -914/+177 | |
In order to avoid some unnecessary documentation rebuilds | |||||
2019-03-04 | Fix .Rbuildignore | Johannes Ranke | 1 | -14/+13 | |
thanks to Kurt Hornik for pointing out that perl regexp syntax is needed, not shell glob syntax | |||||
2019-03-04 | Winbuilder also needs cores = 1v0.9.48.1 | Johannes Ranke | 1 | -1/+1 | |
2019-03-04 | signif for DTx when printing nafta results | Johannes Ranke | 3 | -5/+5 | |
In order to be able to test cross-platform | |||||
2019-03-04 | Review tests and examples based on winbuilder results | Johannes Ranke | 38 | -668/+715 | |
Static documentation rebuilt by pkgdown | |||||
2019-02-28 | Update README for cgit.jrwb.de | Johannes Ranke | 1 | -1/+1 | |
2019-02-27 | Fix test for mkinds printing | Johannes Ranke | 2 | -1/+7 | |
2019-02-27 | Comment out unused code | Johannes Ranke | 2 | -27/+27 | |
2019-02-27 | Further increase test coverage | Johannes Ranke | 7 | -11/+125 | |
2019-02-27 | Increase test coverage | Johannes Ranke | 8 | -39/+413 | |
2019-02-27 | Fix CAKE export test to actually work | Johannes Ranke | 7 | -7/+18 | |
Also test the model specification via the link argument | |||||
2019-02-26 | Static documentation rebuilt by pkgdown | Johannes Ranke | 61 | -80/+264 | |
2019-02-26 | NAFTA SOP Attachment vignette | Johannes Ranke | 57 | -156/+1616 | |
Also: - Change rounding in print.nafta - Add dots argument to nafta() - Use cores=1 in examples - Restrict N in IORE model to values > 0 | |||||
2019-02-26 | Static documentation rebuilt by pkgdown | Johannes Ranke | 19 | -88/+349 | |
2019-02-26 | Add another NAFTA dataset + test | Johannes Ranke | 14 | -53/+647 | |
2019-02-25 | Fixes for last commit | Johannes Ranke | 2 | -1/+3 | |