aboutsummaryrefslogtreecommitdiff
path: root/tests
AgeCommit message (Collapse)AuthorFilesLines
2019-10-31Add likelihood ratio test and other methods, fixesJohannes Ranke5-40/+82
The likelihood ratio test method is lrtest, in addition, methods for update and residuals were added.
2019-10-28Fix the cutoff for likelihood based intervalsJohannes Ranke2-60/+45
The cutoff now matches what is given by Venzon and Moolgavkar (1988). Also, confidence intervals closely match intervals obtained with stats4::confint in the test case where an stats4::mle object is created from the likelihood function in one test case. Static documentation rebuilt by pkgdown
2019-10-26Fix checks and testsJohannes Ranke2-7/+7
Static documentation rebuilt by pkgdown
2019-10-26Address some check and test failuresJohannes Ranke2-5/+5
2019-10-26parms and confint methodsJohannes Ranke2-53/+129
The confint method can do profile likelihood based confidence intervals!
2019-10-25Use roxygen for functions and methodsJohannes Ranke1-1/+1
2019-10-22Somehow the figures weren't committed yetJohannes Ranke2-0/+195
2019-10-22Two more plotting testsJohannes Ranke1-0/+4
2019-10-22Skip the visual test that still fails on travisJohannes Ranke1-1/+2
2019-10-22Go back to d_3 for errmod = "obs"Johannes Ranke1-13/+13
in the hope that this makes plotting cross-platform also for this error model
2019-10-22Improved visual testingJohannes Ranke6-7/+479
2019-10-21Adress errors and notes on winbuilderJohannes Ranke2-13/+3
2019-10-21Fix platform dependence of the correlation matrixJohannes Ranke3-20/+5
Especially on winbuilder (i386 and amd64)
2019-10-21Explicit solution_type for FOCUS D in testsJohannes Ranke4-6/+147
Because on winbuilder obviously gcc was not found, so the Eigenvalue based solution method was used, leading to a test failure when comparing the summary, as the solution method is listed
2019-10-21Skip an offensive test on TravisJohannes Ranke1-0/+1
2019-10-21Improve some plotting routines, more testsJohannes Ranke6-24/+664
Static documentation rebuilt by pkgdown
2019-10-21Improve tests, remove geometric_meanJohannes Ranke11-73/+351
2019-10-21Refactor mkinfit, infrastructure workJohannes Ranke7-137/+209
mkinfit objects now include an ll() function to calculate the log-likelihood. Part of the code was refactored, hopefully making it easier to read and maintain. IRLS is currently the default algorithm for the error model "obs", for no particular reason. This may be subject to change when I get around to investigate. Slow tests are now in a separate subdirectory and will probably only be run by my own Makefile target. Formatting of test logs is improved. Roundtripping error model parameters works with a precision of 10% when we use lots of replicates in the synthetic data (see slow tests). This is not new in this commit, but as I think it is reasonable this closes #7.
2019-07-08Support summarizing older fitsJohannes Ranke2-1/+30
generated with mkin < 0.9.49.5
2019-07-05Static documentation rebuilt by pkgdownJohannes Ranke2-2/+2
2019-07-04Address failures of CRAN checks, improve NEWSv0.9.49.5Johannes Ranke2-7/+14
Static documentation rebuilt by pkgdown
2019-07-03Skip a test on CRAN/winbuilderJohannes Ranke1-0/+1
The test uses multiple cores in order to complete within a reasonable time
2019-07-03Add check and test logsJohannes Ranke1-1/+1
2019-06-05Adapt tests to new algorithms and outputJohannes Ranke3-4/+5
One of the tests exceeded the number of iterations when using the d_3 error model algorithm, so only use "direct" in this case.
2019-06-04Fix a bug introduced in the last commitJohannes Ranke1-1/+1
2019-06-04Additional algorithm "d_c", more tests, docsJohannes Ranke3-76/+41
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.
2019-06-04Algorithms direct, two-, three-, fourstep, IRLSJohannes Ranke1-5/+45
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
2019-06-03Status von Samstag morgen - untestedJohannes Ranke1-0/+42
2019-05-23Fix a bug that could lead to wrong chi2 error levelsJohannes Ranke1-18/+27
2019-05-08Add functionality to plot the error modelJohannes Ranke1-1/+1
by plotting squared residuals against predicted values, and showing the variance function used in the fitted error model. Rebuild docs
2019-05-07Fix hessian calculationsJohannes Ranke2-246/+1
Static documentation rebuilt by pkgdown
2019-05-03Improve error model fittingJohannes Ranke1-1/+1
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
2019-05-02Prepare for CRAN releaseJohannes Ranke1-0/+1
- 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
2019-05-02Improve testsJohannes Ranke3-12/+23
- 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
2019-05-02Better initials for error model parametersJohannes Ranke3-7/+7
- Also make it possible to specify initial values for error model parameters. - Run tests - Rebuild docs
2019-04-24Improve output and update testsJohannes Ranke5-78/+49
Remove skipped tests as I do not intend to reactivate them
2019-04-10Address failure on travisJohannes Ranke3-2/+3
Also reduce the digits in the representative half-live given by nafta()
2019-04-10Adapt tests, vignettes and examplesJohannes Ranke16-265/+407
- Write the NEWS - Static documentation rebuilt by pkgdown - Adapt mkinerrmin - Fix (hopefully all) remaining problems in mkinfit
2019-04-04Direct error model fitting worksJohannes Ranke1-35/+71
- 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
2019-03-04Winbuilder also needs cores = 1v0.9.48.1Johannes Ranke1-1/+1
2019-03-04signif for DTx when printing nafta resultsJohannes Ranke2-4/+4
In order to be able to test cross-platform
2019-03-04Review tests and examples based on winbuilder resultsJohannes Ranke7-36/+39
Static documentation rebuilt by pkgdown
2019-02-27Fix test for mkinds printingJohannes Ranke2-1/+7
2019-02-27Further increase test coverageJohannes Ranke6-5/+118
2019-02-27Increase test coverageJohannes Ranke6-17/+380
2019-02-27Fix CAKE export test to actually workJohannes Ranke6-6/+17
Also test the model specification via the link argument
2019-02-26NAFTA SOP Attachment vignetteJohannes Ranke3-14/+14
Also: - Change rounding in print.nafta - Add dots argument to nafta() - Use cores=1 in examples - Restrict N in IORE model to values > 0
2019-02-26Add another NAFTA dataset + testJohannes Ranke7-27/+609
2019-02-25Fixes for last commitJohannes Ranke2-1/+3
2019-02-25Test AIC calculationJohannes Ranke2-1/+2

Contact - Imprint