Age | Commit message (Collapse) | Author | Files | Lines | |
---|---|---|---|---|---|
2022-11-18 | Make mixed model test data permanent to ensure reproducibility | Johannes Ranke | 1 | -0/+17 | |
To ensure that tests on different platforms work on the same data, the mixed modelling test data previosly generated in tests/testthat/setup_script.R were generated once using the script in inst/dataset/generation/ds_mixed.R, and are now distributed with the package. | |||||
2022-11-18 | Pass error.init to saemix_model, show in parplot | Johannes Ranke | 2 | -5/+17 | |
Due to an oversight, error.init was not really passed to saemix_model in saem.mmkin. The new initial values were reverted to c(1, 1), in order to avoid changing the test results. Initial values for error model parameters are now shown in parplot.multistart. | |||||
2022-11-18 | Improve logLik.mkinfit to attach nobs attribute | Johannes Ranke | 1 | -0/+1 | |
The lack of that attribute lead to a failure to calculate the BIC in test_AIC.R on R-devel from yesterday. | |||||
2022-11-16 | Read in all data per default | Johannes Ranke | 1 | -1/+1 | |
2022-11-15 | Import saemix for easier profiling, update online docs | Johannes Ranke | 1 | -1/+2 | |
2022-11-14 | Automatic starting parameters for saem.mmkin | Johannes Ranke | 1 | -1/+28 | |
For the case of mkin transformations. This gives faster convergence, and appears to avoid problems with numeric ODE solutions | |||||
2022-11-08 | Same SFORB simplification for saem.mmkin fits | Johannes Ranke | 1 | -2/+2 | |
2022-11-08 | Show DFOP g equivalent of SFORB in summary, test | Johannes Ranke | 2 | -8/+11 | |
2022-11-08 | Simplify SFORB also in the endpoint function | Johannes Ranke | 1 | -11/+10 | |
2022-11-08 | Simplify SFORB analytical solution, whitespace | Johannes Ranke | 1 | -64/+64 | |
I do not know why the formulae for b1 and b2 on page 64 of FOCUS kinetics (2014) were not simplified. Clearly, the term k12 * k21 - (k12 + k1output) * k21) can be simplified to - k1output * k21 The test for equivalence of DFOP and SFORB fits verifies that the change is OK. I also removed trailing whitespaces, substituted tab characters by two whitespaces and removed indenting of text in paragraphs describing parameters in roxygen comments to unify formatting. | |||||
2022-11-07 | Make print and summary for saem.mmkin more robust | Johannes Ranke | 2 | -8/+18 | |
If the likelihood computed by importance sampling, these methods failed. Now they report "Not available" or NA, respectively. | |||||
2022-11-04 | Further improvement of robustness of anova method | Johannes Ranke | 1 | -9/+9 | |
2022-11-04 | Fix anova.saem.mmkin for unavailable likelihoods | Johannes Ranke | 1 | -4/+10 | |
2022-11-04 | Attempt at automatic setting of random effects | Johannes Ranke | 1 | -4/+24 | |
Based on parameters in the separate fits that fail the t-test. | |||||
2022-11-04 | Make it easy to override maxsteps for lsoda | Johannes Ranke | 1 | -23/+26 | |
The hope was to be more successful in saemix fits, but I did not notice an improvement (e.g. for a failing likelihood calculation with importance sampling, where the error message suggested to increase maxsteps). | |||||
2022-11-04 | Make illparms.mhmkin and anova.saem.mmkin more robust | Johannes Ranke | 3 | -12/+14 | |
2022-11-04 | Never fail with errors in saem.mmkin | Johannes Ranke | 1 | -6/+0 | |
I think it is always preferable to be able to investigate the saemix object returned. | |||||
2022-11-01 | Add tex_listing() | Johannes Ranke | 1 | -0/+32 | |
2022-11-01 | Add read_spreadsheet | Johannes Ranke | 1 | -0/+113 | |
2022-11-01 | Fix plotting saem fits with covariates | Johannes Ranke | 2 | -47/+72 | |
2022-11-01 | Fix a bug, couldn't set class attribute on NULL | Johannes Ranke | 1 | -1/+1 | |
2022-11-01 | Fix illparms tests | Johannes Ranke | 1 | -1/+1 | |
2022-11-01 | Improved printing for illparms() | Johannes Ranke | 1 | -4/+20 | |
For the case of single fits and no ill-defined parameters found | |||||
2022-10-31 | Fix R CMD check | Johannes Ranke | 1 | -3/+5 | |
2022-10-31 | Possibility to override the error model in update.saem | Johannes Ranke | 2 | -11/+14 | |
2022-10-31 | Add anova.mhmkin method | Johannes Ranke | 1 | -0/+16 | |
2022-10-30 | Correct documentation of sorting in anova.saem.mmkin() | Johannes Ranke | 1 | -3/+4 | |
2022-10-30 | saem summary in case of non-invertible FIM parts | Johannes Ranke | 1 | -7/+13 | |
2022-10-29 | Update multistart docs | Johannes Ranke | 1 | -2/+2 | |
2022-10-28 | Rename parhist to parplot and make it generic | Johannes Ranke | 4 | -8/+15 | |
That parhist name was not the brightest idea, as it does not show histograms. | |||||
2022-10-28 | Export status method for mhmkin, move to status.R | Johannes Ranke | 2 | -39/+43 | |
2022-10-28 | Rename 'convergence' method to 'status' | Johannes Ranke | 5 | -27/+25 | |
The reason is that it is misleading in the case of saem.mmkin objects, because convergence is not really checked there. | |||||
2022-10-26 | Really test anova output, test covariates | Johannes Ranke | 1 | -0/+5 | |
2022-10-26 | Update multistart example code and vignette | Johannes Ranke | 1 | -9/+3 | |
2022-10-26 | Remove kernel density estimate from llhist | Johannes Ranke | 1 | -11/+9 | |
2022-10-26 | Make multistart work with testthat scopes | Johannes Ranke | 1 | -3/+20 | |
Also skip long-running test with saem using the analytical from mkin | |||||
2022-10-25 | Complete documentation and fix a bug | Johannes Ranke | 3 | -2/+6 | |
The bug was introduced by the changes in summary.saem.mmkin.R and surfaced in the tests when using saemix transformations. | |||||
2022-10-25 | Revert accidental change | Johannes Ranke | 1 | -21/+27 | |
2022-10-21 | Explain chisq tests in anova | Johannes Ranke | 1 | -1/+2 | |
Now that I understand how anova.lmer from which I ported the code produces mostly meaningful likelihood ratio tests in the table. | |||||
2022-10-21 | Adapt summary.saem.mmkin to covariate models | Johannes Ranke | 1 | -7/+6 | |
Dissipation times are calculated for covariate values of zero currently, which will usually not be very useful. | |||||
2022-10-21 | Add a simple anova method for model comparison | Johannes Ranke | 2 | -4/+116 | |
Update docs | |||||
2022-10-21 | Make update.saem.mmkin work with objects from multistart | Johannes Ranke | 1 | -6/+10 | |
In particular, objects selected using best.multistart can now be updated, as the starting parameters are inserted into the call, without reference to 'start_parms' which will not be available outside the multistart method. | |||||
2022-10-20 | First working version setting up covariate models | Johannes Ranke | 1 | -4/+53 | |
2022-10-18 | Don't fail if one of the Hessians can't be computed | Johannes Ranke | 1 | -1/+8 | |
2022-10-17 | Fix selecting by log likelihood in parhist | Johannes Ranke | 1 | -8/+21 | |
2022-10-17 | SFORB in saem, update for mhmkin and multistart | Johannes Ranke | 3 | -1/+69 | |
2022-10-14 | update method for mhmkin objects, clarify comment | Johannes Ranke | 2 | -2/+25 | |
2022-10-14 | Select best fit from multistart, use in parhist | Johannes Ranke | 2 | -14/+68 | |
- Add 'best' and 'which.best' generics with methods for multistart objects - Per default, scale the parameters in parhist plots using the fit with the highest log likelihood. | |||||
2022-10-13 | Cope with failed FIM inversions | Johannes Ranke | 3 | -10/+29 | |
2022-10-05 | Simplify the removal of random effects | Johannes Ranke | 1 | -4/+33 | |
This is achieved by introducing the argument 'no_random_effect' to the saem function. |