diff options
| author | Johannes Ranke <jranke@uni-bremen.de> | 2022-05-18 21:26:17 +0200 |
|---|---|---|
| committer | Johannes Ranke <jranke@uni-bremen.de> | 2022-05-18 21:26:17 +0200 |
| commit | 91c5db736a4d3f2290a0cc5698fb4e35ae7bda59 (patch) | |
| tree | 8e9e34d18f055936172329c1248e6e2ff136bff9 /docs/reference/mkinfit.html | |
| parent | ea57db98cef3fb882f7bd9656b44f270e7bded38 (diff) | |
Remove outdated comment in FOCUS L vignette, update docs
This also adds the first benchmark results obtained on my laptop system
Diffstat (limited to 'docs/reference/mkinfit.html')
| -rw-r--r-- | docs/reference/mkinfit.html | 75 |
1 files changed, 38 insertions, 37 deletions
diff --git a/docs/reference/mkinfit.html b/docs/reference/mkinfit.html index c006ddab..e5bf1203 100644 --- a/docs/reference/mkinfit.html +++ b/docs/reference/mkinfit.html @@ -307,7 +307,7 @@ internal rate transformation.</p> for measurement error in analytical chemistry. <em>Technometrics</em> 37(2), 176-184.</p> <p>Ranke J and Meinecke S (2019) Error Models for the Kinetic Evaluation of Chemical Degradation Data. <em>Environments</em> 6(12) 124 -doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link">10.3390/environments6120124</a> +<a href="https://doi.org/10.3390/environments6120124" class="external-link">doi:10.3390/environments6120124</a> .</p> </div> <div id="see-also"> @@ -330,16 +330,16 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-in"><span class="va">fit</span> <span class="op"><-</span> <span class="fu">mkinfit</span><span class="op">(</span><span class="st">"FOMC"</span>, <span class="va">FOCUS_2006_C</span>, quiet <span class="op">=</span> <span class="cn">TRUE</span><span class="op">)</span></span> <span class="r-in"><span class="fu"><a href="https://rdrr.io/r/base/summary.html" class="external-link">summary</a></span><span class="op">(</span><span class="va">fit</span><span class="op">)</span></span> <span class="r-out co"><span class="r-pr">#></span> mkin version used for fitting: 1.1.0 </span> -<span class="r-out co"><span class="r-pr">#></span> R version used for fitting: 4.1.2 </span> -<span class="r-out co"><span class="r-pr">#></span> Date of fit: Mon Mar 7 13:11:56 2022 </span> -<span class="r-out co"><span class="r-pr">#></span> Date of summary: Mon Mar 7 13:11:56 2022 </span> +<span class="r-out co"><span class="r-pr">#></span> R version used for fitting: 4.2.0 </span> +<span class="r-out co"><span class="r-pr">#></span> Date of fit: Wed May 18 20:37:57 2022 </span> +<span class="r-out co"><span class="r-pr">#></span> Date of summary: Wed May 18 20:37:57 2022 </span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Equations:</span> <span class="r-out co"><span class="r-pr">#></span> d_parent/dt = - (alpha/beta) * 1/((time/beta) + 1) * parent</span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Model predictions using solution type analytical </span> <span class="r-out co"><span class="r-pr">#></span> </span> -<span class="r-out co"><span class="r-pr">#></span> Fitted using 222 model solutions performed in 0.045 s</span> +<span class="r-out co"><span class="r-pr">#></span> Fitted using 222 model solutions performed in 0.041 s</span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Error model: Constant variance </span> <span class="r-out co"><span class="r-pr">#></span> </span> @@ -374,10 +374,10 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Parameter correlation:</span> <span class="r-out co"><span class="r-pr">#></span> parent_0 log_alpha log_beta sigma</span> -<span class="r-out co"><span class="r-pr">#></span> parent_0 1.000e+00 -1.565e-01 -3.142e-01 4.772e-08</span> -<span class="r-out co"><span class="r-pr">#></span> log_alpha -1.565e-01 1.000e+00 9.564e-01 1.005e-07</span> -<span class="r-out co"><span class="r-pr">#></span> log_beta -3.142e-01 9.564e-01 1.000e+00 8.541e-08</span> -<span class="r-out co"><span class="r-pr">#></span> sigma 4.772e-08 1.005e-07 8.541e-08 1.000e+00</span> +<span class="r-out co"><span class="r-pr">#></span> parent_0 1.000e+00 -1.565e-01 -3.142e-01 4.770e-08</span> +<span class="r-out co"><span class="r-pr">#></span> log_alpha -1.565e-01 1.000e+00 9.564e-01 9.974e-08</span> +<span class="r-out co"><span class="r-pr">#></span> log_beta -3.142e-01 9.564e-01 1.000e+00 8.468e-08</span> +<span class="r-out co"><span class="r-pr">#></span> sigma 4.770e-08 9.974e-08 8.468e-08 1.000e+00</span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Backtransformed parameters:</span> <span class="r-out co"><span class="r-pr">#></span> Confidence intervals for internally transformed parameters are asymmetric.</span> @@ -462,7 +462,7 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-out co"><span class="r-pr">#></span> $distimes</span> <span class="r-out co"><span class="r-pr">#></span> DT50 DT90</span> <span class="r-out co"><span class="r-pr">#></span> parent 6.89313 22.89848</span> -<span class="r-out co"><span class="r-pr">#></span> m1 134.15634 445.65772</span> +<span class="r-out co"><span class="r-pr">#></span> m1 134.15634 445.65770</span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-in"></span> <span class="r-in"><span class="co"># We can show a quick (only one replication) benchmark for this case, as we</span></span> @@ -471,7 +471,7 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-in"><span class="co"># benchmark vignette</span></span> <span class="r-in"><span class="co"># \dontrun{</span></span> <span class="r-in"><span class="kw">if</span><span class="op">(</span><span class="kw"><a href="https://rdrr.io/r/base/library.html" class="external-link">require</a></span><span class="op">(</span><span class="va"><a href="http://rbenchmark.googlecode.com" class="external-link">rbenchmark</a></span><span class="op">)</span><span class="op">)</span> <span class="op">{</span></span> -<span class="r-in"> <span class="fu"><a href="https://rdrr.io/pkg/rbenchmark/man/benchmark.html" class="external-link">benchmark</a></span><span class="op">(</span>replications <span class="op">=</span> <span class="fl">1</span>, order <span class="op">=</span> <span class="st">"relative"</span>, columns <span class="op">=</span> <span class="fu"><a href="https://rdrr.io/r/base/c.html" class="external-link">c</a></span><span class="op">(</span><span class="st">"test"</span>, <span class="st">"relative"</span>, <span class="st">"elapsed"</span><span class="op">)</span>,</span> +<span class="r-in"> <span class="fu">benchmark</span><span class="op">(</span>replications <span class="op">=</span> <span class="fl">1</span>, order <span class="op">=</span> <span class="st">"relative"</span>, columns <span class="op">=</span> <span class="fu"><a href="https://rdrr.io/r/base/c.html" class="external-link">c</a></span><span class="op">(</span><span class="st">"test"</span>, <span class="st">"relative"</span>, <span class="st">"elapsed"</span><span class="op">)</span>,</span> <span class="r-in"> deSolve_compiled <span class="op">=</span> <span class="fu">mkinfit</span><span class="op">(</span><span class="va">SFO_SFO</span>, <span class="va">FOCUS_D</span>, quiet <span class="op">=</span> <span class="cn">TRUE</span>, error_model <span class="op">=</span> <span class="st">"tc"</span>,</span> <span class="r-in"> solution_type <span class="op">=</span> <span class="st">"deSolve"</span>, use_compiled <span class="op">=</span> <span class="cn">TRUE</span><span class="op">)</span>,</span> <span class="r-in"> eigen <span class="op">=</span> <span class="fu">mkinfit</span><span class="op">(</span><span class="va">SFO_SFO</span>, <span class="va">FOCUS_D</span>, quiet <span class="op">=</span> <span class="cn">TRUE</span>, error_model <span class="op">=</span> <span class="st">"tc"</span>,</span> @@ -479,10 +479,8 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-in"> analytical <span class="op">=</span> <span class="fu">mkinfit</span><span class="op">(</span><span class="va">SFO_SFO</span>, <span class="va">FOCUS_D</span>, quiet <span class="op">=</span> <span class="cn">TRUE</span>, error_model <span class="op">=</span> <span class="st">"tc"</span>,</span> <span class="r-in"> solution_type <span class="op">=</span> <span class="st">"analytical"</span><span class="op">)</span><span class="op">)</span></span> <span class="r-in"><span class="op">}</span></span> -<span class="r-out co"><span class="r-pr">#></span> test relative elapsed</span> -<span class="r-out co"><span class="r-pr">#></span> 3 analytical 1.000 0.573</span> -<span class="r-out co"><span class="r-pr">#></span> 1 deSolve_compiled 1.642 0.941</span> -<span class="r-out co"><span class="r-pr">#></span> 2 eigen 2.517 1.442</span> +<span class="r-msg co"><span class="r-pr">#></span> Loading required package: rbenchmark</span> +<span class="r-wrn co"><span class="r-pr">#></span> <span class="warning">Warning: </span>there is no package called ‘rbenchmark’</span> <span class="r-in"><span class="co"># }</span></span> <span class="r-in"></span> <span class="r-in"><span class="co"># Use stepwise fitting, using optimised parameters from parent only fit, FOMC-SFO</span></span> @@ -506,10 +504,13 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-in"><span class="co"># Also, the missing standard error for log_beta and the t-tests for alpha</span></span> <span class="r-in"><span class="co"># and beta indicate overparameterisation</span></span> <span class="r-in"><span class="fu"><a href="https://rdrr.io/r/base/summary.html" class="external-link">summary</a></span><span class="op">(</span><span class="va">fit.FOMC_SFO.tc</span>, data <span class="op">=</span> <span class="cn">FALSE</span><span class="op">)</span></span> +<span class="r-wrn co"><span class="r-pr">#></span> <span class="warning">Warning: </span>NaNs produced</span> +<span class="r-wrn co"><span class="r-pr">#></span> <span class="warning">Warning: </span>NaNs produced</span> +<span class="r-wrn co"><span class="r-pr">#></span> <span class="warning">Warning: </span>diag(.) had 0 or NA entries; non-finite result is doubtful</span> <span class="r-out co"><span class="r-pr">#></span> mkin version used for fitting: 1.1.0 </span> -<span class="r-out co"><span class="r-pr">#></span> R version used for fitting: 4.1.2 </span> -<span class="r-out co"><span class="r-pr">#></span> Date of fit: Mon Mar 7 13:12:07 2022 </span> -<span class="r-out co"><span class="r-pr">#></span> Date of summary: Mon Mar 7 13:12:07 2022 </span> +<span class="r-out co"><span class="r-pr">#></span> R version used for fitting: 4.2.0 </span> +<span class="r-out co"><span class="r-pr">#></span> Date of fit: Wed May 18 20:38:07 2022 </span> +<span class="r-out co"><span class="r-pr">#></span> Date of summary: Wed May 18 20:38:07 2022 </span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Equations:</span> <span class="r-out co"><span class="r-pr">#></span> d_parent/dt = - (alpha/beta) * 1/((time/beta) + 1) * parent</span> @@ -518,12 +519,12 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Model predictions using solution type deSolve </span> <span class="r-out co"><span class="r-pr">#></span> </span> -<span class="r-out co"><span class="r-pr">#></span> Fitted using 3729 model solutions performed in 2.67 s</span> +<span class="r-out co"><span class="r-pr">#></span> Fitted using 3924 model solutions performed in 7.107 s</span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Error model: Two-component variance function </span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Error model algorithm: d_3 </span> -<span class="r-out co"><span class="r-pr">#></span> Direct fitting and three-step fitting yield approximately the same likelihood </span> +<span class="r-out co"><span class="r-pr">#></span> Three-step fitting yielded a higher likelihood than direct fitting </span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Starting values for parameters to be optimised:</span> <span class="r-out co"><span class="r-pr">#></span> value type</span> @@ -558,7 +559,7 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-out co"><span class="r-pr">#></span> Estimate Std. Error Lower Upper</span> <span class="r-out co"><span class="r-pr">#></span> parent_0 101.600000 2.6400000 96.240000 107.000000</span> <span class="r-out co"><span class="r-pr">#></span> log_k_m1 -5.284000 0.0929100 -5.474000 -5.095000</span> -<span class="r-out co"><span class="r-pr">#></span> f_parent_qlogis 0.001426 0.0767000 -0.155000 0.157800</span> +<span class="r-out co"><span class="r-pr">#></span> f_parent_qlogis 0.001426 0.0766900 -0.155000 0.157800</span> <span class="r-out co"><span class="r-pr">#></span> log_alpha 5.522000 0.0077320 5.506000 5.538000</span> <span class="r-out co"><span class="r-pr">#></span> log_beta 7.806000 NaN NaN NaN</span> <span class="r-out co"><span class="r-pr">#></span> sigma_low 0.002488 0.0002431 0.001992 0.002984</span> @@ -566,31 +567,31 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Parameter correlation:</span> <span class="r-out co"><span class="r-pr">#></span> parent_0 log_k_m1 f_parent_qlogis log_alpha log_beta</span> -<span class="r-out co"><span class="r-pr">#></span> parent_0 1.000000 -0.095226 -0.76678 0.70544 NaN</span> -<span class="r-out co"><span class="r-pr">#></span> log_k_m1 -0.095226 1.000000 0.51432 -0.14387 NaN</span> -<span class="r-out co"><span class="r-pr">#></span> f_parent_qlogis -0.766780 0.514321 1.00000 -0.61396 NaN</span> -<span class="r-out co"><span class="r-pr">#></span> log_alpha 0.705444 -0.143872 -0.61396 1.00000 NaN</span> +<span class="r-out co"><span class="r-pr">#></span> parent_0 1.000000 -0.095145 -0.76674 0.70541 NaN</span> +<span class="r-out co"><span class="r-pr">#></span> log_k_m1 -0.095145 1.000000 0.51428 -0.14381 NaN</span> +<span class="r-out co"><span class="r-pr">#></span> f_parent_qlogis -0.766743 0.514278 1.00000 -0.61392 NaN</span> +<span class="r-out co"><span class="r-pr">#></span> log_alpha 0.705413 -0.143809 -0.61392 1.00000 NaN</span> <span class="r-out co"><span class="r-pr">#></span> log_beta NaN NaN NaN NaN 1</span> -<span class="r-out co"><span class="r-pr">#></span> sigma_low 0.016073 0.001586 0.01548 5.87007 NaN</span> -<span class="r-out co"><span class="r-pr">#></span> rsd_high 0.006626 -0.011700 -0.05357 0.04849 NaN</span> +<span class="r-out co"><span class="r-pr">#></span> sigma_low 0.016077 0.001586 0.01548 5.87034 NaN</span> +<span class="r-out co"><span class="r-pr">#></span> rsd_high 0.006617 -0.011694 -0.05356 0.04848 NaN</span> <span class="r-out co"><span class="r-pr">#></span> sigma_low rsd_high</span> -<span class="r-out co"><span class="r-pr">#></span> parent_0 0.016073 0.006626</span> -<span class="r-out co"><span class="r-pr">#></span> log_k_m1 0.001586 -0.011700</span> -<span class="r-out co"><span class="r-pr">#></span> f_parent_qlogis 0.015476 -0.053566</span> -<span class="r-out co"><span class="r-pr">#></span> log_alpha 5.870075 0.048487</span> +<span class="r-out co"><span class="r-pr">#></span> parent_0 0.016077 0.006617</span> +<span class="r-out co"><span class="r-pr">#></span> log_k_m1 0.001586 -0.011694</span> +<span class="r-out co"><span class="r-pr">#></span> f_parent_qlogis 0.015476 -0.053560</span> +<span class="r-out co"><span class="r-pr">#></span> log_alpha 5.870339 0.048481</span> <span class="r-out co"><span class="r-pr">#></span> log_beta NaN NaN</span> -<span class="r-out co"><span class="r-pr">#></span> sigma_low 1.000000 -0.652558</span> -<span class="r-out co"><span class="r-pr">#></span> rsd_high -0.652558 1.000000</span> +<span class="r-out co"><span class="r-pr">#></span> sigma_low 1.000000 -0.652555</span> +<span class="r-out co"><span class="r-pr">#></span> rsd_high -0.652555 1.000000</span> <span class="r-out co"><span class="r-pr">#></span> </span> <span class="r-out co"><span class="r-pr">#></span> Backtransformed parameters:</span> <span class="r-out co"><span class="r-pr">#></span> Confidence intervals for internally transformed parameters are asymmetric.</span> <span class="r-out co"><span class="r-pr">#></span> t-test (unrealistically) based on the assumption of normal distribution</span> <span class="r-out co"><span class="r-pr">#></span> for estimators of untransformed parameters.</span> <span class="r-out co"><span class="r-pr">#></span> Estimate t value Pr(>t) Lower Upper</span> -<span class="r-out co"><span class="r-pr">#></span> parent_0 1.016e+02 32.7800 6.311e-26 9.624e+01 1.070e+02</span> +<span class="r-out co"><span class="r-pr">#></span> parent_0 1.016e+02 32.7800 6.312e-26 9.624e+01 1.070e+02</span> <span class="r-out co"><span class="r-pr">#></span> k_m1 5.072e-03 10.1200 1.216e-11 4.196e-03 6.130e-03</span> -<span class="r-out co"><span class="r-pr">#></span> f_parent_to_m1 5.004e-01 20.8300 4.317e-20 4.613e-01 5.394e-01</span> -<span class="r-out co"><span class="r-pr">#></span> alpha 2.502e+02 0.5624 2.889e-01 2.463e+02 2.542e+02</span> +<span class="r-out co"><span class="r-pr">#></span> f_parent_to_m1 5.004e-01 20.8300 4.318e-20 4.613e-01 5.394e-01</span> +<span class="r-out co"><span class="r-pr">#></span> alpha 2.502e+02 0.5624 2.890e-01 2.463e+02 2.542e+02</span> <span class="r-out co"><span class="r-pr">#></span> beta 2.455e+03 0.5549 2.915e-01 NA NA</span> <span class="r-out co"><span class="r-pr">#></span> sigma_low 2.488e-03 0.4843 3.158e-01 1.992e-03 2.984e-03</span> <span class="r-out co"><span class="r-pr">#></span> rsd_high 7.921e-02 8.4300 8.001e-10 6.018e-02 9.823e-02</span> @@ -630,7 +631,7 @@ doi: <a href="https://doi.org/10.3390/environments6120124" class="external-link" </div> <div class="pkgdown"> - <p></p><p>Site built with <a href="https://pkgdown.r-lib.org/" class="external-link">pkgdown</a> 2.0.2.</p> + <p></p><p>Site built with <a href="https://pkgdown.r-lib.org/" class="external-link">pkgdown</a> 2.0.3.</p> </div> </footer></div> |