From 40b78bed232798ecbeb72759cdf8d400ea35b31f Mon Sep 17 00:00:00 2001
From: Johannes Ranke <jranke@uni-bremen.de>
Date: Fri, 23 Jul 2021 13:55:34 +0200
Subject: Some example evaluations of dimethenamid data

Evaluations with nlme, saemix and nlmixr are included
---
 vignettes/web_only/dimethenamid_2018.rmd | 374 +++++++++++++++++++++++++++++++
 1 file changed, 374 insertions(+)
 create mode 100644 vignettes/web_only/dimethenamid_2018.rmd

(limited to 'vignettes/web_only/dimethenamid_2018.rmd')

diff --git a/vignettes/web_only/dimethenamid_2018.rmd b/vignettes/web_only/dimethenamid_2018.rmd
new file mode 100644
index 00000000..d3541a34
--- /dev/null
+++ b/vignettes/web_only/dimethenamid_2018.rmd
@@ -0,0 +1,374 @@
+---
+title: Example evaluations of the dimethenamid data from 2018
+author: Johannes Ranke
+date: Last change 23 June 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
+output:
+  html_document:
+    toc: true
+    toc_float: true
+    code_folding: hide
+    fig_retina: null
+bibliography: ../references.bib
+vignette: >
+  %\VignetteEngine{knitr::rmarkdown}
+  %\VignetteEncoding{UTF-8}
+---
+
+[Wissenschaftlicher Berater, Kronacher Str. 12, 79639 Grenzach-Wyhlen, Germany](http://www.jrwb.de)<br />
+[Privatdozent at the University of Bremen](http://chem.uft.uni-bremen.de/ranke)
+
+```{r, include = FALSE}
+require(knitr)
+options(digits = 5)
+opts_chunk$set(
+  comment = "",
+  tidy = FALSE,
+  cache = TRUE
+)
+```
+
+# Introduction
+
+During the preparation of the journal article on nonlinear mixed-effects models in
+degradation kinetics (submitted) and the analysis of the dimethenamid degradation
+data analysed therein, a need for a more detailed analysis using not only nlme and saemix,
+but also nlmixr for fitting the mixed-effects models was identified.
+
+This vignette is an attempt to satisfy this need.
+
+# Data
+
+Residue data forming the basis for the endpoints derived in the conclusion on
+the peer review of the pesticide risk assessment of dimethenamid-P published by
+the European Food Safety Authority (EFSA) in 2018 [@efsa_2018_dimethenamid]
+were transcribed from the risk assessment report [@dimethenamid_rar_2018_b8]
+which can be downloaded from the
+[EFSA register of questions](https://open.efsa.europa.eu/study-inventory/EFSA-Q-2014-00716).
+
+The data are [available in the mkin
+package](https://pkgdown.jrwb.de/mkin/reference/dimethenamid_2018.html). The
+following code (hidden by default, please use the button to the right to show
+it) treats the data available for the racemic mixture dimethenamid (DMTA) and
+its enantiomer dimethenamid-P (DMTAP) in the same way, as no difference between
+their degradation behaviour was identified in the EU risk assessment. The
+observation times of each dataset are multiplied with the corresponding
+normalisation factor also available in the dataset, in order to make it
+possible to describe all datasets with a single set of parameters.
+
+Also, datasets observed in the same soil are merged, resulting in dimethenamid
+(DMTA) data from six soils.
+
+```{r dimethenamid_data}
+library(mkin)
+dmta_ds <- lapply(1:8, function(i) {
+  ds_i <- dimethenamid_2018$ds[[i]]$data
+  ds_i[ds_i$name == "DMTAP", "name"] <-  "DMTA"
+  ds_i$time <- ds_i$time * dimethenamid_2018$f_time_norm[i]
+  ds_i
+})
+names(dmta_ds) <- sapply(dimethenamid_2018$ds, function(ds) ds$title)
+dmta_ds[["Borstel"]] <- rbind(dmta_ds[["Borstel 1"]], dmta_ds[["Borstel 2"]])
+dmta_ds[["Borstel 1"]] <- NULL
+dmta_ds[["Borstel 2"]] <- NULL
+dmta_ds[["Elliot"]] <- rbind(dmta_ds[["Elliot 1"]], dmta_ds[["Elliot 2"]])
+dmta_ds[["Elliot 1"]] <- NULL
+dmta_ds[["Elliot 2"]] <- NULL
+```
+
+# Parent degradation
+
+We evaluate the observed degradation of the parent compound using simple
+exponential decline (SFO) and biexponential decline (DFOP), using constant
+variance (const) and a two-component variance (tc) as error models.
+
+## Separate evaluations
+
+As a first step, to get a visual impression of the fit of the different models,
+we do separate evaluations for each soil using the mmkin function from the
+mkin package:
+
+```{r f_parent_mkin}
+f_parent_mkin_const <- mmkin(c("SFO", "DFOP"), dmta_ds,
+  error_model = "const", quiet = TRUE)
+f_parent_mkin_tc <- mmkin(c("SFO", "DFOP"), dmta_ds,
+  error_model = "tc", quiet = TRUE)
+```
+
+The plot of the individual SFO fits shown below suggests that at least in some
+datasets the degradation slows down towards later time points, and that the
+scatter of the residuals error is smaller for smaller values (panel to the
+right):
+
+```{r f_parent_mkin_sfo_const}
+plot(mixed(f_parent_mkin_const["SFO", ]))
+```
+
+Using biexponential decline (DFOP) results in a slightly more random
+scatter of the residuals:
+
+```{r f_parent_mkin_dfop_const}
+plot(mixed(f_parent_mkin_const["DFOP", ]))
+```
+
+The population curve (bold line) in the above plot results from taking the mean
+of the individual transformed parameters, i.e. of log k1 and log k2, as well as
+of the logit of the g parameter of the DFOP model). Here, this procedure
+does not result in parameters that represent the degradation well, because in some
+datasets the fitted value for k2 is extremely close to zero, leading to a log
+k2 value that dominates the average. This is alleviated if only rate constants
+that pass the t-test for significant difference from zero (on the untransformed
+scale) are considered in the averaging:
+
+```{r f_parent_mkin_dfop_const_test}
+plot(mixed(f_parent_mkin_const["DFOP", ]), test_log_parms = TRUE)
+```
+
+While this is visually much more satisfactory, such an average procedure could
+introduce a bias, as not all results from the individual fits enter the
+population curve with the same weight. This is where nonlinear mixed-effects
+models can help out by treating all datasets with equally by fitting a
+parameter distribution model together with the degradation model and the error
+model (see below).
+
+The remaining trend of the residuals to be higher for higher predicted residues
+is reduced by using the two-component error model:
+
+```{r f_parent_mkin_dfop_tc_test}
+plot(mixed(f_parent_mkin_tc["DFOP", ]), test_log_parms = TRUE)
+```
+
+## Nonlinear mixed-effects models
+
+Instead of taking a model selection decision for each of the individual fits, we fit
+nonlinear mixed-effects models (using different fitting algorithms as implemented in
+different packages) and do model selection using all available data at the same time.
+In order to make sure that these decisions are not unduly influenced by the
+type of algorithm used, by implementation details or by the use of wrong control
+parameters, we compare the model selection results obtained with different R
+packages, with different algorithms and checking control parameters.
+
+### nlme
+
+The nlme package was the first R extension providing facilities to fit nonlinear
+mixed-effects models. We use would like to do model selection from all four
+combinations of degradation models and error models based on the AIC.
+However, fitting the DFOP model with constant variance and using default
+control parameters results in an error, signalling that the maximum number
+of 50 iterations was reached, potentially indicating overparameterisation.
+However, the algorithm converges when the two-component error model is
+used in combination with the DFOP model. This can be explained by the fact
+that the smaller residues observed at later sampling times get more
+weight when using the two-component error model which will counteract the
+tendency of the algorithm to try parameter combinations unsuitable for
+fitting these data.
+
+```{r f_parent_nlme, warning = FALSE}
+f_parent_nlme_sfo_const <- nlme(f_parent_mkin_const["SFO", ])
+#f_parent_nlme_dfop_const <- nlme(f_parent_mkin_const["DFOP", ]) # error
+f_parent_nlme_sfo_tc <- nlme(f_parent_mkin_tc["SFO", ])
+f_parent_nlme_dfop_tc <- nlme(f_parent_mkin_tc["DFOP", ])
+```
+
+Note that overparameterisation is also indicated by warnings obtained when
+fitting SFO or DFOP with the two-component error model ('false convergence' in
+the 'LME step' in some iterations). In addition to these fits, attempts
+were also made to include correlations between random effects by using the
+log Cholesky parameterisation of the matrix specifying them. The code
+used for these attempts can be made visible below.
+
+```{r f_parent_nlme_logchol, warning = FALSE, eval = FALSE}
+f_parent_nlme_sfo_const_logchol <- nlme(f_parent_mkin_const["SFO", ],
+  random = pdLogChol(list(DMTA_0 ~ 1, log_k_DMTA ~ 1)))
+anova(f_parent_nlme_sfo_const, f_parent_nlme_sfo_const_logchol) # not better
+f_parent_nlme_dfop_tc_logchol <- update(f_parent_nlme_dfop_tc,
+  random = pdLogChol(list(DMTA_0 ~ 1, log_k1 ~ 1, log_k2 ~ 1, g_qlogis ~ 1)))
+# using log Cholesky parameterisation for random effects (nlme default) does
+# not converge and gives lots of warnings about the LME step not converging
+```
+
+The model comparison function of the nlme package can directly be applied
+to these fits showing a similar goodness-of-fit of the SFO model, but a much
+lower AIC for the DFOP model fitted with the two-component error model.
+Also, the likelihood ratio test indicates that this difference is significant.
+as the p-value is below 0.0001.
+
+```{r AIC_parent_nlme}
+anova(
+  f_parent_nlme_sfo_const, f_parent_nlme_sfo_tc, f_parent_nlme_dfop_tc
+)
+```
+
+The selected model (DFOP with two-component error) fitted to the data assuming
+no correlations between random effects is shown below.
+
+```{r plot_parent_nlme}
+plot(f_parent_nlme_dfop_tc)
+```
+
+### saemix
+
+The saemix package provided the first Open Source implementation of the
+Stochastic Approximation to the Expectation Maximisation (SAEM) algorithm.
+SAEM fits of degradation models can be performed using an interface to the
+saemix package available in current development versions of the mkin package.
+
+The corresponding SAEM fits of the four combinations of degradation and error
+models are fitted below. As there is no convergence criterion implemented in
+the saemix package, the convergence plots need to be manually checked for every
+fit.
+
+The convergence plot for the SFO model using constant variance is shown below.
+
+```{r f_parent_saemix_sfo_const, results = 'hide'}
+library(saemix)
+f_parent_saemix_sfo_const <- saem(f_parent_mkin_const["SFO", ], quiet = TRUE,
+  transformations = "saemix")
+plot(f_parent_saemix_sfo_const$so, plot.type = "convergence")
+```
+
+Obviously the default number of iterations is sufficient to reach convergence.
+This can also be said for the SFO fit using the two-component error model.
+
+```{r f_parent_saemix_sfo_tc, results = 'hide'}
+f_parent_saemix_sfo_tc <- saem(f_parent_mkin_tc["SFO", ], quiet = TRUE,
+  transformations = "saemix")
+plot(f_parent_saemix_sfo_tc$so, plot.type = "convergence")
+```
+
+When fitting the DFOP model with constant variance, parameter convergence
+is not as unambiguous. Therefore, the number of iterations in the first
+phase of the algorithm was increased, leading to visually satisfying
+convergence.
+
+```{r f_parent_saemix_dfop_const, results = 'hide'}
+f_parent_saemix_dfop_const <- saem(f_parent_mkin_const["DFOP", ], quiet = TRUE,
+  control = saemixControl(nbiter.saemix = c(800, 200), print = FALSE,
+    save = FALSE, save.graphs = FALSE, displayProgress = FALSE),
+  transformations = "saemix")
+plot(f_parent_saemix_dfop_const$so, plot.type = "convergence")
+```
+
+The same applies to the case where the DFOP model is fitted with the
+two-component error model. Convergence of the variance of k2 is enhanced
+by using the two-component error, it remains pretty stable already after 200
+iterations of the first phase.
+
+```{r f_parent_saemix_dfop_tc_moreiter, results = 'hide'}
+f_parent_saemix_dfop_tc_moreiter <- saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+  control = saemixControl(nbiter.saemix = c(800, 200), print = FALSE,
+    save = FALSE, save.graphs = FALSE, displayProgress = FALSE),
+  transformations = "saemix")
+plot(f_parent_saemix_dfop_tc_moreiter$so, plot.type = "convergence")
+```
+
+The four combinations can be compared using the model comparison function from the
+saemix package:
+
+```{r AIC_parent_saemix}
+compare.saemix(f_parent_saemix_sfo_const$so, f_parent_saemix_sfo_tc$so,
+  f_parent_saemix_dfop_const$so, f_parent_saemix_dfop_tc_moreiter$so)
+```
+
+As in the case of nlme fits, the DFOP model fitted with two-component error
+(number 4) gives the lowest AIC. The numeric values are reasonably close to
+the ones obtained using nlme, considering that the algorithms for fitting the
+model and for the likelihood calculation are quite different.
+
+In order to check the influence of the likelihood calculation algorithms
+implemented in saemix, the likelihood from Gaussian quadrature is added
+to the best fit, and the AIC values obtained from the three methods
+are compared.
+
+```{r AIC_parent_saemix_methods}
+f_parent_saemix_dfop_tc_moreiter$so <-
+  llgq.saemix(f_parent_saemix_dfop_tc_moreiter$so)
+AIC(f_parent_saemix_dfop_tc_moreiter$so)
+AIC(f_parent_saemix_dfop_tc_moreiter$so, method = "gq")
+AIC(f_parent_saemix_dfop_tc_moreiter$so, method = "lin")
+```
+
+The AIC values based on importance sampling and Gaussian quadrature are quite
+similar. Using linearisation is less accurate, but still gives a similar value.
+
+
+### nlmixr
+
+In the last years, a lot of effort has been put into the nlmixr package which
+is designed for pharmacokinetics, where nonlinear mixed-effects models are
+routinely used, but which can also be used for related data like chemical
+degradation data. A current development branch of the mkin package provides
+an interface between mkin and nlmixr. Here, we check if we get equivalent
+results when using a refined version of the First Order Conditional Estimation
+(FOCE) algorithm used in nlme, namely First Order Conditional Estimation with
+Interaction (FOCEI), and the SAEM algorithm as implemented in nlmixr.
+
+First, the focei algorithm is used for the four model combinations and the
+goodness of fit of the results is compared.
+
+```{r f_parent_nlmixr_focei, results = "hide", message = FALSE, warning = FALSE}
+f_parent_nlmixr_focei_sfo_const <- nlmixr(f_parent_mkin_const["SFO", ], est = "focei")
+f_parent_nlmixr_focei_sfo_tc <- nlmixr(f_parent_mkin_tc["SFO", ], est = "focei")
+f_parent_nlmixr_focei_dfop_const <- nlmixr(f_parent_mkin_const["DFOP", ], est = "focei")
+f_parent_nlmixr_focei_dfop_tc<- nlmixr(f_parent_mkin_tc["DFOP", ], est = "focei")
+```
+
+```{r AIC_parent_nlmixr_focei}
+AIC(f_parent_nlmixr_focei_sfo_const$nm, f_parent_nlmixr_focei_sfo_tc$nm,
+  f_parent_nlmixr_focei_dfop_const$nm, f_parent_nlmixr_focei_dfop_tc$nm)
+```
+
+The AIC values are very close to the ones obtained with nlme.
+
+Secondly, we use the SAEM estimation routine and check the convergence plots for
+SFO with constant variance
+
+```{r f_parent_nlmixr_saem_sfo_const, results = "hide", warning = FALSE, message = FALSE}
+f_parent_nlmixr_saem_sfo_const <- nlmixr(f_parent_mkin_const["SFO", ], est = "saem",
+  control = nlmixr::saemControl(logLik = TRUE))
+traceplot(f_parent_nlmixr_saem_sfo_const$nm)
+```
+
+for SFO with two-component error
+
+```{r f_parent_nlmixr_saem_sfo_tc, results = "hide", warning = FALSE, message = FALSE}
+f_parent_nlmixr_saem_sfo_tc <- nlmixr(f_parent_mkin_tc["SFO", ], est = "saem",
+  control = nlmixr::saemControl(logLik = TRUE))
+nlmixr::traceplot(f_parent_nlmixr_saem_sfo_tc$nm)
+```
+
+For DFOP with constant variance, the convergence plots show considerable instability
+of the fit, which can be alleviated by increasing the number of iterations and
+the number of parallel chains for the first phase of algorithm.
+
+```{r f_parent_nlmixr_saem_dfop_const, results = "hide", warning = FALSE, message = FALSE}
+f_parent_nlmixr_saem_dfop_const <- nlmixr(f_parent_mkin_const["DFOP", ], est = "saem",
+  control = nlmixr::saemControl(logLik = TRUE, nBurn = 1000), nmc = 15)
+nlmixr::traceplot(f_parent_nlmixr_saem_dfop_const$nm)
+```
+
+For DFOP with two-component error, the same increase in iterations and parallel
+chains was used, but using the two-component error appears to lead to a less
+erratic convergence, so this may not be necessary to this degree.
+
+
+```{r f_parent_nlmixr_saem_dfop_tc, results = "hide", warning = FALSE, message = FALSE}
+f_parent_nlmixr_saem_dfop_tc <- nlmixr(f_parent_mkin_tc["DFOP", ], est = "saem",
+  control = nlmixr::saemControl(logLik = TRUE, nBurn = 1000, nmc = 15))
+nlmixr::traceplot(f_parent_nlmixr_saem_dfop_tc$nm)
+```
+
+The AIC values are internally calculated using Gaussian quadrature. For an
+unknown reason, the AIC value obtained for the DFOP fit using the two-component
+error model is given as Infinity.
+
+```{r AIC_parent_nlmixr_saem}
+AIC(f_parent_nlmixr_saem_sfo_const$nm, f_parent_nlmixr_saem_sfo_tc$nm,
+  f_parent_nlmixr_saem_dfop_const$nm, f_parent_nlmixr_saem_dfop_tc$nm)
+```
+
+
+
+
+# References
+
+<!-- vim: set foldmethod=syntax: -->
-- 
cgit v1.2.1


From 0b754ffa91b9496bdd2f892cf3ca2bd887028dea Mon Sep 17 00:00:00 2001
From: Johannes Ranke <jranke@uni-bremen.de>
Date: Tue, 27 Jul 2021 18:22:01 +0200
Subject: Fix dimethenamid vignette problems and update docs

---
 vignettes/web_only/dimethenamid_2018.rmd | 57 ++++++++++++++++++++++----------
 1 file changed, 40 insertions(+), 17 deletions(-)

(limited to 'vignettes/web_only/dimethenamid_2018.rmd')

diff --git a/vignettes/web_only/dimethenamid_2018.rmd b/vignettes/web_only/dimethenamid_2018.rmd
index d3541a34..30325044 100644
--- a/vignettes/web_only/dimethenamid_2018.rmd
+++ b/vignettes/web_only/dimethenamid_2018.rmd
@@ -1,7 +1,7 @@
 ---
 title: Example evaluations of the dimethenamid data from 2018
 author: Johannes Ranke
-date: Last change 23 June 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
+date: Last change 27 July 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
 output:
   html_document:
     toc: true
@@ -163,8 +163,10 @@ tendency of the algorithm to try parameter combinations unsuitable for
 fitting these data.
 
 ```{r f_parent_nlme, warning = FALSE}
+library(nlme)
 f_parent_nlme_sfo_const <- nlme(f_parent_mkin_const["SFO", ])
-#f_parent_nlme_dfop_const <- nlme(f_parent_mkin_const["DFOP", ]) # error
+#f_parent_nlme_dfop_const <- nlme(f_parent_mkin_const["DFOP", ])
+# maxIter = 50 reached
 f_parent_nlme_sfo_tc <- nlme(f_parent_mkin_tc["SFO", ])
 f_parent_nlme_dfop_tc <- nlme(f_parent_mkin_tc["DFOP", ])
 ```
@@ -180,10 +182,10 @@ used for these attempts can be made visible below.
 f_parent_nlme_sfo_const_logchol <- nlme(f_parent_mkin_const["SFO", ],
   random = pdLogChol(list(DMTA_0 ~ 1, log_k_DMTA ~ 1)))
 anova(f_parent_nlme_sfo_const, f_parent_nlme_sfo_const_logchol) # not better
-f_parent_nlme_dfop_tc_logchol <- update(f_parent_nlme_dfop_tc,
-  random = pdLogChol(list(DMTA_0 ~ 1, log_k1 ~ 1, log_k2 ~ 1, g_qlogis ~ 1)))
+#f_parent_nlme_dfop_tc_logchol <- update(f_parent_nlme_dfop_tc,
+#  random = pdLogChol(list(DMTA_0 ~ 1, log_k1 ~ 1, log_k2 ~ 1, g_qlogis ~ 1)))
 # using log Cholesky parameterisation for random effects (nlme default) does
-# not converge and gives lots of warnings about the LME step not converging
+# not converge here and gives lots of warnings about the LME step not converging
 ```
 
 The model comparison function of the nlme package can directly be applied
@@ -221,7 +223,7 @@ The convergence plot for the SFO model using constant variance is shown below.
 
 ```{r f_parent_saemix_sfo_const, results = 'hide'}
 library(saemix)
-f_parent_saemix_sfo_const <- saem(f_parent_mkin_const["SFO", ], quiet = TRUE,
+f_parent_saemix_sfo_const <- mkin::saem(f_parent_mkin_const["SFO", ], quiet = TRUE,
   transformations = "saemix")
 plot(f_parent_saemix_sfo_const$so, plot.type = "convergence")
 ```
@@ -230,18 +232,19 @@ Obviously the default number of iterations is sufficient to reach convergence.
 This can also be said for the SFO fit using the two-component error model.
 
 ```{r f_parent_saemix_sfo_tc, results = 'hide'}
-f_parent_saemix_sfo_tc <- saem(f_parent_mkin_tc["SFO", ], quiet = TRUE,
+f_parent_saemix_sfo_tc <- mkin::saem(f_parent_mkin_tc["SFO", ], quiet = TRUE,
   transformations = "saemix")
 plot(f_parent_saemix_sfo_tc$so, plot.type = "convergence")
 ```
 
 When fitting the DFOP model with constant variance, parameter convergence
-is not as unambiguous. Therefore, the number of iterations in the first
+is not as unambiguous (see the failure of nlme with the default number of
+iterations above). Therefore, the number of iterations in the first
 phase of the algorithm was increased, leading to visually satisfying
 convergence.
 
 ```{r f_parent_saemix_dfop_const, results = 'hide'}
-f_parent_saemix_dfop_const <- saem(f_parent_mkin_const["DFOP", ], quiet = TRUE,
+f_parent_saemix_dfop_const <- mkin::saem(f_parent_mkin_const["DFOP", ], quiet = TRUE,
   control = saemixControl(nbiter.saemix = c(800, 200), print = FALSE,
     save = FALSE, save.graphs = FALSE, displayProgress = FALSE),
   transformations = "saemix")
@@ -250,11 +253,11 @@ plot(f_parent_saemix_dfop_const$so, plot.type = "convergence")
 
 The same applies to the case where the DFOP model is fitted with the
 two-component error model. Convergence of the variance of k2 is enhanced
-by using the two-component error, it remains pretty stable already after 200
+by using the two-component error, it remains more or less stable already after 200
 iterations of the first phase.
 
 ```{r f_parent_saemix_dfop_tc_moreiter, results = 'hide'}
-f_parent_saemix_dfop_tc_moreiter <- saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+f_parent_saemix_dfop_tc_moreiter <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
   control = saemixControl(nbiter.saemix = c(800, 200), print = FALSE,
     save = FALSE, save.graphs = FALSE, displayProgress = FALSE),
   transformations = "saemix")
@@ -306,6 +309,7 @@ First, the focei algorithm is used for the four model combinations and the
 goodness of fit of the results is compared.
 
 ```{r f_parent_nlmixr_focei, results = "hide", message = FALSE, warning = FALSE}
+library(nlmixr)
 f_parent_nlmixr_focei_sfo_const <- nlmixr(f_parent_mkin_const["SFO", ], est = "focei")
 f_parent_nlmixr_focei_sfo_tc <- nlmixr(f_parent_mkin_tc["SFO", ], est = "focei")
 f_parent_nlmixr_focei_dfop_const <- nlmixr(f_parent_mkin_const["DFOP", ], est = "focei")
@@ -317,7 +321,14 @@ AIC(f_parent_nlmixr_focei_sfo_const$nm, f_parent_nlmixr_focei_sfo_tc$nm,
   f_parent_nlmixr_focei_dfop_const$nm, f_parent_nlmixr_focei_dfop_tc$nm)
 ```
 
-The AIC values are very close to the ones obtained with nlme.
+The AIC values are very close to the ones obtained with nlme which are repeated below
+for convenience.
+
+```{r AIC_parent_nlme_rep}
+AIC(
+  f_parent_nlme_sfo_const, f_parent_nlme_sfo_tc, f_parent_nlme_dfop_tc
+)
+```
 
 Secondly, we use the SAEM estimation routine and check the convergence plots for
 SFO with constant variance
@@ -333,7 +344,7 @@ for SFO with two-component error
 ```{r f_parent_nlmixr_saem_sfo_tc, results = "hide", warning = FALSE, message = FALSE}
 f_parent_nlmixr_saem_sfo_tc <- nlmixr(f_parent_mkin_tc["SFO", ], est = "saem",
   control = nlmixr::saemControl(logLik = TRUE))
-nlmixr::traceplot(f_parent_nlmixr_saem_sfo_tc$nm)
+traceplot(f_parent_nlmixr_saem_sfo_tc$nm)
 ```
 
 For DFOP with constant variance, the convergence plots show considerable instability
@@ -343,7 +354,7 @@ the number of parallel chains for the first phase of algorithm.
 ```{r f_parent_nlmixr_saem_dfop_const, results = "hide", warning = FALSE, message = FALSE}
 f_parent_nlmixr_saem_dfop_const <- nlmixr(f_parent_mkin_const["DFOP", ], est = "saem",
   control = nlmixr::saemControl(logLik = TRUE, nBurn = 1000), nmc = 15)
-nlmixr::traceplot(f_parent_nlmixr_saem_dfop_const$nm)
+traceplot(f_parent_nlmixr_saem_dfop_const$nm)
 ```
 
 For DFOP with two-component error, the same increase in iterations and parallel
@@ -354,7 +365,7 @@ erratic convergence, so this may not be necessary to this degree.
 ```{r f_parent_nlmixr_saem_dfop_tc, results = "hide", warning = FALSE, message = FALSE}
 f_parent_nlmixr_saem_dfop_tc <- nlmixr(f_parent_mkin_tc["DFOP", ], est = "saem",
   control = nlmixr::saemControl(logLik = TRUE, nBurn = 1000, nmc = 15))
-nlmixr::traceplot(f_parent_nlmixr_saem_dfop_tc$nm)
+traceplot(f_parent_nlmixr_saem_dfop_tc$nm)
 ```
 
 The AIC values are internally calculated using Gaussian quadrature. For an
@@ -366,8 +377,20 @@ AIC(f_parent_nlmixr_saem_sfo_const$nm, f_parent_nlmixr_saem_sfo_tc$nm,
   f_parent_nlmixr_saem_dfop_const$nm, f_parent_nlmixr_saem_dfop_tc$nm)
 ```
 
-
-
+The following table gives the AIC values obtained with the three packages.
+
+```{r AIC_all}
+AIC_all <- data.frame(
+  nlme = c(AIC(f_parent_nlme_sfo_const), AIC(f_parent_nlme_sfo_tc), NA, AIC(f_parent_nlme_dfop_tc)),
+  nlmixr_focei = sapply(list(f_parent_nlmixr_focei_sfo_const$nm, f_parent_nlmixr_focei_sfo_tc$nm,
+  f_parent_nlmixr_focei_dfop_const$nm, f_parent_nlmixr_focei_dfop_tc$nm), AIC),
+  saemix = sapply(list(f_parent_saemix_sfo_const$so, f_parent_saemix_sfo_tc$so,
+    f_parent_saemix_dfop_const$so, f_parent_saemix_dfop_tc_moreiter$so), AIC),
+  nlmixr_saem = sapply(list(f_parent_nlmixr_saem_sfo_const$nm, f_parent_nlmixr_saem_sfo_tc$nm,
+  f_parent_nlmixr_saem_dfop_const$nm, f_parent_nlmixr_saem_dfop_tc$nm), AIC)
+)
+kable(AIC_all)
+```
 
 # References
 
-- 
cgit v1.2.1


From 51fab94230e926cec690dc455964bd797a97b7c7 Mon Sep 17 00:00:00 2001
From: Johannes Ranke <jranke@uni-bremen.de>
Date: Wed, 4 Aug 2021 16:37:52 +0200
Subject: Improve AIC table in vignette

---
 vignettes/web_only/dimethenamid_2018.rmd | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'vignettes/web_only/dimethenamid_2018.rmd')

diff --git a/vignettes/web_only/dimethenamid_2018.rmd b/vignettes/web_only/dimethenamid_2018.rmd
index 30325044..c152e578 100644
--- a/vignettes/web_only/dimethenamid_2018.rmd
+++ b/vignettes/web_only/dimethenamid_2018.rmd
@@ -1,7 +1,7 @@
 ---
 title: Example evaluations of the dimethenamid data from 2018
 author: Johannes Ranke
-date: Last change 27 July 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
+date: Last change 4 August 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
 output:
   html_document:
     toc: true
@@ -381,6 +381,8 @@ The following table gives the AIC values obtained with the three packages.
 
 ```{r AIC_all}
 AIC_all <- data.frame(
+  "Degradation model" = c("SFO", "SFO", "DFOP", "DFOP"),
+  "Error model" = c("const", "tc", "const", "tc"),
   nlme = c(AIC(f_parent_nlme_sfo_const), AIC(f_parent_nlme_sfo_tc), NA, AIC(f_parent_nlme_dfop_tc)),
   nlmixr_focei = sapply(list(f_parent_nlmixr_focei_sfo_const$nm, f_parent_nlmixr_focei_sfo_tc$nm,
   f_parent_nlmixr_focei_dfop_const$nm, f_parent_nlmixr_focei_dfop_tc$nm), AIC),
-- 
cgit v1.2.1


From c41381a961263c28d60976e68923157916c78b15 Mon Sep 17 00:00:00 2001
From: Johannes Ranke <jranke@uni-bremen.de>
Date: Thu, 16 Sep 2021 15:31:13 +0200
Subject: Adapt and improve the dimethenamid vignette

Adapt to the corrected data and unify control parameters for saemix and
nlmixr with saem. Update docs
---
 vignettes/web_only/dimethenamid_2018.rmd | 248 +++++++++++++++++--------------
 1 file changed, 135 insertions(+), 113 deletions(-)

(limited to 'vignettes/web_only/dimethenamid_2018.rmd')

diff --git a/vignettes/web_only/dimethenamid_2018.rmd b/vignettes/web_only/dimethenamid_2018.rmd
index c152e578..e5c8764d 100644
--- a/vignettes/web_only/dimethenamid_2018.rmd
+++ b/vignettes/web_only/dimethenamid_2018.rmd
@@ -1,7 +1,7 @@
 ---
 title: Example evaluations of the dimethenamid data from 2018
 author: Johannes Ranke
-date: Last change 4 August 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
+date: Last change 16 September 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
 output:
   html_document:
     toc: true
@@ -14,8 +14,7 @@ vignette: >
   %\VignetteEncoding{UTF-8}
 ---
 
-[Wissenschaftlicher Berater, Kronacher Str. 12, 79639 Grenzach-Wyhlen, Germany](http://www.jrwb.de)<br />
-[Privatdozent at the University of Bremen](http://chem.uft.uni-bremen.de/ranke)
+[Wissenschaftlicher Berater, Kronacher Str. 12, 79639 Grenzach-Wyhlen, Germany](http://www.jrwb.de)
 
 ```{r, include = FALSE}
 require(knitr)
@@ -29,10 +28,11 @@ opts_chunk$set(
 
 # Introduction
 
-During the preparation of the journal article on nonlinear mixed-effects models in
-degradation kinetics (submitted) and the analysis of the dimethenamid degradation
-data analysed therein, a need for a more detailed analysis using not only nlme and saemix,
-but also nlmixr for fitting the mixed-effects models was identified.
+During the preparation of the journal article on nonlinear mixed-effects models
+in degradation kinetics [@ranke2021] and the analysis of the dimethenamid
+degradation data analysed therein, a need for a more detailed analysis using
+not only nlme and saemix, but also nlmixr for fitting the mixed-effects models
+was identified.
 
 This vignette is an attempt to satisfy this need.
 
@@ -42,8 +42,8 @@ Residue data forming the basis for the endpoints derived in the conclusion on
 the peer review of the pesticide risk assessment of dimethenamid-P published by
 the European Food Safety Authority (EFSA) in 2018 [@efsa_2018_dimethenamid]
 were transcribed from the risk assessment report [@dimethenamid_rar_2018_b8]
-which can be downloaded from the
-[EFSA register of questions](https://open.efsa.europa.eu/study-inventory/EFSA-Q-2014-00716).
+which can be downloaded from the Open EFSA repository
+[https://open.efsa.europa.eu/study-inventory/EFSA-Q-2014-00716](https://open.efsa.europa.eu).
 
 The data are [available in the mkin
 package](https://pkgdown.jrwb.de/mkin/reference/dimethenamid_2018.html). The
@@ -60,16 +60,13 @@ Also, datasets observed in the same soil are merged, resulting in dimethenamid
 
 ```{r dimethenamid_data}
 library(mkin)
-dmta_ds <- lapply(1:8, function(i) {
+dmta_ds <- lapply(1:7, function(i) {
   ds_i <- dimethenamid_2018$ds[[i]]$data
   ds_i[ds_i$name == "DMTAP", "name"] <-  "DMTA"
   ds_i$time <- ds_i$time * dimethenamid_2018$f_time_norm[i]
   ds_i
 })
 names(dmta_ds) <- sapply(dimethenamid_2018$ds, function(ds) ds$title)
-dmta_ds[["Borstel"]] <- rbind(dmta_ds[["Borstel 1"]], dmta_ds[["Borstel 2"]])
-dmta_ds[["Borstel 1"]] <- NULL
-dmta_ds[["Borstel 2"]] <- NULL
 dmta_ds[["Elliot"]] <- rbind(dmta_ds[["Elliot 1"]], dmta_ds[["Elliot 2"]])
 dmta_ds[["Elliot 1"]] <- NULL
 dmta_ds[["Elliot 2"]] <- NULL
@@ -150,7 +147,7 @@ packages, with different algorithms and checking control parameters.
 ### nlme
 
 The nlme package was the first R extension providing facilities to fit nonlinear
-mixed-effects models. We use would like to do model selection from all four
+mixed-effects models. We would like to do model selection from all four
 combinations of degradation models and error models based on the AIC.
 However, fitting the DFOP model with constant variance and using default
 control parameters results in an error, signalling that the maximum number
@@ -165,34 +162,20 @@ fitting these data.
 ```{r f_parent_nlme, warning = FALSE}
 library(nlme)
 f_parent_nlme_sfo_const <- nlme(f_parent_mkin_const["SFO", ])
-#f_parent_nlme_dfop_const <- nlme(f_parent_mkin_const["DFOP", ])
-# maxIter = 50 reached
+# f_parent_nlme_dfop_const <- nlme(f_parent_mkin_const["DFOP", ])
 f_parent_nlme_sfo_tc <- nlme(f_parent_mkin_tc["SFO", ])
 f_parent_nlme_dfop_tc <- nlme(f_parent_mkin_tc["DFOP", ])
 ```
-
-Note that overparameterisation is also indicated by warnings obtained when
-fitting SFO or DFOP with the two-component error model ('false convergence' in
-the 'LME step' in some iterations). In addition to these fits, attempts
-were also made to include correlations between random effects by using the
-log Cholesky parameterisation of the matrix specifying them. The code
-used for these attempts can be made visible below.
-
-```{r f_parent_nlme_logchol, warning = FALSE, eval = FALSE}
-f_parent_nlme_sfo_const_logchol <- nlme(f_parent_mkin_const["SFO", ],
-  random = pdLogChol(list(DMTA_0 ~ 1, log_k_DMTA ~ 1)))
-anova(f_parent_nlme_sfo_const, f_parent_nlme_sfo_const_logchol) # not better
-#f_parent_nlme_dfop_tc_logchol <- update(f_parent_nlme_dfop_tc,
-#  random = pdLogChol(list(DMTA_0 ~ 1, log_k1 ~ 1, log_k2 ~ 1, g_qlogis ~ 1)))
-# using log Cholesky parameterisation for random effects (nlme default) does
-# not converge here and gives lots of warnings about the LME step not converging
-```
+Note that a certain degree of overparameterisation is also indicated by a
+warning obtained when fitting DFOP with the two-component error model ('false
+convergence' in the 'LME step' in iteration 3). However, as this warning does
+not occur in later iterations, and specifically not in the last of the
+`r f_parent_nlme_dfop_tc$numIter` iterations, we can ignore this warning.
 
 The model comparison function of the nlme package can directly be applied
-to these fits showing a similar goodness-of-fit of the SFO model, but a much
-lower AIC for the DFOP model fitted with the two-component error model.
-Also, the likelihood ratio test indicates that this difference is significant.
-as the p-value is below 0.0001.
+to these fits showing a much lower AIC for the DFOP model fitted with the
+two-component error model. Also, the likelihood ratio test indicates that this
+difference is significant. as the p-value is below 0.0001.
 
 ```{r AIC_parent_nlme}
 anova(
@@ -200,6 +183,27 @@ anova(
 )
 ```
 
+In addition to these fits, attempts were also made to include correlations
+between random effects by using the log Cholesky parameterisation of the matrix
+specifying them. The code used for these attempts can be made visible below.
+
+```{r f_parent_nlme_logchol, warning = FALSE, eval = FALSE}
+f_parent_nlme_sfo_const_logchol <- nlme(f_parent_mkin_const["SFO", ],
+  random = nlme::pdLogChol(list(DMTA_0 ~ 1, log_k_DMTA ~ 1)))
+anova(f_parent_nlme_sfo_const, f_parent_nlme_sfo_const_logchol)
+f_parent_nlme_sfo_tc_logchol <- nlme(f_parent_mkin_tc["SFO", ],
+  random = nlme::pdLogChol(list(DMTA_0 ~ 1, log_k_DMTA ~ 1)))
+anova(f_parent_nlme_sfo_tc, f_parent_nlme_sfo_tc_logchol)
+f_parent_nlme_dfop_tc_logchol <- nlme(f_parent_mkin_const["DFOP", ],
+  random = nlme::pdLogChol(list(DMTA_0 ~ 1, log_k1 ~ 1, log_k2 ~ 1, g_qlogis ~ 1)))
+anova(f_parent_nlme_dfop_tc, f_parent_nlme_dfop_tc_logchol)
+```
+
+While the SFO variants converge fast, the additional parameters introduced
+by this lead to convergence warnings for the DFOP model. The model comparison
+clearly show that adding correlations between random effects does not improve
+the fits.
+
 The selected model (DFOP with two-component error) fitted to the data assuming
 no correlations between random effects is shown below.
 
@@ -211,29 +215,37 @@ plot(f_parent_nlme_dfop_tc)
 
 The saemix package provided the first Open Source implementation of the
 Stochastic Approximation to the Expectation Maximisation (SAEM) algorithm.
-SAEM fits of degradation models can be performed using an interface to the
-saemix package available in current development versions of the mkin package.
+SAEM fits of degradation models can be conveniently performed using an
+interface to the saemix package available in current development versions of
+the mkin package.
 
 The corresponding SAEM fits of the four combinations of degradation and error
 models are fitted below. As there is no convergence criterion implemented in
 the saemix package, the convergence plots need to be manually checked for every
-fit.
+fit. As we will compare the SAEM implementation of saemix to the results
+obtained using the nlmixr package later, we define control settings that
+work well for all the parent data fits shown in this vignette.
+
+```{r saemix_control}
+library(saemix)
+saemix_control <- saemixControl(nbiter.saemix = c(800, 300), nb.chains = 15,
+    print = FALSE, save = FALSE, save.graphs = FALSE, displayProgress = FALSE)
+```
 
 The convergence plot for the SFO model using constant variance is shown below.
 
-```{r f_parent_saemix_sfo_const, results = 'hide'}
-library(saemix)
+```{r f_parent_saemix_sfo_const, results = 'hide', dependson = "saemix_control"}
 f_parent_saemix_sfo_const <- mkin::saem(f_parent_mkin_const["SFO", ], quiet = TRUE,
-  transformations = "saemix")
+  control = saemix_control, transformations = "saemix")
 plot(f_parent_saemix_sfo_const$so, plot.type = "convergence")
 ```
 
 Obviously the default number of iterations is sufficient to reach convergence.
 This can also be said for the SFO fit using the two-component error model.
 
-```{r f_parent_saemix_sfo_tc, results = 'hide'}
+```{r f_parent_saemix_sfo_tc, results = 'hide', dependson = "saemix_control"}
 f_parent_saemix_sfo_tc <- mkin::saem(f_parent_mkin_tc["SFO", ], quiet = TRUE,
-  transformations = "saemix")
+  control = saemix_control, transformations = "saemix")
 plot(f_parent_saemix_sfo_tc$so, plot.type = "convergence")
 ```
 
@@ -243,56 +255,52 @@ iterations above). Therefore, the number of iterations in the first
 phase of the algorithm was increased, leading to visually satisfying
 convergence.
 
-```{r f_parent_saemix_dfop_const, results = 'hide'}
+```{r f_parent_saemix_dfop_const, results = 'hide', dependson = "saemix_control"}
 f_parent_saemix_dfop_const <- mkin::saem(f_parent_mkin_const["DFOP", ], quiet = TRUE,
-  control = saemixControl(nbiter.saemix = c(800, 200), print = FALSE,
-    save = FALSE, save.graphs = FALSE, displayProgress = FALSE),
-  transformations = "saemix")
+  control = saemix_control, transformations = "saemix")
 plot(f_parent_saemix_dfop_const$so, plot.type = "convergence")
 ```
 
-The same applies to the case where the DFOP model is fitted with the
-two-component error model. Convergence of the variance of k2 is enhanced
-by using the two-component error, it remains more or less stable already after 200
-iterations of the first phase.
-
-```{r f_parent_saemix_dfop_tc_moreiter, results = 'hide'}
-f_parent_saemix_dfop_tc_moreiter <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
-  control = saemixControl(nbiter.saemix = c(800, 200), print = FALSE,
-    save = FALSE, save.graphs = FALSE, displayProgress = FALSE),
-  transformations = "saemix")
-plot(f_parent_saemix_dfop_tc_moreiter$so, plot.type = "convergence")
-```
-
-The four combinations can be compared using the model comparison function from the
-saemix package:
+The same applies in the case where the DFOP model is fitted with the
+two-component error model. Convergence of the variance of k2 is enhanced by
+using the two-component error, it remains more or less stable already after
+200 iterations of the first phase.
 
-```{r AIC_parent_saemix}
-compare.saemix(f_parent_saemix_sfo_const$so, f_parent_saemix_sfo_tc$so,
-  f_parent_saemix_dfop_const$so, f_parent_saemix_dfop_tc_moreiter$so)
+```{r f_parent_saemix_dfop_tc, results = 'hide', dependson = "saemix_control"}
+f_parent_saemix_dfop_tc <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+  control = saemix_control, transformations = "saemix")
+plot(f_parent_saemix_dfop_tc$so, plot.type = "convergence")
+```
+The four combinations and including the variations of the DFOP/tc combination
+can be compared using the model comparison function from the saemix package:
+
+```{r AIC_parent_saemix, cache = FALSE}
+compare.saemix(
+  f_parent_saemix_sfo_const$so,
+  f_parent_saemix_sfo_tc$so,
+  f_parent_saemix_dfop_const$so,
+  f_parent_saemix_dfop_tc$so)
 ```
 
 As in the case of nlme fits, the DFOP model fitted with two-component error
-(number 4) gives the lowest AIC. The numeric values are reasonably close to
-the ones obtained using nlme, considering that the algorithms for fitting the
-model and for the likelihood calculation are quite different.
+(number 4) gives the lowest AIC. Using more iterations and/or more chains
+does not have a large influence on the final AIC (not shown).
 
 In order to check the influence of the likelihood calculation algorithms
 implemented in saemix, the likelihood from Gaussian quadrature is added
 to the best fit, and the AIC values obtained from the three methods
 are compared.
 
-```{r AIC_parent_saemix_methods}
-f_parent_saemix_dfop_tc_moreiter$so <-
-  llgq.saemix(f_parent_saemix_dfop_tc_moreiter$so)
-AIC(f_parent_saemix_dfop_tc_moreiter$so)
-AIC(f_parent_saemix_dfop_tc_moreiter$so, method = "gq")
-AIC(f_parent_saemix_dfop_tc_moreiter$so, method = "lin")
+```{r AIC_parent_saemix_methods, cache = FALSE}
+f_parent_saemix_dfop_tc$so <-
+  llgq.saemix(f_parent_saemix_dfop_tc$so)
+AIC(f_parent_saemix_dfop_tc$so)
+AIC(f_parent_saemix_dfop_tc$so, method = "gq")
+AIC(f_parent_saemix_dfop_tc$so, method = "lin")
 ```
-
-The AIC values based on importance sampling and Gaussian quadrature are quite
-similar. Using linearisation is less accurate, but still gives a similar value.
-
+The AIC values based on importance sampling and Gaussian quadrature are very
+similar. Using linearisation is known to be less accurate, but still gives a
+similar value.
 
 ### nlmixr
 
@@ -302,11 +310,11 @@ routinely used, but which can also be used for related data like chemical
 degradation data. A current development branch of the mkin package provides
 an interface between mkin and nlmixr. Here, we check if we get equivalent
 results when using a refined version of the First Order Conditional Estimation
-(FOCE) algorithm used in nlme, namely First Order Conditional Estimation with
-Interaction (FOCEI), and the SAEM algorithm as implemented in nlmixr.
+(FOCE) algorithm used in nlme, namely the First Order Conditional Estimation
+with Interaction (FOCEI), and the SAEM algorithm as implemented in nlmixr.
 
-First, the focei algorithm is used for the four model combinations and the
-goodness of fit of the results is compared.
+First, the focei algorithm is used for the four model combinations. A number of
+warnings are produced with unclear significance.
 
 ```{r f_parent_nlmixr_focei, results = "hide", message = FALSE, warning = FALSE}
 library(nlmixr)
@@ -316,78 +324,92 @@ f_parent_nlmixr_focei_dfop_const <- nlmixr(f_parent_mkin_const["DFOP", ], est =
 f_parent_nlmixr_focei_dfop_tc<- nlmixr(f_parent_mkin_tc["DFOP", ], est = "focei")
 ```
 
-```{r AIC_parent_nlmixr_focei}
-AIC(f_parent_nlmixr_focei_sfo_const$nm, f_parent_nlmixr_focei_sfo_tc$nm,
-  f_parent_nlmixr_focei_dfop_const$nm, f_parent_nlmixr_focei_dfop_tc$nm)
+```{r AIC_parent_nlmixr_focei, cache = FALSE}
+aic_nlmixr_focei <- sapply(
+  list(f_parent_nlmixr_focei_sfo_const$nm, f_parent_nlmixr_focei_sfo_tc$nm,
+    f_parent_nlmixr_focei_dfop_const$nm, f_parent_nlmixr_focei_dfop_tc$nm),
+  AIC)
 ```
 
 The AIC values are very close to the ones obtained with nlme which are repeated below
 for convenience.
 
-```{r AIC_parent_nlme_rep}
-AIC(
-  f_parent_nlme_sfo_const, f_parent_nlme_sfo_tc, f_parent_nlme_dfop_tc
+```{r AIC_parent_nlme_rep, cache = FALSE}
+aic_nlme <- sapply(
+  list(f_parent_nlme_sfo_const, NA, f_parent_nlme_sfo_tc, f_parent_nlme_dfop_tc),
+  function(x) if (is.na(x[1])) NA else AIC(x))
+aic_nlme_nlmixr_focei <- data.frame(
+  "Degradation model" = c("SFO", "SFO", "DFOP", "DFOP"),
+  "Error model" = rep(c("constant variance", "two-component"), 2),
+  "AIC (nlme)" = aic_nlme,
+  "AIC (nlmixr with FOCEI)" = aic_nlmixr_focei,
+  check.names = FALSE
 )
 ```
 
-Secondly, we use the SAEM estimation routine and check the convergence plots for
-SFO with constant variance
+Secondly, we use the SAEM estimation routine and check the convergence plots. The
+control parameters also used for the saemix fits are defined beforehand.
+
+```{r nlmixr_saem_control}
+nlmixr_saem_control <- saemControl(logLik = TRUE,
+  nBurn = 1000, nEm = 300, nmc = 15)
+```
+
+The we fit SFO with constant variance
 
-```{r f_parent_nlmixr_saem_sfo_const, results = "hide", warning = FALSE, message = FALSE}
+```{r f_parent_nlmixr_saem_sfo_const, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_sfo_const <- nlmixr(f_parent_mkin_const["SFO", ], est = "saem",
-  control = nlmixr::saemControl(logLik = TRUE))
+  control = nlmixr_saem_control)
 traceplot(f_parent_nlmixr_saem_sfo_const$nm)
 ```
 
-for SFO with two-component error
+and SFO with two-component error.
 
-```{r f_parent_nlmixr_saem_sfo_tc, results = "hide", warning = FALSE, message = FALSE}
+```{r f_parent_nlmixr_saem_sfo_tc, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_sfo_tc <- nlmixr(f_parent_mkin_tc["SFO", ], est = "saem",
-  control = nlmixr::saemControl(logLik = TRUE))
+  control = nlmixr_saem_control)
 traceplot(f_parent_nlmixr_saem_sfo_tc$nm)
 ```
 
-For DFOP with constant variance, the convergence plots show considerable instability
-of the fit, which can be alleviated by increasing the number of iterations and
-the number of parallel chains for the first phase of algorithm.
+For DFOP with constant variance, the convergence plots show considerable
+instability of the fit, which indicates overparameterisation which was already
+observed earlier for this model combination.
 
-```{r f_parent_nlmixr_saem_dfop_const, results = "hide", warning = FALSE, message = FALSE}
+```{r f_parent_nlmixr_saem_dfop_const, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_dfop_const <- nlmixr(f_parent_mkin_const["DFOP", ], est = "saem",
-  control = nlmixr::saemControl(logLik = TRUE, nBurn = 1000), nmc = 15)
+  control = nlmixr_saem_control)
 traceplot(f_parent_nlmixr_saem_dfop_const$nm)
 ```
 
-For DFOP with two-component error, the same increase in iterations and parallel
-chains was used, but using the two-component error appears to lead to a less
-erratic convergence, so this may not be necessary to this degree.
-
+For DFOP with two-component error, a less erratic convergence is seen.
 
-```{r f_parent_nlmixr_saem_dfop_tc, results = "hide", warning = FALSE, message = FALSE}
+```{r f_parent_nlmixr_saem_dfop_tc, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_dfop_tc <- nlmixr(f_parent_mkin_tc["DFOP", ], est = "saem",
-  control = nlmixr::saemControl(logLik = TRUE, nBurn = 1000, nmc = 15))
+  control = nlmixr_saem_control)
 traceplot(f_parent_nlmixr_saem_dfop_tc$nm)
 ```
 
 The AIC values are internally calculated using Gaussian quadrature. For an
-unknown reason, the AIC value obtained for the DFOP fit using the two-component
-error model is given as Infinity.
+unknown reason, the AIC value obtained for the DFOP fit using constant error
+is given as Infinity.
 
-```{r AIC_parent_nlmixr_saem}
+```{r AIC_parent_nlmixr_saem, cache = FALSE}
 AIC(f_parent_nlmixr_saem_sfo_const$nm, f_parent_nlmixr_saem_sfo_tc$nm,
   f_parent_nlmixr_saem_dfop_const$nm, f_parent_nlmixr_saem_dfop_tc$nm)
 ```
 
 The following table gives the AIC values obtained with the three packages.
 
-```{r AIC_all}
+```{r AIC_all, cache = FALSE}
 AIC_all <- data.frame(
+  check.names = FALSE,
   "Degradation model" = c("SFO", "SFO", "DFOP", "DFOP"),
   "Error model" = c("const", "tc", "const", "tc"),
   nlme = c(AIC(f_parent_nlme_sfo_const), AIC(f_parent_nlme_sfo_tc), NA, AIC(f_parent_nlme_dfop_tc)),
   nlmixr_focei = sapply(list(f_parent_nlmixr_focei_sfo_const$nm, f_parent_nlmixr_focei_sfo_tc$nm,
   f_parent_nlmixr_focei_dfop_const$nm, f_parent_nlmixr_focei_dfop_tc$nm), AIC),
   saemix = sapply(list(f_parent_saemix_sfo_const$so, f_parent_saemix_sfo_tc$so,
-    f_parent_saemix_dfop_const$so, f_parent_saemix_dfop_tc_moreiter$so), AIC),
+    f_parent_saemix_dfop_const$so, f_parent_saemix_dfop_tc$so), AIC),
   nlmixr_saem = sapply(list(f_parent_nlmixr_saem_sfo_const$nm, f_parent_nlmixr_saem_sfo_tc$nm,
   f_parent_nlmixr_saem_dfop_const$nm, f_parent_nlmixr_saem_dfop_tc$nm), AIC)
 )
-- 
cgit v1.2.1


From 047d048b89e167fb354b45cd7c6b719b9f4cdd28 Mon Sep 17 00:00:00 2001
From: Johannes Ranke <jranke@uni-bremen.de>
Date: Fri, 17 Sep 2021 08:47:09 +0200
Subject: Put the AIC comparison in a subsubsection

---
 vignettes/web_only/dimethenamid_2018.rmd | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

(limited to 'vignettes/web_only/dimethenamid_2018.rmd')

diff --git a/vignettes/web_only/dimethenamid_2018.rmd b/vignettes/web_only/dimethenamid_2018.rmd
index e5c8764d..7679edc4 100644
--- a/vignettes/web_only/dimethenamid_2018.rmd
+++ b/vignettes/web_only/dimethenamid_2018.rmd
@@ -1,7 +1,7 @@
 ---
 title: Example evaluations of the dimethenamid data from 2018
 author: Johannes Ranke
-date: Last change 16 September 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
+date: Last change 17 September 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
 output:
   html_document:
     toc: true
@@ -32,7 +32,8 @@ During the preparation of the journal article on nonlinear mixed-effects models
 in degradation kinetics [@ranke2021] and the analysis of the dimethenamid
 degradation data analysed therein, a need for a more detailed analysis using
 not only nlme and saemix, but also nlmixr for fitting the mixed-effects models
-was identified.
+was identified, as many model variants do not converge when fitted with nlme,
+and not all relevant error models can be fitted with saemix.
 
 This vignette is an attempt to satisfy this need.
 
@@ -59,7 +60,7 @@ Also, datasets observed in the same soil are merged, resulting in dimethenamid
 (DMTA) data from six soils.
 
 ```{r dimethenamid_data}
-library(mkin)
+library(mkin, quietly = TRUE)
 dmta_ds <- lapply(1:7, function(i) {
   ds_i <- dimethenamid_2018$ds[[i]]$data
   ds_i[ds_i$name == "DMTAP", "name"] <-  "DMTA"
@@ -294,9 +295,12 @@ are compared.
 ```{r AIC_parent_saemix_methods, cache = FALSE}
 f_parent_saemix_dfop_tc$so <-
   llgq.saemix(f_parent_saemix_dfop_tc$so)
-AIC(f_parent_saemix_dfop_tc$so)
-AIC(f_parent_saemix_dfop_tc$so, method = "gq")
-AIC(f_parent_saemix_dfop_tc$so, method = "lin")
+AIC_parent_saemix_methods <- c(
+  is = AIC(f_parent_saemix_dfop_tc$so, method = "is"),
+  gq = AIC(f_parent_saemix_dfop_tc$so, method = "gq"),
+  lin = AIC(f_parent_saemix_dfop_tc$so, method = "lin")
+)
+print(AIC_parent_saemix_methods)
 ```
 The AIC values based on importance sampling and Gaussian quadrature are very
 similar. Using linearisation is known to be less accurate, but still gives a
@@ -398,6 +402,8 @@ AIC(f_parent_nlmixr_saem_sfo_const$nm, f_parent_nlmixr_saem_sfo_tc$nm,
   f_parent_nlmixr_saem_dfop_const$nm, f_parent_nlmixr_saem_dfop_tc$nm)
 ```
 
+### Comparison
+
 The following table gives the AIC values obtained with the three packages.
 
 ```{r AIC_all, cache = FALSE}
@@ -416,6 +422,8 @@ AIC_all <- data.frame(
 kable(AIC_all)
 ```
 
+
+
 # References
 
 <!-- vim: set foldmethod=syntax: -->
-- 
cgit v1.2.1


From 5c15ef747568b3a9a9c094b6aa546dc80e3aa87a Mon Sep 17 00:00:00 2001
From: Johannes Ranke <jranke@uni-bremen.de>
Date: Mon, 27 Sep 2021 20:10:01 +0200
Subject: intervals() methods, more DFOP/tc variants

---
 vignettes/web_only/dimethenamid_2018.rmd | 147 +++++++++++++++++++++++++------
 1 file changed, 118 insertions(+), 29 deletions(-)

(limited to 'vignettes/web_only/dimethenamid_2018.rmd')

diff --git a/vignettes/web_only/dimethenamid_2018.rmd b/vignettes/web_only/dimethenamid_2018.rmd
index 7679edc4..ae93984d 100644
--- a/vignettes/web_only/dimethenamid_2018.rmd
+++ b/vignettes/web_only/dimethenamid_2018.rmd
@@ -1,7 +1,7 @@
 ---
 title: Example evaluations of the dimethenamid data from 2018
 author: Johannes Ranke
-date: Last change 17 September 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
+date: Last change 27 September 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
 output:
   html_document:
     toc: true
@@ -18,6 +18,8 @@ vignette: >
 
 ```{r, include = FALSE}
 require(knitr)
+require(mkin)
+require(nlme)
 options(digits = 5)
 opts_chunk$set(
   comment = "",
@@ -153,7 +155,7 @@ combinations of degradation models and error models based on the AIC.
 However, fitting the DFOP model with constant variance and using default
 control parameters results in an error, signalling that the maximum number
 of 50 iterations was reached, potentially indicating overparameterisation.
-However, the algorithm converges when the two-component error model is
+Nevertheless, the algorithm converges when the two-component error model is
 used in combination with the DFOP model. This can be explained by the fact
 that the smaller residues observed at later sampling times get more
 weight when using the two-component error model which will counteract the
@@ -167,6 +169,7 @@ f_parent_nlme_sfo_const <- nlme(f_parent_mkin_const["SFO", ])
 f_parent_nlme_sfo_tc <- nlme(f_parent_mkin_tc["SFO", ])
 f_parent_nlme_dfop_tc <- nlme(f_parent_mkin_tc["DFOP", ])
 ```
+
 Note that a certain degree of overparameterisation is also indicated by a
 warning obtained when fitting DFOP with the two-component error model ('false
 convergence' in the 'LME step' in iteration 3). However, as this warning does
@@ -176,7 +179,7 @@ not occur in later iterations, and specifically not in the last of the
 The model comparison function of the nlme package can directly be applied
 to these fits showing a much lower AIC for the DFOP model fitted with the
 two-component error model. Also, the likelihood ratio test indicates that this
-difference is significant. as the p-value is below 0.0001.
+difference is significant as the p-value is below 0.0001.
 
 ```{r AIC_parent_nlme}
 anova(
@@ -231,6 +234,8 @@ work well for all the parent data fits shown in this vignette.
 library(saemix)
 saemix_control <- saemixControl(nbiter.saemix = c(800, 300), nb.chains = 15,
     print = FALSE, save = FALSE, save.graphs = FALSE, displayProgress = FALSE)
+saemix_control_10k <- saemixControl(nbiter.saemix = c(10000, 1000), nb.chains = 15,
+    print = FALSE, save = FALSE, save.graphs = FALSE, displayProgress = FALSE)
 ```
 
 The convergence plot for the SFO model using constant variance is shown below.
@@ -250,11 +255,8 @@ f_parent_saemix_sfo_tc <- mkin::saem(f_parent_mkin_tc["SFO", ], quiet = TRUE,
 plot(f_parent_saemix_sfo_tc$so, plot.type = "convergence")
 ```
 
-When fitting the DFOP model with constant variance, parameter convergence
-is not as unambiguous (see the failure of nlme with the default number of
-iterations above). Therefore, the number of iterations in the first
-phase of the algorithm was increased, leading to visually satisfying
-convergence.
+When fitting the DFOP model with constant variance (see below), parameter
+convergence is not as unambiguous.
 
 ```{r f_parent_saemix_dfop_const, results = 'hide', dependson = "saemix_control"}
 f_parent_saemix_dfop_const <- mkin::saem(f_parent_mkin_const["DFOP", ], quiet = TRUE,
@@ -262,30 +264,71 @@ f_parent_saemix_dfop_const <- mkin::saem(f_parent_mkin_const["DFOP", ], quiet =
 plot(f_parent_saemix_dfop_const$so, plot.type = "convergence")
 ```
 
-The same applies in the case where the DFOP model is fitted with the
-two-component error model. Convergence of the variance of k2 is enhanced by
-using the two-component error, it remains more or less stable already after
-200 iterations of the first phase.
+This is improved when the DFOP model is fitted with the two-component error
+model. Convergence of the variance of k2 is enhanced, it remains more or less
+stable already after 200 iterations of the first phase.
 
 ```{r f_parent_saemix_dfop_tc, results = 'hide', dependson = "saemix_control"}
 f_parent_saemix_dfop_tc <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
   control = saemix_control, transformations = "saemix")
 plot(f_parent_saemix_dfop_tc$so, plot.type = "convergence")
 ```
-The four combinations and including the variations of the DFOP/tc combination
-can be compared using the model comparison function from the saemix package:
+
+We also check if using many more iterations (10 000 for the first and 1000 for
+the second phase) improve the result in a significant way. The AIC values
+obtained are compared further below.
+
+```{r f_parent_saemix_dfop_tc_10k, results = 'hide', dependson = "saemix_control"}
+f_parent_saemix_dfop_tc_10k <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+  control = saemix_control_10k, transformations = "saemix")
+plot(f_parent_saemix_dfop_tc_10k$so, plot.type = "convergence")
+```
+
+An alternative way to fit DFOP in combination with the two-component error model
+is to use the model formulation with transformed parameters as used per default
+in mkin.
+
+```{r f_parent_saemix_dfop_tc_mkin, results = 'hide', dependson = "saemix_control"}
+f_parent_saemix_dfop_tc_mkin <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+  control = saemix_control, transformations = "mkin")
+plot(f_parent_saemix_dfop_tc_mkin$so, plot.type = "convergence")
+```
+
+As the convergence plots do not clearly indicate that the algorithm has converged, we
+again use a much larger number of iterations, which leads to satisfactory
+convergence (see below).
+
+```{r f_parent_saemix_dfop_tc_mkin_10k, results = 'hide', dependson = "saemix_control"}
+f_parent_saemix_dfop_tc_mkin_10k <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+  control = saemix_control_10k, transformations = "mkin")
+plot(f_parent_saemix_dfop_tc_mkin_10k$so, plot.type = "convergence")
+```
+
+The four combinations (SFO/const, SFO/tc, DFOP/const and DFOP/tc), including
+the variations of the DFOP/tc combination can be compared using the model
+comparison function of the saemix package:
 
 ```{r AIC_parent_saemix, cache = FALSE}
-compare.saemix(
+AIC_parent_saemix <- saemix::compare.saemix(
   f_parent_saemix_sfo_const$so,
   f_parent_saemix_sfo_tc$so,
   f_parent_saemix_dfop_const$so,
-  f_parent_saemix_dfop_tc$so)
+  f_parent_saemix_dfop_tc$so,
+  f_parent_saemix_dfop_tc_10k$so,
+  f_parent_saemix_dfop_tc_mkin$so,
+  f_parent_saemix_dfop_tc_mkin_10k$so)
+rownames(AIC_parent_saemix) <- c(
+  "SFO const", "SFO tc", "DFOP const", "DFOP tc", "DFOP tc more iterations",
+  "DFOP tc mkintrans", "DFOP tc mkintrans more iterations")
+print(AIC_parent_saemix)
 ```
 
 As in the case of nlme fits, the DFOP model fitted with two-component error
-(number 4) gives the lowest AIC. Using more iterations and/or more chains
-does not have a large influence on the final AIC (not shown).
+(number 4) gives the lowest AIC. Using a much larger number of iterations
+does not improve the fit a lot. When the mkin transformations are used
+instead of the saemix transformations, this large number of iterations leads
+to a goodness of fit that is comparable to the result obtained with saemix
+transformations.
 
 In order to check the influence of the likelihood calculation algorithms
 implemented in saemix, the likelihood from Gaussian quadrature is added
@@ -294,7 +337,7 @@ are compared.
 
 ```{r AIC_parent_saemix_methods, cache = FALSE}
 f_parent_saemix_dfop_tc$so <-
-  llgq.saemix(f_parent_saemix_dfop_tc$so)
+  saemix::llgq.saemix(f_parent_saemix_dfop_tc$so)
 AIC_parent_saemix_methods <- c(
   is = AIC(f_parent_saemix_dfop_tc$so, method = "is"),
   gq = AIC(f_parent_saemix_dfop_tc$so, method = "gq"),
@@ -302,6 +345,7 @@ AIC_parent_saemix_methods <- c(
 )
 print(AIC_parent_saemix_methods)
 ```
+
 The AIC values based on importance sampling and Gaussian quadrature are very
 similar. Using linearisation is known to be less accurate, but still gives a
 similar value.
@@ -355,15 +399,19 @@ Secondly, we use the SAEM estimation routine and check the convergence plots. Th
 control parameters also used for the saemix fits are defined beforehand.
 
 ```{r nlmixr_saem_control}
-nlmixr_saem_control <- saemControl(logLik = TRUE,
+nlmixr_saem_control_800 <- saemControl(logLik = TRUE,
+  nBurn = 800, nEm = 300, nmc = 15)
+nlmixr_saem_control_1000 <- saemControl(logLik = TRUE,
   nBurn = 1000, nEm = 300, nmc = 15)
+nlmixr_saem_control_10k <- saemControl(logLik = TRUE,
+  nBurn = 10000, nEm = 1000, nmc = 15)
 ```
 
 The we fit SFO with constant variance
 
 ```{r f_parent_nlmixr_saem_sfo_const, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_sfo_const <- nlmixr(f_parent_mkin_const["SFO", ], est = "saem",
-  control = nlmixr_saem_control)
+  control = nlmixr_saem_control_800)
 traceplot(f_parent_nlmixr_saem_sfo_const$nm)
 ```
 
@@ -371,7 +419,7 @@ and SFO with two-component error.
 
 ```{r f_parent_nlmixr_saem_sfo_tc, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_sfo_tc <- nlmixr(f_parent_mkin_tc["SFO", ], est = "saem",
-  control = nlmixr_saem_control)
+  control = nlmixr_saem_control_800)
 traceplot(f_parent_nlmixr_saem_sfo_tc$nm)
 ```
 
@@ -381,7 +429,7 @@ observed earlier for this model combination.
 
 ```{r f_parent_nlmixr_saem_dfop_const, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_dfop_const <- nlmixr(f_parent_mkin_const["DFOP", ], est = "saem",
-  control = nlmixr_saem_control)
+  control = nlmixr_saem_control_800)
 traceplot(f_parent_nlmixr_saem_dfop_const$nm)
 ```
 
@@ -389,22 +437,54 @@ For DFOP with two-component error, a less erratic convergence is seen.
 
 ```{r f_parent_nlmixr_saem_dfop_tc, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_dfop_tc <- nlmixr(f_parent_mkin_tc["DFOP", ], est = "saem",
-  control = nlmixr_saem_control)
+  control = nlmixr_saem_control_800)
 traceplot(f_parent_nlmixr_saem_dfop_tc$nm)
 ```
 
-The AIC values are internally calculated using Gaussian quadrature. For an
-unknown reason, the AIC value obtained for the DFOP fit using constant error
-is given as Infinity.
+To check if an increase in the number of iterations improves the fit, we repeat
+the fit with 1000 iterations for the burn in phase and 300 iterations for the
+second phase.
+
+```{r f_parent_nlmixr_saem_dfop_tc_1k, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
+f_parent_nlmixr_saem_dfop_tc_1000 <- nlmixr(f_parent_mkin_tc["DFOP", ], est = "saem",
+  control = nlmixr_saem_control_1000)
+traceplot(f_parent_nlmixr_saem_dfop_tc_1000$nm)
+```
+
+Here the fit looks very similar, but we will see below that it shows a higher AIC
+than the fit with 800 iterations in the burn in phase. Next we choose
+10 000 iterations for the burn in phase and 1000 iterations for the second
+phase for comparison with saemix.
+
+```{r f_parent_nlmixr_saem_dfop_tc_10k, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
+f_parent_nlmixr_saem_dfop_tc_10k <- nlmixr(f_parent_mkin_tc["DFOP", ], est = "saem",
+  control = nlmixr_saem_control_10k)
+traceplot(f_parent_nlmixr_saem_dfop_tc_10k$nm)
+```
+
+In the above convergence plot, the time course of 'eta.DMTA_0' and
+'log_k2' indicate a false convergence.
+
+The AIC values are internally calculated using Gaussian quadrature.
 
 ```{r AIC_parent_nlmixr_saem, cache = FALSE}
 AIC(f_parent_nlmixr_saem_sfo_const$nm, f_parent_nlmixr_saem_sfo_tc$nm,
-  f_parent_nlmixr_saem_dfop_const$nm, f_parent_nlmixr_saem_dfop_tc$nm)
+  f_parent_nlmixr_saem_dfop_const$nm, f_parent_nlmixr_saem_dfop_tc$nm,
+  f_parent_nlmixr_saem_dfop_tc_1000$nm,
+  f_parent_nlmixr_saem_dfop_tc_10k$nm)
 ```
 
+We can see that again, the DFOP/tc model shows the best goodness of fit.
+However, increasing the number of burn-in iterations from 800 to 1000 results
+in a higher AIC. If we further increase the number of iterations to 10 000
+(burn-in) and 1000 (second phase), the AIC cannot be calculated for the
+nlmixr/saem fit, supporting that the fit did not converge properly.
+
 ### Comparison
 
-The following table gives the AIC values obtained with the three packages.
+The following table gives the AIC values obtained with the three packages using
+the same control parameters (800 iterations burn-in, 300 iterations second
+phase, 15 chains).
 
 ```{r AIC_all, cache = FALSE}
 AIC_all <- data.frame(
@@ -422,6 +502,15 @@ AIC_all <- data.frame(
 kable(AIC_all)
 ```
 
+```{r parms_all, cache = FALSE}
+intervals(f_parent_saemix_dfop_tc)
+intervals(f_parent_saemix_dfop_tc)
+intervals(f_parent_saemix_dfop_tc_10k)
+intervals(f_parent_saemix_dfop_tc_mkin_10k)
+intervals(f_parent_nlmixr_saem_dfop_tc)
+intervals(f_parent_nlmixr_saem_dfop_tc_10k)
+```
+
 
 
 # References
-- 
cgit v1.2.1


From e7751e791f46b2aa334f52109e0bd8211dfd7083 Mon Sep 17 00:00:00 2001
From: Johannes Ranke <jranke@uni-bremen.de>
Date: Tue, 11 Jan 2022 19:28:22 +0100
Subject: Update the dimethenamid vignette with current saemix

Convergence is faster with this version (@ecomets mentioned that there
was a bugfix lately that could lead to faster convergence). However,
if I use too many iterations (i.e. 10 000 as in the last version of
this vignette), I get an error in solving omega.teta during later
iterations, apparently due to overparameterisation of the DFOP model
in this case.
---
 vignettes/web_only/dimethenamid_2018.rmd | 56 +++++++++++++++++---------------
 1 file changed, 29 insertions(+), 27 deletions(-)

(limited to 'vignettes/web_only/dimethenamid_2018.rmd')

diff --git a/vignettes/web_only/dimethenamid_2018.rmd b/vignettes/web_only/dimethenamid_2018.rmd
index ae93984d..08661b5a 100644
--- a/vignettes/web_only/dimethenamid_2018.rmd
+++ b/vignettes/web_only/dimethenamid_2018.rmd
@@ -1,7 +1,7 @@
 ---
 title: Example evaluations of the dimethenamid data from 2018
 author: Johannes Ranke
-date: Last change 27 September 2021, built on `r format(Sys.Date(), format = "%d %b %Y")`
+date: Last change 11 January 2022, built on `r format(Sys.Date(), format = "%d %b %Y")`
 output:
   html_document:
     toc: true
@@ -230,11 +230,11 @@ fit. As we will compare the SAEM implementation of saemix to the results
 obtained using the nlmixr package later, we define control settings that
 work well for all the parent data fits shown in this vignette.
 
-```{r saemix_control}
+```{r saemix_control, results='hide'}
 library(saemix)
 saemix_control <- saemixControl(nbiter.saemix = c(800, 300), nb.chains = 15,
     print = FALSE, save = FALSE, save.graphs = FALSE, displayProgress = FALSE)
-saemix_control_10k <- saemixControl(nbiter.saemix = c(10000, 1000), nb.chains = 15,
+saemix_control_moreiter <- saemixControl(nbiter.saemix = c(1600, 300), nb.chains = 15,
     print = FALSE, save = FALSE, save.graphs = FALSE, displayProgress = FALSE)
 ```
 
@@ -274,14 +274,15 @@ f_parent_saemix_dfop_tc <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
 plot(f_parent_saemix_dfop_tc$so, plot.type = "convergence")
 ```
 
-We also check if using many more iterations (10 000 for the first and 1000 for
-the second phase) improve the result in a significant way. The AIC values
-obtained are compared further below.
-
-```{r f_parent_saemix_dfop_tc_10k, results = 'hide', dependson = "saemix_control"}
-f_parent_saemix_dfop_tc_10k <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
-  control = saemix_control_10k, transformations = "saemix")
-plot(f_parent_saemix_dfop_tc_10k$so, plot.type = "convergence")
+```{r f_parent_saemix_dfop_tc_moreiter, results = 'hide', dependson = "saemix_control"}
+# The last time I tried (2022-01-11) this gives an error in solve.default(omega.eta)
+# system is computationally singular: reciprocal condition number = 5e-17
+#f_parent_saemix_dfop_tc_10k <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+#  control = saemix_control_10k, transformations = "saemix")
+# Now we do not get a significant improvement by using twice the number of iterations
+f_parent_saemix_dfop_tc_moreiter <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+  control = saemix_control_moreiter, transformations = "saemix")
+#plot(f_parent_saemix_dfop_tc_moreiter$so, plot.type = "convergence")
 ```
 
 An alternative way to fit DFOP in combination with the two-component error model
@@ -293,15 +294,16 @@ f_parent_saemix_dfop_tc_mkin <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = T
   control = saemix_control, transformations = "mkin")
 plot(f_parent_saemix_dfop_tc_mkin$so, plot.type = "convergence")
 ```
-
 As the convergence plots do not clearly indicate that the algorithm has converged, we
-again use a much larger number of iterations, which leads to satisfactory
+again use four times the number of iterations, which leads to almost satisfactory
 convergence (see below).
 
-```{r f_parent_saemix_dfop_tc_mkin_10k, results = 'hide', dependson = "saemix_control"}
-f_parent_saemix_dfop_tc_mkin_10k <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
-  control = saemix_control_10k, transformations = "mkin")
-plot(f_parent_saemix_dfop_tc_mkin_10k$so, plot.type = "convergence")
+```{r f_parent_saemix_dfop_tc_mkin_moreiter, results = 'hide', dependson = "saemix_control"}
+saemix_control_muchmoreiter <- saemixControl(nbiter.saemix = c(3200, 300), nb.chains = 15,
+    print = FALSE, save = FALSE, save.graphs = FALSE, displayProgress = FALSE)
+f_parent_saemix_dfop_tc_mkin_muchmoreiter <- mkin::saem(f_parent_mkin_tc["DFOP", ], quiet = TRUE,
+  control = saemix_control_muchmoreiter, transformations = "mkin")
+plot(f_parent_saemix_dfop_tc_mkin_muchmoreiter$so, plot.type = "convergence")
 ```
 
 The four combinations (SFO/const, SFO/tc, DFOP/const and DFOP/tc), including
@@ -314,9 +316,9 @@ AIC_parent_saemix <- saemix::compare.saemix(
   f_parent_saemix_sfo_tc$so,
   f_parent_saemix_dfop_const$so,
   f_parent_saemix_dfop_tc$so,
-  f_parent_saemix_dfop_tc_10k$so,
+  f_parent_saemix_dfop_tc_moreiter$so,
   f_parent_saemix_dfop_tc_mkin$so,
-  f_parent_saemix_dfop_tc_mkin_10k$so)
+  f_parent_saemix_dfop_tc_mkin_muchmoreiter$so)
 rownames(AIC_parent_saemix) <- c(
   "SFO const", "SFO tc", "DFOP const", "DFOP tc", "DFOP tc more iterations",
   "DFOP tc mkintrans", "DFOP tc mkintrans more iterations")
@@ -325,10 +327,10 @@ print(AIC_parent_saemix)
 
 As in the case of nlme fits, the DFOP model fitted with two-component error
 (number 4) gives the lowest AIC. Using a much larger number of iterations
-does not improve the fit a lot. When the mkin transformations are used
-instead of the saemix transformations, this large number of iterations leads
-to a goodness of fit that is comparable to the result obtained with saemix
-transformations.
+does not significantly change the AIC. When the mkin transformations are used
+instead of the saemix transformations, we need four times the number of
+iterations to obtain a goodness of fit that almost as good as the result
+obtained with saemix transformations.
 
 In order to check the influence of the likelihood calculation algorithms
 implemented in saemix, the likelihood from Gaussian quadrature is added
@@ -393,6 +395,7 @@ aic_nlme_nlmixr_focei <- data.frame(
   "AIC (nlmixr with FOCEI)" = aic_nlmixr_focei,
   check.names = FALSE
 )
+print(aic_nlme_nlmixr_focei)
 ```
 
 Secondly, we use the SAEM estimation routine and check the convergence plots. The
@@ -407,7 +410,7 @@ nlmixr_saem_control_10k <- saemControl(logLik = TRUE,
   nBurn = 10000, nEm = 1000, nmc = 15)
 ```
 
-The we fit SFO with constant variance
+Then we fit SFO with constant variance
 
 ```{r f_parent_nlmixr_saem_sfo_const, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_sfo_const <- nlmixr(f_parent_mkin_const["SFO", ], est = "saem",
@@ -425,7 +428,7 @@ traceplot(f_parent_nlmixr_saem_sfo_tc$nm)
 
 For DFOP with constant variance, the convergence plots show considerable
 instability of the fit, which indicates overparameterisation which was already
-observed earlier for this model combination.
+observed above for this model combination.
 
 ```{r f_parent_nlmixr_saem_dfop_const, results = "hide", warning = FALSE, message = FALSE, dependson = "nlmixr_saem_control"}
 f_parent_nlmixr_saem_dfop_const <- nlmixr(f_parent_mkin_const["DFOP", ], est = "saem",
@@ -505,8 +508,7 @@ kable(AIC_all)
 ```{r parms_all, cache = FALSE}
 intervals(f_parent_saemix_dfop_tc)
 intervals(f_parent_saemix_dfop_tc)
-intervals(f_parent_saemix_dfop_tc_10k)
-intervals(f_parent_saemix_dfop_tc_mkin_10k)
+intervals(f_parent_saemix_dfop_tc_mkin_muchmoreiter)
 intervals(f_parent_nlmixr_saem_dfop_tc)
 intervals(f_parent_nlmixr_saem_dfop_tc_10k)
 ```
-- 
cgit v1.2.1