From 78d34a8918edcb91982a3886e4898a63898f52c3 Mon Sep 17 00:00:00 2001 From: Johannes Ranke Date: Thu, 20 Apr 2023 21:40:08 +0200 Subject: Update vignettes in dev docs After the post-release fixes to the release version online docs --- docs/dev/articles/web_only/multistart.html | 52 +++++++++++++++++++----------- 1 file changed, 34 insertions(+), 18 deletions(-) (limited to 'docs/dev/articles/web_only/multistart.html') diff --git a/docs/dev/articles/web_only/multistart.html b/docs/dev/articles/web_only/multistart.html index b5635df2..2de5059c 100644 --- a/docs/dev/articles/web_only/multistart.html +++ b/docs/dev/articles/web_only/multistart.html @@ -34,7 +34,7 @@ mkin - 1.2.3 + 1.2.4 @@ -127,13 +127,15 @@ -
+

Short demo of the multistart method

-

Johannes Ranke

+

Johannes +Ranke

-

Last change 17 April 2023 (rebuilt 2023-04-17)

+

Last change 20 April 2023 +(rebuilt 2023-04-20)

Source: vignettes/web_only/multistart.rmd @@ -142,7 +144,8 @@ -

The dimethenamid data from 2018 from seven soils is used as example data in this vignette.

+

The dimethenamid data from 2018 from seven soils is used as example +data in this vignette.

 library(mkin)
 dmta_ds <- lapply(1:7, function(i) {
@@ -154,26 +157,34 @@
 names(dmta_ds) <- sapply(dimethenamid_2018$ds, function(ds) ds$title)
 dmta_ds[["Elliot"]] <- rbind(dmta_ds[["Elliot 1"]], dmta_ds[["Elliot 2"]])
 dmta_ds[["Elliot 1"]] <- dmta_ds[["Elliot 2"]] <- NULL
-

First, we check the DFOP model with the two-component error model and random effects for all degradation parameters.

+

First, we check the DFOP model with the two-component error model and +random effects for all degradation parameters.

 f_mmkin <- mmkin("DFOP", dmta_ds, error_model = "tc", cores = 7, quiet = TRUE)
 f_saem_full <- saem(f_mmkin)
 illparms(f_saem_full)
## [1] "sd(log_k2)"
-

We see that not all variability parameters are identifiable. The illparms function tells us that the confidence interval for the standard deviation of ‘log_k2’ includes zero. We check this assessment using multiple runs with different starting values.

+

We see that not all variability parameters are identifiable. The +illparms function tells us that the confidence interval for +the standard deviation of ‘log_k2’ includes zero. We check this +assessment using multiple runs with different starting values.

-f_saem_full_multi <- multistart(f_saem_full, n = 16, cores = 8)
+f_saem_full_multi <- multistart(f_saem_full, n = 16, cores = 16)
 parplot(f_saem_full_multi, lpos = "topleft")

-

This confirms that the variance of k2 is the most problematic parameter, so we reduce the parameter distribution model by removing the intersoil variability for k2.

+

This confirms that the variance of k2 is the most problematic +parameter, so we reduce the parameter distribution model by removing the +intersoil variability for k2.

-f_saem_reduced <- update(f_saem_full, no_random_effect = "log_k2")
+f_saem_reduced <- stats::update(f_saem_full, no_random_effect = "log_k2")
 illparms(f_saem_reduced)
-f_saem_reduced_multi <- multistart(f_saem_reduced, n = 16, cores = 8)
+f_saem_reduced_multi <- multistart(f_saem_reduced, n = 16, cores = 16)
 parplot(f_saem_reduced_multi, lpos = "topright", ylim = c(0.5, 2))

-

The results confirm that all remaining parameters can be determined with sufficient certainty.

-

We can also analyse the log-likelihoods obtained in the multiple runs:

+

The results confirm that all remaining parameters can be determined +with sufficient certainty.

+

We can also analyse the log-likelihoods obtained in the multiple +runs:

 llhist(f_saem_reduced_multi)

@@ -184,11 +195,16 @@ 
## Data: 155 observations of 1 variable(s) grouped in 6 datasets
 ## 
 ##                            npar    AIC    BIC     Lik  Chisq Df Pr(>Chisq)
-## f_saem_reduced                9 663.74 661.87 -322.87                     
-## best(f_saem_reduced_multi)    9 663.60 661.72 -322.80 0.1476  0           
-## f_saem_full                  10 670.35 668.26 -325.17 0.0000  1          1
-## best(f_saem_full_multi)      10 665.61 663.53 -322.80 4.7372  0
-

The reduced model results in lower AIC and BIC values, so it is clearly preferable. Using multiple starting values gives a large improvement in case of the full model, because it is less well-defined, which impedes convergence. For the reduced model, using multiple starting values only results in a small improvement of the model fit.

+## f_saem_reduced 9 663.73 661.86 -322.86 +## best(f_saem_reduced_multi) 9 663.69 661.82 -322.85 0.0361 0 +## f_saem_full 10 669.77 667.69 -324.89 0.0000 1 1 +## best(f_saem_full_multi) 10 665.56 663.48 -322.78 4.2060 0 +

The reduced model results in lower AIC and BIC values, so it is +clearly preferable. Using multiple starting values gives a large +improvement in case of the full model, because it is less well-defined, +which impedes convergence. For the reduced model, using multiple +starting values only results in a small improvement of the model +fit.