From 630e657f1794ea441afc9ff10663309fec5e847e Mon Sep 17 00:00:00 2001 From: Johannes Ranke Date: Tue, 1 Nov 2022 14:16:21 +0100 Subject: Update online docs --- docs/dev/articles/web_only/multistart.html | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 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 0c08905a..50a57d1b 100644 --- a/docs/dev/articles/web_only/multistart.html +++ b/docs/dev/articles/web_only/multistart.html @@ -34,7 +34,7 @@ mkin - 1.1.2 + 1.2.0 @@ -109,7 +109,7 @@

Short demo of the multistart method

Johannes Ranke

-

Last change 26 September 2022 (rebuilt 2022-10-28)

+

Last change 26 September 2022 (rebuilt 2022-11-01)

Source: vignettes/web_only/multistart.rmd @@ -144,23 +144,21 @@

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")
-illparms(f_saem_reduced)
-
## character(0)
-
-f_saem_reduced_multi <- multistart(f_saem_reduced, n = 16, cores = 16)
+illparms(f_saem_reduced)
+f_saem_reduced_multi <- multistart(f_saem_reduced, n = 16, cores = 16)
 parplot(f_saem_reduced_multi, lpos = "topright")

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)

 

 
The parameter histograms can be further improved by excluding the result with the low likelihood.

-
+
 parplot(f_saem_reduced_multi, lpos = "topright", llmin = -326, ylim = c(0.5, 2))

 

 
We can use the anova method to compare the models, including a likelihood ratio test if the models are nested.

-
+
 anova(f_saem_full, best(f_saem_reduced_multi), test = TRUE)

 
## Data: 155 observations of 1 variable(s) grouped in 6 datasets
 ## 
-- 
cgit v1.2.1