From 42171ba55222383a0d47e5aacd46a972819e7812 Mon Sep 17 00:00:00 2001 From: Johannes Ranke Date: Wed, 15 Apr 2020 18:13:04 +0200 Subject: Include random effects in starting parameters - mean_degparms() now optionally returns starting values for fixed and random effects, which makes it possible to obtain acceptable fits also in more difficult cases (with more parameters) - Fix the anova method, as it is currently not enough to inherit from lme: https://bugs.r-project.org/bugzilla/show_bug.cgi?id=17761 - Show fit information, and per default also errmin information in plot.nlme.mmkin() - Examples for nlme.mmkin: Decrease tolerance and increase the number of iterations in the PNLS step in order to be able to fit FOMC-SFO and DFOP-SFO --- docs/reference/nlme.html | 80 ++++++++++-------------------------------------- 1 file changed, 16 insertions(+), 64 deletions(-) (limited to 'docs/reference/nlme.html') diff --git a/docs/reference/nlme.html b/docs/reference/nlme.html index 981845fe..70c6b63c 100644 --- a/docs/reference/nlme.html +++ b/docs/reference/nlme.html @@ -144,7 +144,7 @@ datasets.

nlme_function(object)
 
-mean_degparms(object)
+mean_degparms(object, random = FALSE)
 
 nlme_data(object)
@@ -155,13 +155,23 @@ datasets.

object

An mmkin row object containing several fits of the same model to different datasets

+ + random +

Should a list with fixed and random effects be returned?

+

Value

A function that can be used with nlme

-

A named vector containing mean values of the fitted degradation model parameters

+

If random is FALSE (default), a named vector containing mean values + of the fitted degradation model parameters. If random is TRUE, a list with + fixed and random effects, in the format required by the start argument of + nlme for the case of a single grouping variable ds?

A groupedData object

+

See also

+ +

nlme.mmkin

Examples

sampling_times = c(0, 1, 3, 7, 14, 28, 60, 90, 120)
@@ -226,68 +236,9 @@ datasets.

 #> -2.6169360 -0.2185329  0.0574070  0.5720937  3.0459868 
 #> 
 #> Number of Observations: 49
-#> Number of Groups: 3 
plot(augPred(m_nlme, level = 0:1), layout = c(3, 1))

-# \dontrun{
-  # Test on some real data
-  ds_2 <- lapply(experimental_data_for_UBA_2019[6:10],
-   function(x) x$data[c("name", "time", "value")])
-  m_sfo_sfo <- mkinmod(parent = mkinsub("SFO", "A1"),
-    A1 = mkinsub("SFO"), use_of_ff = "min")
#> Successfully compiled differential equation model from auto-generated C code.
  m_sfo_sfo_ff <- mkinmod(parent = mkinsub("SFO", "A1"),
-    A1 = mkinsub("SFO"), use_of_ff = "max")
#> Successfully compiled differential equation model from auto-generated C code.
  m_fomc_sfo <- mkinmod(parent = mkinsub("FOMC", "A1"),
-    A1 = mkinsub("SFO"))
#> Successfully compiled differential equation model from auto-generated C code.
  m_dfop_sfo <- mkinmod(parent = mkinsub("DFOP", "A1"),
-    A1 = mkinsub("SFO"))
#> Successfully compiled differential equation model from auto-generated C code.
  m_sforb_sfo <- mkinmod(parent = mkinsub("SFORB", "A1"),
-    A1 = mkinsub("SFO"))
#> Successfully compiled differential equation model from auto-generated C code.

-  f_2 <- mmkin(list("SFO-SFO" = m_sfo_sfo,
-   "SFO-SFO-ff" = m_sfo_sfo_ff,
-   "FOMC-SFO" = m_fomc_sfo,
-   "DFOP-SFO" = m_dfop_sfo,
-   "SFORB-SFO" = m_sforb_sfo),
-    ds_2)
-
-  grouped_data_2 <- nlme_data(f_2["SFO-SFO", ])
-
-  mean_dp_sfo_sfo <- mean_degparms(f_2["SFO-SFO", ])
-  mean_dp_sfo_sfo_ff <- mean_degparms(f_2["SFO-SFO-ff", ])
-  mean_dp_fomc_sfo <- mean_degparms(f_2["FOMC-SFO", ])
-  mean_dp_dfop_sfo <- mean_degparms(f_2["DFOP-SFO", ])
-  mean_dp_sforb_sfo <- mean_degparms(f_2["SFORB-SFO", ])
-
-  nlme_f_sfo_sfo <- nlme_function(f_2["SFO-SFO", ])
-  nlme_f_sfo_sfo_ff <- nlme_function(f_2["SFO-SFO-ff", ])
-  nlme_f_fomc_sfo <- nlme_function(f_2["FOMC-SFO", ])
-  assign("nlme_f_sfo_sfo", nlme_f_sfo_sfo, globalenv())
-  assign("nlme_f_sfo_sfo_ff", nlme_f_sfo_sfo_ff, globalenv())
-  assign("nlme_f_fomc_sfo", nlme_f_fomc_sfo, globalenv())
-
-  # Allowing for correlations between random effects (not shown)
-  # leads to non-convergence
-  f_nlme_sfo_sfo <- nlme(value ~ nlme_f_sfo_sfo(name, time,
-       parent_0, log_k_parent_sink, log_k_parent_A1, log_k_A1_sink),
-     data = grouped_data_2,
-     fixed = parent_0 + log_k_parent_sink + log_k_parent_A1 + log_k_A1_sink ~ 1,
-     random = pdDiag(parent_0 + log_k_parent_sink + log_k_parent_A1 + log_k_A1_sink ~ 1),
-     start = mean_dp_sfo_sfo)
-   # augPred does not see to work on this object, so no plot is shown
-
-  # The same model fitted with transformed formation fractions does not converge
-  f_nlme_sfo_sfo_ff <- nlme(value ~ nlme_f_sfo_sfo_ff(name, time,
-       parent_0, log_k_parent, log_k_A1, f_parent_ilr_1),
-     data = grouped_data_2,
-     fixed = parent_0 + log_k_parent + log_k_A1 + f_parent_ilr_1 ~ 1,
-     random = pdDiag(parent_0 + log_k_parent + log_k_A1 + f_parent_ilr_1 ~ 1),
-     start = mean_dp_sfo_sfo_ff)
#> Error in nlme.formula(value ~ nlme_f_sfo_sfo_ff(name, time, parent_0,     log_k_parent, log_k_A1, f_parent_ilr_1), data = grouped_data_2,     fixed = parent_0 + log_k_parent + log_k_A1 + f_parent_ilr_1 ~         1, random = pdDiag(parent_0 + log_k_parent + log_k_A1 +         f_parent_ilr_1 ~ 1), start = mean_dp_sfo_sfo_ff): step halving factor reduced below minimum in PNLS step

-  f_nlme_fomc_sfo <- nlme(value ~ nlme_f_fomc_sfo(name, time,
-       parent_0, log_alpha, log_beta, log_k_A1, f_parent_ilr_1),
-     data = grouped_data_2,
-     fixed = parent_0 + log_alpha + log_beta + log_k_A1 + f_parent_ilr_1 ~ 1,
-     random = pdDiag(parent_0 + log_alpha + log_beta + log_k_A1 + f_parent_ilr_1 ~ 1),
-     start = mean_dp_fomc_sfo)
-
-  # DFOP-SFO and SFORB-SFO did not converge with full random effects
-
-  anova(f_nlme_fomc_sfo, f_nlme_sfo_sfo)
#>                 Model df       AIC       BIC    logLik   Test  L.Ratio p-value
-#> f_nlme_fomc_sfo     1 11  932.5817  967.0755 -455.2909                        
-#> f_nlme_sfo_sfo      2  9 1089.2492 1117.4714 -535.6246 1 vs 2 160.6675  <.0001
# }
+#> Number of Groups: 3 
plot(augPred(m_nlme, level = 0:1), layout = c(3, 1))
# augPred does not seem to work on fits with more than one state
+# variable
+