Basic multistart method for saem.mmkin objects

3 files changed, 55 insertions, 9 deletions

diff --git a/man/mkinfit.Rd b/man/mkinfit.Rd
index f96b4d22..b5b24449 100644
--- a/man/mkinfit.Rd
+++ b/man/mkinfit.Rd
@@ -23,8 +23,8 @@ mkinfit(
   atol = 1e-08,
   rtol = 1e-10,
   error_model = c("const", "obs", "tc"),
-  error_model_algorithm = c("auto", "d_3", "direct", "twostep", "threestep", "fourstep",
-    "IRLS", "OLS"),
+  error_model_algorithm = c("auto", "d_3", "direct", "twostep", "threestep",
+    "fourstep", "IRLS", "OLS"),
   reweight.tol = 1e-08,
   reweight.max.iter = 10,
   trace_parms = FALSE,
diff --git a/man/multistart.Rd b/man/multistart.Rd
new file mode 100644
index 00000000..ff60b01d
--- /dev/null
+++ b/man/multistart.Rd
@@ -0,0 +1,43 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/multistart.R
+\name{multistart}
+\alias{multistart}
+\alias{multistart.saem.mmkin}
+\title{Perform a hierarchical model fit with multiple starting values}
+\usage{
+multistart(object, n = 50, cores = 1, ...)
+
+\method{multistart}{saem.mmkin}(object, n = 50, cores = 1, ...)
+}
+\arguments{
+\item{object}{The fit object to work with}
+
+\item{n}{How many different combinations of starting parameters should be
+used?}
+
+\item{cores}{How many fits should be run in parallel?}
+
+\item{\dots}{Passed to the update function.}
+}
+\value{
+A list of \link{saem.mmkin} objects, with class attributes
+'multistart.saem.mmkin' and 'multistart'.
+}
+\description{
+The purpose of this method is to check if a certain algorithm for fitting
+nonlinear hierarchical models (also known as nonlinear mixed-effects models)
+will reliably yield results that are sufficiently similar to each other, if
+started with a certain range of reasonable starting parameters. It is
+inspired by the article on practical identifiabiliy in the frame of nonlinear
+mixed-effects models by Duchesne et al (2021).
+}
+\details{
+Currently, parallel execution of the fits is only supported using
+\link[parallel:mclapply]{parallel::mclapply}, i.e. not available on Windows.
+}
+\references{
+Duchesne R, Guillemin A, Gandrillon O, Crauste F. Practical
+identifiability in the frame of nonlinear mixed effects models: the example
+of the in vitro erythropoiesis. BMC Bioinformatics. 2021 Oct 4;22(1):478.
+doi: 10.1186/s12859-021-04373-4.
+}
diff --git a/man/parms.Rd b/man/parms.Rd
index af92bd2a..293bdaab 100644
--- a/man/parms.Rd
+++ b/man/parms.Rd
@@ -8,9 +8,9 @@
 \usage{
 parms(object, ...)
 
-\method{parms}{mkinfit}(object, transformed = FALSE, ...)
+\method{parms}{mkinfit}(object, transformed = FALSE, errparms = TRUE, ...)
 
-\method{parms}{mmkin}(object, transformed = FALSE, ...)
+\method{parms}{mmkin}(object, transformed = FALSE, errparms = TRUE, ...)
 }
 \arguments{
 \item{object}{A fitted model object. Methods are implemented for
@@ -18,14 +18,17 @@ parms(object, ...)
 
 \item{\dots}{Not used}
 
-\item{transformed}{Should the parameters be returned
-as used internally during the optimisation?}
+\item{transformed}{Should the parameters be returned as used internally
+during the optimisation?}
+
+\item{errparms}{Should the error model parameters be returned
+in addition to the degradation parameters?}
 }
 \value{
 For mkinfit objects, a numeric vector of fitted model parameters.
-For mmkin row objects, a matrix with the parameters with a
-row for each dataset. If the mmkin object has more than one row, a list of
-such matrices is returned.
+For mmkin row objects, a matrix with the parameters with a row for each
+dataset. If the mmkin object has more than one row, a list of such matrices
+is returned.
 }
 \description{
 This function always returns degradation model parameters as well as error