diff options
Diffstat (limited to 'man/parplot.Rd')
| -rw-r--r-- | man/parplot.Rd | 12 |
1 files changed, 11 insertions, 1 deletions
diff --git a/man/parplot.Rd b/man/parplot.Rd index 37c5841d..67bf0cc1 100644 --- a/man/parplot.Rd +++ b/man/parplot.Rd @@ -10,6 +10,7 @@ parplot(object, ...) \method{parplot}{multistart.saem.mmkin}( object, llmin = -Inf, + llquant = NA, scale = c("best", "median"), lpos = "bottomleft", main = "", @@ -23,7 +24,11 @@ parplot(object, ...) \item{llmin}{The minimum likelihood of objects to be shown} -\item{scale}{By default, scale parameters using the best available fit. +\item{llquant}{Fractional value for selecting only the fits with higher +likelihoods. Overrides 'llmin'.} + +\item{scale}{By default, scale parameters using the best +available fit. If 'median', parameters are scaled using the median parameters from all fits.} \item{lpos}{Positioning of the legend.} @@ -35,6 +40,11 @@ Produces a boxplot with all parameters from the multiple runs, scaled either by the parameters of the run with the highest likelihood, or by their medians as proposed in the paper by Duchesne et al. (2021). } +\details{ +Starting values of degradation model parameters and error model parameters +are shown as green circles. The results obtained in the original run +are shown as red circles. +} \references{ Duchesne R, Guillemin A, Gandrillon O, Crauste F. Practical identifiability in the frame of nonlinear mixed effects models: the example |