Plot a fitted nonlinear mixed model obtained via an mmkin row object

# S3 method for nlme.mmkin
plot(
  x,
  i = 1:ncol(x$mmkin_orig),
  obs_vars = names(x$mkinmod$map),
  standardized = TRUE,
  xlab = "Time",
  xlim = range(x$data$time),
  resplot = c("predicted", "time"),
  ymax = "auto",
  maxabs = "auto",
  ncol.legend = ifelse(length(i) <= 3, length(i) + 1, ifelse(length(i) <= 8, 3, 4)),
  nrow.legend = ceiling((length(i) + 1)/ncol.legend),
  rel.height.legend = 0.03 + 0.08 * nrow.legend,
  rel.height.bottom = 1.1,
  pch_ds = 1:length(i),
  col_ds = pch_ds + 1,
  lty_ds = col_ds,
  frame = TRUE,
  ...
)

Arguments

x	An object of class `nlme.mmkin`
i	A numeric index to select datasets for which to plot the nlme fit, in case plots get too large
obs_vars	A character vector of names of the observed variables for which the data and the model should be plotted. Defauls to all observed variables in the model.
standardized	Should the residuals be standardized? Only takes effect if `resplot = "time"`.
xlab	Label for the x axis.
xlim	Plot range in x direction.
resplot	Should the residuals plotted against time or against predicted values?
ymax	Vector of maximum y axis values
maxabs	Maximum absolute value of the residuals. This is used for the scaling of the y axis and defaults to "auto".
rel.height.legend	The relative height of the legend shown on top
rel.height.bottom	The relative height of the bottom plot row
pch_ds	Symbols to be used for plotting the data.
col_ds	Colors used for plotting the observed data and the corresponding model prediction lines for the different datasets.
lty_ds	Line types to be used for the model predictions.
frame	Should a frame be drawn around the plots?
...	Further arguments passed to `plot.mkinfit` and `mkinresplot`.

Value

The function is called for its side effect.

Author

Johannes Ranke

Examples

ds <- lapply(experimental_data_for_UBA_2019[6:10],
 function(x) x$data[c("name", "time", "value")])
names(ds) <- paste0("ds ", 6:10)
dfop_sfo <- mkinmod(parent = mkinsub("DFOP", "A1"),
  A1 = mkinsub("SFO"), quiet = TRUE)
f <- mmkin(list("DFOP-SFO" = dfop_sfo), ds, quiet = TRUE, cores = 1)
plot(f[, 3:4], standardized = TRUE)

library(nlme)
# For this fit we need to increase pnlsMaxiter, and we increase the
# tolerance in order to speed up the fit for this example evaluation
f_nlme <- nlme(f, control = list(pnlsMaxIter = 120, tolerance = 1e-3))
plot(f_nlme)