summary_simulate: Summarize a matrix of simulations by their mean (median), sd...

In nlraa: Nonlinear Regression for Agricultural Applications

Summarize a matrix of simulations by their mean (median), sd (mad), and quantiles

Description

Utility function to summarize the output from ‘simulate’ functions in this package

Usage

summary_simulate(
  object,
  probs = c(0.025, 0.975),
  robust = FALSE,
  data,
  by,
  ...
)

Arguments

object	nobs x nsim matrix where nobs are the number of observations in the dataset and nsim are the number of simulations
probs	the percentiles to be computed by the quantile function
robust	If FALSE (the default) the mean is used as the measure of central tendency and the standard deviation as the measure of variability. If TRUE, the median and the median absolute deviation (MAD) are applied instead.
data	the original data.frame used to fit the model. A data.frame will be returned instead of a matrix in this case.
by	opionally aggregate the results by some factor in the data.frame. It will be coarced to a formula. This should either be a character or a formula (starting with ‘~’). The aggregation follows the ‘robust’ argument above.
...	additional arguments to be passed. (none used at the moment)

Value

By default it returns a matrix unless the ‘data’ argument is present and then it will return a data.frame

Examples

data(barley, package = "nlraa")
fit <- nls(yield ~ SSlinp(NF, a, b, xs), data = barley)
sim <- simulate_nls(fit, nsim = 100)
sims <- summary_simulate(sim)

## If we want to combine the data.frame
simd <- summary_simulate(sim, data = barley)
## If we also want to aggregate by nitrogen rate
simda <- summary_simulate(sim, data = barley, by = "NF")
## The robust option uses the median instead
simdar <- summary_simulate(sim, data = barley, by = "NF",
                           robust = TRUE)

nlraa documentation built on July 9, 2023, 6:08 p.m.