A wrapper function allowing for multiple methods of piecewise regression to
be applied using a standard format for inputs. See vignette("broken-stick")
and vignette("two-line") for more information.
Usage
piecewise_mods(
dat,
xvar,
yvar,
lower = NULL,
upper = NULL,
log = FALSE,
method = c("segmented", "chngpt", "regrans", "stevens", "TL", "all")
)Arguments
- dat
data frame or matrix containing the data
- xvar
Name of column (integer or double) of measurements for the x-axis variable (e.g., carapace width).
- yvar
Name of column (integer or double) of measurements for the y-axis variable (e.g., claw height).
- lower
Integer or double; the lower bound for possible SM50 values. Must be on the same trans of the data. Defaults to the 20th percentile of the x-variable.
- upper
Integer or double; the upper bound for possible SM50 values. Must be on the same trans of the data. Defaults to the 80th percentile of the x-variable.
- log
Boolean; should both variables be log-transformed before performing the regression? Defaults to FALSE.
- method
Method to use for the regression. A single string or vector containing one or more of c("segmented", "chngpt", "regrans", "stevens", "TL"), or "all" to return the results of all methods for comparison.
Details
The two_line_logistic() function is closely related but not included in this wrapper function because you will generally want more control over the initial values of the parameters and the nonlinear least-squares algorithm may not always converge.
This function is primarily intended for easy comparison between the SM50 estimates produced by a variety of different piecewise regression models. For follow-up analyses, we recommend calling the specific function(s) of interest (regrans(), broken_stick_stevens(), two_line(), segmented::segmented(), or chngpt::chngpt()) and exploring how changing the upper and lower bounds for possible SM50 values and the number of breakpoints to be tested may influence the resulting estimates.
Examples
set.seed(12)
fc <- fake_crustaceans(n = 100, L50 = 100, allo_params = c(1, 0.2, 1.1, 0.2))
piecewise_mods(fc, xvar = "x", yvar = "y", method = c("segmented", "chngpt"))
#> chngpt segmented
#> 89.44561 88.71463