Fits a nonlinear model made up of two distinct line segments connected by a logistic curve.
Usage
two_line_logistic(
dat,
xvar,
yvar,
imm_int = 1,
imm_slope = 0.2,
mat_int = 4,
mat_slope = 0.3,
SM50_start = NULL,
alpha_start = 9,
log = FALSE,
verbose = FALSE
)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).
- imm_int
Starting value for the immature intercept parameter when fitting the NLS model
- imm_slope
tarting value for the immature slope parameter when fitting the NLS model
- mat_int
Starting value for the mature intercept parameter when fitting the NLS model
- mat_slope
Starting value for the mature slope parameter when fitting the NLS model
- SM50_start
Starting value for SM50 parameter when fitting the NLS model. If not provided, taken to be the median of the x-variable
- alpha_start
Starting value for the logistic slope parameter when fitting the NLS model
- log
Boolean; should both variables be log-transformed before performing the regression? Defaults to FALSE.
- verbose
Should additional output be returned besides the SM50 estimate?
Value
If verbose is FALSE (the default), an estimate of SM50. Otherwise, output is the NLS model object.
Details
This relies on minpack.lm::nlsLM(), which is often able to
converge when stats::nls() function cannot find a solution.
Examples
set.seed(12)
fc <- fake_crustaceans(
error_scale = 17,
slope = 9,
L50 = 75,
n = 800,
allo_params = c(0.9, 0.25, 1.05, 0.2),
x_mean = 85
)
two_line_logistic(fc, "x", "y", verbose = FALSE)
#> SM50
#> 77.68165