sigdrift_start: Starting estimates for the sigmoidal-drift model

In mnirs: Muscle Near-Infrared Spectroscopy Processing and Analysis

Starting estimates for the sigmoidal-drift model

Description

Vector-level initialiser behind sigdrift_init(), called directly by the kinetics worker on the fit window. The sigmoid is seeded as for SSgompertz() (init_asymptotes(), init_inflection()), the drift onset resolved from that seed, and the residual from the seeded sigmoid past the onset regressed on time from the onset: the intercept corrects the asymptote B and the slope is the drift. A second pass re-seeds the sigmoid on the drift-corrected response, correcting an inflection biased by the drift. Fewer than two points past the onset seed a zero drift. User-fixed values are held.

Usage

sigdrift_start(x, t, fixed = list(), shape = "symmetric")

Arguments

x	A numeric vector of the response variable (sorted by t).
t	A numeric vector of the predictor variable.
fixed	A named list of user-fixed parameter values.
shape	Character; the 4-parameter sigmoidal shape. One of "symmetric" (default; logistic()), "gompertz" (gompertz()), or "gompertz_left" (gompertz_left()).

Value

A named numeric vector of starting estimates in model order.

mnirs documentation built on Sept. 13, 2026, 1:06 a.m.