initialRichards {richards} | R Documentation |
These functions returns initial values for the parameters in the Richards functions models.
initialNyFixed(mCall, data, LHS, ny = NULL, minnrow = 5, pnames = c("a", "d", "b", "x50")) initialNyFixedLog(mCall, data, LHS, ny = NULL, minnrow = 5, pnames = c("a", "d", "xmid", "scal")) initialNyFixedLogB(mCall, data, LHS, ny = NULL, minnrow = 5, pnames = c("a", "d", "xmid", "b")) initialRichards(mCall, data, LHS, ny = 1, minnrow = 6, factor = 1.35, pnames = c("a", "d", "b", "x50", "ny")) initialRichardsLog(mCall, data, LHS, ny = 1, minnrow = 6, pnames = c("a", "d", "xmid", "scal", "ny")) initialRichardsLogB(mCall, data, LHS, ny = 1, minnrow = 6, pnames = c("a", "d", "xmid", "b", "ny"))
mCall |
See selfStart: "a matched call to the function model". |
data |
See selfStart: "a data frame in which to interpret the variables in mCall". |
LHS |
See selfStart: "the expression from the left-hand side of the model formula in the call to nls". |
ny |
a numeric value, or NULL . |
minnrow |
an integer, the number of observations required. |
factor |
a numeric value, a factor for the independent variable. |
pnames |
See selfStart: "a character vector specifying the terms on the right hand side of model for which initial estimates should be calculated. Passed as the namevec argument to the deriv function." |
A four parameter logistic model is fitted to the data by SSfpl and nls.
These fitted four parameters will together with ny
set to
1
determine the initial values found by initialRichards
,
initialRichardsLog
and initialRichardsLogB
.
For fixed ny
the asymptotes and location parameter
(the input value where the function value will be midway
between the asymptotes)
of a fitted four parameter model will be returned.
A scale parameter
(for the Richards curve with parameter ny
)
will be determine such that
the slope this curve
is as
the slope of the fitted four parameter curve,
the slopes for both curves midway between the asymptotes.
Vector of initial values: "This function should return initial values for the parameters in the model."
Jens Henrik Badsberg
demo(sourceNy) demo(sourceNyExtras) demo(sourceRichards) ls()