sitar(x, y, id, data, df, knots, fixed = random, random = "a+b+c",
a.formula = ~1, b.formula = ~1, c.formula = ~1, bounds = 0.04, start,
bstart = xoffset, xoffset = "mean", returndata = FALSE, verbose = FALSE,
correlation = NULL, weights = NULL, subset = NULL, method = "ML", na.action = na.fail,
control = nlmeControl(returnObject = TRUE))
## S3 method for class 'sitar':
update(object, ..., evaluate = TRUE)x, y and id.df quantiles of x distribution).random)."a+b+c").~ 1).~ 1).~ 1).x for regression spline, or fractional extension of range (default 0.04).nlme).b (either "mean", "apv" or value (default xoffset)).x (either "mean" (default), "apv" or value).subset and
subsample for simulanlme).corStruct object describing the within-group correlation structure (see nlme).varFunc object or one-sided formula describing the within-group heteroscedasticity structure (see nlme).nlme).nlme).nlme).nlme).sitar.update consisting of any of the above sitar parameters.update call is passed to sitar for evaluation, while if FALSE the expanded call itself is returned.sitar representing the nonlinear mixed-effects model fit, with all the components returned by nlme
(see nlmeObject for a full description) plus the following components:bstart.xoffset.sitar call that produced the object.y.lm object providing starting values for the B-spline curve.print, plot, anova and summary have methods to show the results of the fit. The
functions resid, coef, fitted, fixed.effects, random.effects,
predict, getData, getGroups, getCovariate and getVarCov can be used to extract some of its components.Note that versions of sitar prior to 1.0.4 did not return fitnlme.
Both plot and predict may require it, in which case they update
the SITAR object on the fly, with a message. Also version 1.0.5 altered the defaults
for xoffset and bstart. Models fitted with versions prior to 1.0.5 need refitting.
xoffset allows the origin of x to be varied, while bstart specifies the
starting value for b, both of which can affect the model fit and particularly
b. The values of bstart, knots and bounds are offset by xoffset
for fitting purposes, and similarly for fixed effect b. update updates the model by taking the object call,
adding any new parameters and replacing changed ones. Where possible the fixed and random
effects of the model being updated are suitably modified and passed via the start argument.
data(heights)
## fit simple model
(m1 <- sitar(x=age, y=height, id=id, data=heights, df=5))
## relate random effects to age at menarche (with censored values +ve)
## both a (size) and b (tempo) are positively associated with age at menarche
amen <- abs(heights$men)
(m2 <- update(m1, a.form=~amen, b.form=~amen, c.form=~amen))Run the code above in your browser using DataLab