smeObject: Fitted sme Object

Description Value Author(s) See Also

Description

An object returned by the sme function, inheriting from class sme, representing a fitted smoothing-splines mixed-effects model

Value

An sme object must contain the following components.

call

a list containing an image of the sme call that produced the object.

coefficients

an n+1 by p matrix where n is the number of subjects and p is the number of knots used in the spline basis. The first row of the matrix corresponds to the fitted values of the mean curve at the knots, and the remaining n rows correspond to the fitted values of the individual deviations from the mean curve at the knots.

fitted

a vector of model fitted values corresponding to the original observations.

logLik

the log-likelihood of the fitted model.

residuals

a vector of model residuals.

nobs

the number of observations.

data

a data frame of the original data used to fit the model with variables y, tme and ind corresponding to observations, time points and subject identifiers respectively.

df

a vector consisting of named components mu and v corresponding to the degrees of freedom of the mean and subject curves respectively.

smoothingParameters

a vector of named components mu and v corresponding to the smoothing parameters for the mean and subject curves respectively.

parameters

a list with named components sigmaSquared and D corresponding to the error variance and (unregularized) variance of the random-effects respectively.

iterations

the number of iterations of the EM algorithm that ran before convergence (or the limit was reached)

info

a numeric code indicating diagnostic information from the EM algorithm with zero indicating a successful run.

In some instances, an sme object may also contain the following components.

knots

a vector of the knots used in the spline basis when they do not coincide with the unique design time points.

Author(s)

Maurice Berk maurice.berk01@imperial.ac.uk

See Also

sme


sme documentation built on May 2, 2019, 4:03 a.m.