fitted.funreg

object

Either <code>response</code> or <code>correlation</code>.
If <code>response</code>, fitted values for the scalar response
variable are returned. If <code>correlation</code>, estimated 
individual-level correlation coefficients of the smoothed value of the functional covariate
at various time points with the scalar response variable are returned.

type

Only required if <code>type</code> is <code>correlation</code> 
and there is more than one functional covariate. This specifies
which functional covariate is of interest.

which.coef

Other optional arguments which may be passed from other methods but ignored by this one.

Returns fitted values for a <code>funreg</code> object.

Performs functional regression, and some related
approaches, for intensive longitudinal data (see the book by Walls & Schafer,
2006, Models for Intensive Longitudinal Data, Oxford) when such data is not
necessarily observed on an equally spaced grid of times. The
approach generally follows the ideas of Goldsmith, Bobb, Crainiceanu,
Caffo, and Reich (2011)<DOI:10.1198/jcgs.2010.10007> and the approach taken in their sample code, but
with some modifications to make it more feasible to use with long rather
than wide, non-rectangular longitudinal datasets with unequal and
potentially random measurement times. It also allows easy plotting of the
correlation between the smoothed covariate and the outcome as a function of
time, which can add additional insights on how to interpret a functional
regression. Additionally, it also provides several permutation tests for
the significance of the functional predictor. The heuristic interpretation
of ``time'' is used to describe the index of the functional predictor, but
the same methods can equally be used for another unidimensional continuous
index, such as space along a north-south axis. Note that most of the functionality
of this package has been superseded by added features after 2016 in the 'pfr' function by
Jonathan Gellar, Mathew W. McLean, Jeff Goldsmith, and Fabian Scheipl, in the
'refund' package built by Jeff Goldsmith and co-authors and maintained by Julia Wrobel.
The development of the funreg package in 2015 and 2016 was part of a research
project supported by Award R03 CA171809-01 from the National Cancer Institute and Award P50
DA010075 from the National Institute on Drug Abuse. The content is solely the responsibility of the
authors and does not necessarily represent the official views of the
National Institute on Drug Abuse, the National Cancer Institute, or the
National Institutes of Health.

fitted.funreg: fitted method for funreg object

Description

Usage

Arguments

Value