This package contains functions to automatically identify the structure of group- and individual-level networks from a range of vector autoregressive models, estimated with structural equation modeling.
Stephanie Lane [aut, trl],
Kathleen Gates [aut, cre],
Zachary Fisher [aut],
Cara Arizmendi [aut],
Peter Molenaar [aut],
Michael Hallquist [ctb],
Hallie Pike [ctb],
Cara Arizmendi [ctb],
Teague Henry [ctb],
Kelly Duffy [ctb],
Lan Luo [ctb],
Adriene Beltz [csp]
Maintainer: KM Gates gateskm@email.unc.edu
Researchers across varied domains gather multivariate data for each individual unit of study across multiple occasions of measurement. Generally referred to as time series (or in the social sciences, intensive longitudinal) data, examples include psychophysiological processes such as neuroimaging and heart rate variability, daily diary studies, ecological momentary assessments, data passively collected from devices such as smartphones, and observational coding of social interactions among dyads.
A primary goal for acquiring these data is to understand dynamic processes.
The gimme package contains several functions for use with these data.
These functions include gimmeSEM, which provides both group-
and individual-level results by looking across individuals for patterns of
relations among variables. A function that provides group-level results,
aggSEM, is included, as well as a function that provides
individual-level results, indSEM. The major functions within the gimme package all require the
user to specify the data, although many additional options exist.