Embed

Reorganizes an individual’s observed time
series into an embedded matrix. The embedded matrix is constructed with replicates of an
individual time series that are offset from each other in time. The function requires
two parameters, one that specifies the number of observations to be used (i.e. the number of
embedded dimensions) and the other that specifies the number of observations to offset successive embeddings.

Implements the Exploratory Graph Analysis (EGA) framework for dimensionality and psychometric assessment. EGA is part of a new area called network psychometrics that uses undirected network models for the assessment of psychometric properties. EGA estimates the number of dimensions (or factors) using graphical lasso or Triangulated Maximally Filtered Graph (TMFG) and a weighted network community detection algorithm. A bootstrap method for verifying the stability of the dimensions and items in those dimensions is available. The fit of the structure suggested by EGA can be verified using Entropy Fit Indices. A novel approach called Unique Variable Analysis (UVA) can be used to identify and reduce redundant variables in multivariate data. Network loadings, which are roughly equivalent to factor loadings when the data generating model is a factor model, are available. Network scores can also be computed using the network loadings. Dynamic EGA (dynEGA) will estimate dimensions from time series data for individual, group, and sample levels. Golino, H., & Epskamp, S. (2017) <doi:10.1371/journal.pone.0174035>. Golino, H., Shi, D., Christensen, A. P., Garrido, L. E., Nieto, M. D., Sadana, R., & Thiyagarajan, J. A. (2020) <doi:10.31234/osf.io/gzcre>. Christensen, A. P., & Golino, H. (under review) <doi:10.31234/osf.io/hz89e>. Golino, H., Moulder, R. G., Shi, D., Christensen, A. P., Garrido, L. E., Nieto, M. D., Nesselroade, J., Sadana, R., Thiyagarajan, J. A., & Boker, S. M. (2020) <doi:10.31234/osf.io/mtka2>. Christensen, A. P. & Golino, H. (2021) <doi:10.3390/psych3030032>. Christensen, A. P., Garrido, L. E., & Golino, H. (under review) <doi:10.31234/osf.io/4kra2>. Golino, H., Christensen, A. P., Moulder, R. G., Kim, S., & Boker, S. M. (under review) <doi:10.31234/osf.io/tfs7c>.

Hudson Golino

EGAnet

Exploratory Graph Analysis – a Framework for Estimating the
Number of Dimensions in Multivariate Data using Network
Psychometrics

Alexander Christensen

Robert Moulder

Luis E. Garrido

Laura Jamison

Embed function

<dl><dt>x</dt>
<dd>Vector.
An observed time series to be reorganized into a time-delayed embedded matrix.</dd>
<dt>E</dt>
<dd>Integer.
Number of embedded dimensions or the number of observations to be used. For example,
an <code>"E = 5"</code> will generate a matrix with five columns, meaning that five consecutive observations are used to create each row of the embedded matrix.</dd>
<dt>tau</dt>
<dd>Integer.
Number of observations to offset successive embeddings. A tau of one uses adjacent observations.
Default is <code>"tau = 1"</code>.</dd></dl>

Arguments

Pascal Deboeck &lt;pascal.deboeck at psych.utah.edu&gt;

Author

Time-delay Embedding — Embed

<dl>

<dt>x</dt>
<dd>Vector.
An observed time series to be reorganized into a time-delayed embedded matrix.</dd>


<dt>E</dt>
<dd>Integer.
Number of embedded dimensions or the number of observations to be used. For example,
an <code>"E = 5"</code> will generate a matrix with five columns, meaning that five consecutive observations are used to create each row of the embedded matrix.</dd>


<dt>tau</dt>
<dd>Integer.
Number of observations to offset successive embeddings. A tau of one uses adjacent observations.
Default is <code>"tau = 1"</code>.</dd>

</dl>

Embed: Time-delay Embedding

Description

Usage

Value

Arguments

Author

References

Examples