gg.rank.plot

Graphically displays the count of joint ranks selected by each method employed in the simulation study described in the CJIVE manuscript

Joint and Individual Variation Explained (JIVE) is a method for decomposing multiple datasets obtained on the same subjects into
shared structure, structure unique to each dataset, and noise. The two most common implementations are R.JIVE, an iterative
approach, and AJIVE, which uses principal angle analysis. JIVE estimates subspaces but interpreting these subspaces can be
challenging with AJIVE or R.JIVE. We expand upon insights into AJIVE as a canonical correlation analysis (CCA) of principal component
scores. This reformulation, which we call CJIVE, 1) provides an ordering of joint components by the degree of correlation between
corresponding canonical variables; 2) uses a computationally efficient permutation test for the number of joint components, which
provides a p-value for each component; and 3) can be used to predict subject scores for out-of-sample observations.
Please cite the following article when utilizing this package:
Murden, R., Zhang, Z., Guo, Y., & Risk, B. (2022) <doi:10.3389/fnins.2022.969510>.

Raphiel Murden

CJIVE

Canonical Joint and Individual Variation Explained (CJIVE)

Benjamin Risk

gg.rank.plot function

<dl><dt>rank.dat</dt>
<dd>data frame expected to be built with the functions dplyr::count and tidyr::complete, which should include the following variables
Rank - numeric values of the rank selected by each method in each replicate simulation
n - the number of times this value was selected as the rank
Type - the subspace for which the norm is given (i.e., joint/individual score/loading for dataset X1 or X2 (except for joint scores))
Method - the method by which the subspace was estimated, e.g. CJIVE, AJIVE, R.JIVE
JVE_1 and JVE_2 - labels describing the proportion of joint variation explained in each dataset (and typically the number of variables in dataset X2)</dd>
<dt>cols</dt>
<dd>a vector of colors, must have length equal to the number of methods used in the simulation</dd>
<dt>show.legend</dt>
<dd>logical (TRUE/FALSE) for whether a legend should be included in the plot. Default is FALSE</dd>
<dt>text.size</dt>
<dd>numeric value for the font size</dd>
<dt>num.sims</dt>
<dd>numeric value for the number of replicates evaluated in each full combination of experimental settings</dd></dl>

Arguments

Function for plotting selected joint ranks — gg.rank.plot

<dl>

<dt>rank.dat</dt>
<dd>data frame expected to be built with the functions dplyr::count and tidyr::complete, which should include the following variables
Rank - numeric values of the rank selected by each method in each replicate simulation
n - the number of times this value was selected as the rank
Type - the subspace for which the norm is given (i.e., joint/individual score/loading for dataset X1 or X2 (except for joint scores))
Method - the method by which the subspace was estimated, e.g. CJIVE, AJIVE, R.JIVE
JVE_1 and JVE_2 - labels describing the proportion of joint variation explained in each dataset (and typically the number of variables in dataset X2)</dd>


<dt>cols</dt>
<dd>a vector of colors, must have length equal to the number of methods used in the simulation</dd>


<dt>show.legend</dt>
<dd>logical (TRUE/FALSE) for whether a legend should be included in the plot. Default is FALSE</dd>


<dt>text.size</dt>
<dd>numeric value for the font size</dd>


<dt>num.sims</dt>
<dd>numeric value for the number of replicates evaluated in each full combination of experimental settings</dd>

</dl>

gg.rank.plot: Function for plotting selected joint ranks

Description

Usage

Value

Arguments