Experimental 2D and 3D Scatter Plots for Delta-Scale Pairwise Correlations

Usage

delta_scatter(
  x,
  timediff1 = "2-1",
  timediff2 = "3-2",
  timediff3 = NULL,
  fisherz = TRUE,
  interactive = TRUE,
  digits = 3
)

Arguments

x: Input covariate array, with n rows, p columns, and t slices
timediff1: First pair of time points for the x-axis of the scatter plot. Should be in format 't2-t1'
timediff2: Second pair of time points for the y-axis of the scatter plot. Should be in format 't2-t1'
timediff3: Optional third pair of time points for the z-axis of the scatter plot. Should be in format 't2-t1'
fisherz: If TRUE, the Fisher z-transformation (atanh) will be applied to the correlations
interactive: If TRUE and timediff3 is NULL, an interactive plotly plot with hover text containing correlations and variable names will be generated. If FALSE and timediff3 is NULL, a regular ggplot2 scatterplot will be shown. If timediff3 is provided, this parameter will only determine whether hovertext is shown
digits: Number of digits for rounding in the hovertext

Value

Either a 2D or 3D scatterplot

References

Wickham H (2016). ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York. ISBN 978-3-319-24277-4, https://ggplot2.tidyverse.org. Sievert C (2020). Interactive Web-Based Data Visualization with R, plotly, and shiny. Chapman and Hall/CRC. ISBN 9781138331457, https://plotly-r.com.

Examples

if (FALSE) {
delta_scatter(Xarray)
delta_scatter(Xarray, timediff3 = "4-3")
delta_scatter(Xarray, timediff1 = "3-1", timediff2 = "5-3", timediff3 = "7-5")
}