MSEplot.fn {CGManalyzer} | R Documentation |
Plot the mean and standard error or standard deviation of multiscale entropy by group
Description
function to plot the mean and standard error or standard deviation of multiscale entropy by group
Usage
MSEplot.fn(Scale, MSE, Name, responseName = NA, timeUnit = "", byGroup = TRUE,
MSEsd = NA, N = NA, stdError = TRUE, xRange = NA, yRange = NA, las = 2, col = NA,
pch = NA, Position = "topleft", cex.legend = 0.75, main = "")
Arguments
Scale |
a vector for scale |
MSE |
matrix for entropy if byGroup=FALSE, and otherwise for average entropy value in a group at a scale. In the matrix, the row is for scale and column for individuals or groups. |
Name |
vector of names for groups |
responseName |
name to represent the response to be analyzed, such as 'glucose' |
timeUnit |
the time unit for scale |
byGroup |
If byGroup = TRUE, multiscale entropy is plotted by groups; otherwise, by individuals |
MSEsd |
matrix for standard deviation of entropy value in a group at a scale |
N |
matrix for number of subjects in a group at a scale |
stdError |
if it is true, the length of a vertical bar represent 2*standard error; otherwise, the length of a vertical bar represent 2*standard deviation |
xRange |
range for the x-axis |
yRange |
range for the y-axis |
las |
las for the y-axis |
col |
vector for the colors to indicate groups or individuals |
pch |
vector for the point types to indicate groups or individuals |
Position |
position for the legend |
cex.legend |
cex for the legend |
main |
main title for title() |
Details
function to plot the mean and standard error or standard deviation of multiscale entropy by group
Value
No value returned
Author(s)
Xiaohua Douglas Zhang
References
Zhang XD, Zhang Z, Wang D. 2018. CGManalyzer: an R package for analyzing continuous glucose monitoring studies. Bioinformatics 34(9): 1609-1611 (DOI: 10.1093/bioinformatics/btx826).
Examples
library(CGManalyzer)
package.name <- "CGManalyzer"
source( system.file("SPEC", "SPECexample.R", package = package.name) )
scalesInTime <- Scales*equal.interval
MSE.mat <- read.csv(file=system.file("SPEC", "MSE.csv", package = package.name), row.names=1)
Types <- unique( subjectTypes )
Types <- Types[order(Types)]
nType <-length(Types)
col.vec <- rep(NA, length(subjectTypes) )
for( i in 1:nType ) { col.vec[ subjectTypes == Types[i] ] <- i }
MSEplot.fn(scalesInTime, MSE=t(MSE.mat), Name=Types, responseName="glucose", timeUnit="minute",
byGroup=FALSE, MSEsd=NA, N=NA, stdError=TRUE, xRange=NA, yRange=NA,
pch=rep(1, dim(MSE.mat)[1]),las=2, col=col.vec, Position="topleft",
cex.legend=0.0005, main="A: MSE by individual")
legend("topleft", legend=paste0(Types, "(N=", table( subjectTypes ), ")"),
col=1:nType, cex=1, lty=1, pch=1)