girls {rrcov3way} | R Documentation |
Sempe girls' growth curves data
Description
Thirty girls selected from a French auxiological study (1953-1975) to get insight into the physical growth patterns of children from ages four to fifteen, Sempe (1987). They were measured yearly between the ages 4 and 15 on the following eight variables:
weight = Weight
length = Length
crump = Crown-rump length
head = Head circumference
chest = Chest circumference
arm = Arm
calf = Calf
pelvis = Pelvis
The data set is three way data array of size 30 (girls) x 8 (variables) x 12 (years).
Usage
data("girls")
Format
The format is a three way array with the following dimensions: The first dimension refers to 30 girls. The second dimension refers to the eight variables measured on the girls. The third dimension refers to the years – 4 to 15.
Details
The data are generally preprocessed as standard multiway profile data. For details see Kroonenberg (2008), Chapters 6 and 15.
Source
The data sets are available from Pieter Kroonenberg's web site at: "three-mode.leidenuniv.nl/data/girlsgrowthcurvesinfo.htm"
References
Sempe, M. (1987). Multivariate and longitudinal data on growing children: Presentation of the French auxiological survey. In J.Janssen et al. Data analysis. The Ins and Outs of solving real problems (pp. 3-6). New York: Plenum Press.
Kroonenberg (2008). Applied multiway data analysis. Wiley series in probability and statistics. Hoboken NJ, Wiley.
Examples
data(girls)
str(girls)
## Center the data in mode A and find the "average girl"
center.girls <- do3Scale(girls, center=TRUE, only.data=FALSE)
X <- center.girls$x
center <- center.girls$center
average.girl <- as.data.frame(matrix(center, ncol=8, byrow=TRUE))
dimnames(average.girl) <- list(dimnames(X)[[3]], dimnames(X)[[2]])
## Divide these variables by 10 to reduce their range
average.girl$weight <- average.girl$weight/10
average.girl$length <- average.girl$length/10
average.girl$crrump <- average.girl$crrump/10
average.girl
p <- ncol(average.girl)
plot(rownames(average.girl), average.girl[,1], ylim=c(min(average.girl),
max(average.girl)), type="n", xlab="Age", ylab="")
for(i in 1: p)
{
lines(rownames(average.girl), average.girl[,i], lty=i, col=i)
points(rownames(average.girl), average.girl[,i], pch=i, col=i)
}
legend <- colnames(average.girl)
legend[1] <- paste0(legend[1], "*")
legend[2] <- paste0(legend[3], "*")
legend[3] <- paste0(legend[4], "*")
legend("topleft", legend=legend, col=1:p, lty=1:p, pch=1:p)