tcata.line.plot: Temporal Check-All-That-Apply (TCATA) curve

Description

Plots TCATA curves based on count or proportion data. Can also be used for plotting Temporal Dominance of Sensations (TDS) curves based on dominance counts or proportions.

Usage

tcata.line.plot(X, n = 1, attributes = c(), times = c(),
lwd = 1, lty = 1, line.col = c(),
emphasis = NA, emphasis.col = c(), emphasis.lty = 1, emphasis.lwd = 3,
declutter = NA,
reference = NA, ref.col = c(), ref.lty = 2, ref.lwd = 1,
highlight = FALSE, highlight.col = c(), highlight.lty = 1, highlight.lwd = 5,
xlab = "Time", ylab = "Citation proportion", axes.font = 1,
axes.cex = 1, xlim = c(), las = 0,
x.increment = 5, box = FALSE,
legend.cex = 1, legend.font = 1, legend.pos = "topleft", legend.ncol = 2,
height = 8, width = 12, main = "",
save.format = "", save.as = "" )

Arguments

X: matrix of proportions (or, if there is no missing data, on counts), typically with Attributes in rows and times in columns.
n: The number of observations if X is a count matrix. Keep n = 1 if X is a matrix of proportions.
attributes: a vector of attribute labels, corresponding to the attributes in X.
times: a vector of time, corresponding to the times in X.
lwd: line width for attribute curves that matches either attributes or X.
lty: line types for attribute curves that matches either attributes or X.
line.col: attribute curves colours that matches attributes.
emphasis: matrix matching X in its dimensions, with a numeric value corresponding to points requiring emphasis, and NA for points without emphasis.
emphasis.col: vector colours for attributes corresponding to rows of X; taken from line.col if not specified.
emphasis.lty: either a line type (lty) for all emphasis lines .
emphasis.lwd: line weight associated with the emphasis line.
declutter: a matrix with the same dimensions as X; give the value 1 to show a proportion in X and reference (if given), otherwise give 0 or NA.
reference: a matrix with the same dimensions as X; give the value 1 if reference will be shown (allowing finer control than declutter), otherwise give 0 or NA
ref.col: reference line colour
ref.lty: reference line type
ref.lwd: reference line width
highlight: TRUE if differences will be highlighted; otherwise FALSE
highlight.col: a vector of colours for attributes corresponding to rows of X
highlight.lty: line type associated with the highlighting
highlight.lwd: line weight associated with the highlighting line
xlab: label for the x axis
ylab: label for the y axis
axes.font: font for axes labels; see par
axes.cex: size for axes labels.
xlim: x limits specified using a vector of 2 (ascending) numbers.
las: numeric in 0,1,2,3 indicating style of axis labels; see par
x.increment: interval between times when labelling the x axis
box: draw box around plot area; see: box
legend.cex: size of markers shown in the legend
legend.font: font for the legend; see text
legend.pos: location of plot legend; defaults to "topleft"
legend.ncol: number of columns in legend
height: window height
width: window width
main: plot title; see plot
save.format: If indicated, this will be the fle type for the save image. Defaults to "eps" (eps format). Other possible values are "" (not saved) or "png" (png format)
save.as: Filename if the file will be saved

References

Castura, J.C., Antúnez, L., Giménez, A., Ares, G. (2016). Temporal check-all-that-apply (TCATA): A novel temporal sensory method for characterizing products. Food Quality and Preference, 47, 79-90. tools:::Rd_expr_doi("10.1016/j.foodqual.2015.06.017")

Meyners, M., Castura, J.C. (2018). The analysis of temporal check-all-that-apply (TCATA) data. Food Quality and Preference, 67, 67-76. tools:::Rd_expr_doi("10.1016/j.foodqual.2017.02.003")

Examples

Run this code

# example using 'syrah' data set
low1 <- t(syrah[seq(3, 1026, by = 6), -c(1:4)])
colnames(low1) <- 10:180
tcata.line.plot(get.smooth(low1), lwd = 2, main = "Low-ethanol wine (Sip 1)")

# example using 'ojtcata' data set
data(ojtcata)
# comparison of Orange Juice 1 vs. Other OJs (2 to 6)
oj1.v.other <- citation.counts(ojtcata, product.name = "1", product.col = 2,
       attribute.col = 4, results.col = 5:25, comparison = "other")
times <- get.times(colnames(ojtcata)[-c(1:4)])
attributes <- unique(ojtcata$attribute)
palettes <- make.palettes(length(attributes))

# plot results
tcata.line.plot(oj1.v.other$P1, n = oj1.v.other$Pn,
   attributes = attributes, times = times,
   line.col = palettes$pal, reference = oj1.v.other$ref, ref.lty = 3,
   declutter = oj1.v.other$declutter, highlight = TRUE, highlight.lwd = 4,
   highlight.col = palettes$pal.light,
   height = 7, width = 11, legend.cex = 0.7, main = "Product 1 vs. Other Products")

# example showing plots similar to those in Meyners & Castura (2018)
# comparison of Orange Juice 1 vs. All OJs (1 to 6)
oj1.v.all <- citation.counts(ojtcata, product.name = "1", product.col = 2,
       attribute.col = 4, results.col = 5:25, comparison = "average")
lty.mat <- matrix(1,nrow=6,ncol=21)
lty.mat[, 1:3] <- c(rep(NA,8),rep(c(1,NA),4), 1, 1)
lty.mat[2, 9:12] <- lty.mat[5, 8] <- 3
tcata.line.plot(oj1.v.all$P1, n = oj1.v.all$Pn, attributes = attributes,
                times = times, line.col = palettes$pal, lty = lty.mat, lwd = 2,
                height = 7, width = 11, legend.cex = 0.7, main = "Product 1 vs. All Products")

Run the code above in your browser using DataLab