# NOT RUN {
## Single plot.
m1 <- pcrfit(reps, 1, 2, l5)
plot(m1)
## Add another plot in blue
## with 99% confidence interval.
m2 <- pcrfit(reps, 1, 12, l5)
plot(m2, add = TRUE, col = 4, confband = "confidence", level = 0.99)
## Plot a 'modlist' batch with coloring of replicates.
ml1 <- modlist(reps, 1, 2:13, model = l4)
plot(ml1, col = gl(3,4))
## Subset of data.
plot(ml1, type = "n", col = rep(1:3, each = 4),
par2D = list(xlim = c(10, 30)))
## Plot a 'replist'.
rl1 <- replist(ml1, group = gl(3, 4))
plot(rl1)
## Standard deviation instead of
## replicate points; suppress plotting
## of point symbols.
plot(rl1, type = "l", errbar = "sd",
par2D = list(pch = ""))
## 95% confidence values.
plot(rl1, errbar = "conf",
par2D = list(pch = ""))
## Plot single curves for diagnostics.
plot(ml1, which = "single", col = rep(1:3, each = 4))
## 3D plots of 'modlist's or 'replist's.
plot(ml1, which = "3D", col = rep(1:3, each = 4))
rgl.close()
plot(rl1, which = "3D")
rgl.close()
# }
# NOT RUN {
## Example for "image" type when
## using large data.
ml2 <- modlist(vermeulen2)
plot(ml2, which = "image")
## Example for outlier identification:
## RED/*name* indicates failed fitting,
## BLUE/**name** indicates sigmoidal outlier
## using 'testdat' set.
ml3 <- modlist(testdat, model = l5)
plot(ml3, which = "single")
# }
Run the code above in your browser using DataLab