regr2.plot
3D plot of z against x and y, with regression plane fit and display of squared residuals.
3D plot of z against x and y, with regression plane fit and display of squared residuals.
- Keywords
- models, regression
Usage
regr2.plot(x, y, z,
main.in="put a useful title here",
resid.plot=FALSE,
plot.base.plane=TRUE,
plot.back.planes=TRUE,
plot.base.points=FALSE,
eye=NULL, ## S-Plus
theta=0, phi=15, r=sqrt(3), ticktype="detailed", ## R
...)
Arguments
- x,y,z
See
- main.in
main
title for plot.- resid.plot
Argument to
resid.squares
.- plot.base.plane, plot.back.planes, plot.base.points
Should these items be plotted?
- eye
S-Plus only. See
- theta, phi, r, ticktype
R only. See
- …
Other arguments to
persp
.
Value
"Viewing Transformation" for projecting 3D coordinates (x,y,z)
into the 2D plane. See persp
for details.
Note
This plot is designed as a pedagogical example for introductory
courses. When resid.plot=="square"
, then we actually see the
set of squares for which the sum of their areas is minimized by the
method of "least squares". The demo called in the examples section
shows the geometry of regression coefficients, the change in predicted
y when x1 is changed one unit holding all other x variables constant.
References
Heiberger, Richard M. and Holland, Burt (2015). Statistical Analysis and Data Display: An Intermediate Course with Examples in R. Second Edition. Springer-Verlag, New York. https://www.springer.com/us/book/9781493921218
Smith, W. and Gonick, L. (1993). The Cartoon Guide to Statistics. HarperCollins.
See Also
Examples
# NOT RUN {
data(fat)
regr2.plot(fat[,"abdomin"], xlab="abdomin",
fat[,"biceps"], ylab="biceps",
fat[,"bodyfat"], zlab="bodyfat",
resid.plot="square",
eye=c(335.5, 115.65, 171.9), ## used only in S-Plus
theta=140, phi=35, r=sqrt(15), ## used only in R
box=is.R(),
plot.back.planes=FALSE,
main="Least-squares with two X-variables")
# }
# NOT RUN {
demo("regr2", package="HH", ask=FALSE)
## run the file manually to see the individual steps.
# }