RF SPREAD PLOT
Name:
Type:
Purpose:
Generates a residuals-fitted (r-f) spread plot.
Description:
The residuals-fitted (r-f) spread plot is a graphical measure
of the goodness of fit. That is, this command is preceeded
by some type of fit. It plots percent point (or quantile)
plots of the fitted values minus their mean and the residuals
arranged side by side with a common vertical scale.
The vertical spread of the residuals compared to the vertical
spread of the fitted values gives an indication of how much
of the variation is explained by the fit.
Dataplot assumes that some type of fit has already been
performed and that the predicted values are stored in the
internal variable PRED and the residuals are stored in the
internal variable RES. If you want to generate the rf
spread plot for variables that are not automatically
stored on PRED and RES, then simply copy the desired variables
into PRED and RES before entering the RF SPREAD PLOT (e.g.,
LET PRED = Y).
Syntax:
RF SPREAD PLOT <SUBSET/EXCEPT/FOR qualification>
where the <SUBSET/EXCEPT/FOR qualification> is optional.
Examples:
FIT Y X
RF SPREAD PLOT
LOWESS Y X
RF SPREAD PLOT
SPLINE FIT Y X
RF SPREAD PLOT
Default:
Synonyms:
Related Commands:
|
LINES
|
= Sets the type for plot lines.
|
|
CHARACTER
|
= Sets the type for plot characters.
|
|
PERCENT POINT PLOT
|
= Generates a percent point plot.
|
|
PLOT
|
= Generates a data or function plot.
|
Reference:
"Visualizing Data", Cleveland, William S., Hobart Press, 1993.
Applications:
Exploratory Data Analysis
Implementation Date:
Program:
SKIP 25
READ BERGER1.DAT Y X
FIT Y X
CHARACTER CIRCLE
LINE BLANK
RF SPREAD PLOT
|
