Example Program and Statement Details

Example Graph

The following graph was generated by the Example Program:
Example Correlation Loading Plot

Example Program

This is a simplified version of the CorrLoadPlot template for PROC PLS in the SAS/STAT product. It consists of overlaid scatter plots of the scores of the first two factors, the loadings of the model effects, and the loadings of the dependent variables. The loadings are scaled so that the amount of variation in the variables that is explained by the model is proportional to the distance from the origin; circles indicating various levels of explained variation are also overlaid.
The circles are drawn with ELLIPSEPARM statements by setting the SEMIMAJOR and SEMIMINOR lengths to be the same. Notice that all circles are concentric because they share the same origin (0,0). The radius of each circle is passed dynamically.
Also note that an OVERLAYEQUATED layout was used to force the length of unit intervals on both axes to be the same.
The input data shown is representative of that computed by PROC PLS for the Correlation Loadings Plot. For more details, see the first example for PROC PLS in the MISSING Bookref .
proc template;
 define statgraph ellipseparm;
  dynamic RADIUS1 RADIUS2 RADIUS3 RADIUS4 ;
  begingraph; 
   entrytitle "Correlation Loading Plot";
   layout overlayequated / equatetype=square 
     commonaxisopts=
      (tickvaluelist=(-1 -.75 -.5 -.25 0 .25 .5 .75 1) 
        viewmin=-1 viewmax=1) 
     xaxisopts=
      (label="Factor 1" offsetmin=0.05 offsetmax=0.05)
     yaxisopts=
      (label="Factor 2" offsetmin=0.05 offsetmax=0.05);
    ellipseparm semimajor=RADIUS1 semiminor=RADIUS1 slope=0
     xorigin=0 yorigin=0 / clip=true display=(outline)
     outlineattrs=(pattern=dash) datatransparency=.75;
    ellipseparm semimajor=RADIUS2 semiminor=RADIUS2 slope=0 
     xorigin=0 yorigin=0 / clip=true display=(outline) 
     outlineattrs=(pattern=dash) datatransparency=.75;       
    ellipseparm semimajor=RADIUS3 semiminor=RADIUS3 slope=0 
     xorigin=0 yorigin=0 / clip=true display=(outline) 
     outlineattrs=(pattern=dash) datatransparency=.75; 
    ellipseparm semimajor=RADIUS4 semiminor=RADIUS4 slope=0 
     xorigin=0 yorigin=0 / clip=true display=(outline) 
     outlineattrs=(pattern=dash) datatransparency=.75;

    scatterplot x=xcirclelabel y=ycirclelabel / primary=true
     markercharacter=circlelabel datatransparency=0.75 ;
    scatterplot x=corr1 y=corr2 / name="ScatterVars"  
     group=corrgroup markercharacter=corrlabel; 
    discretelegend "ScatterVars"; 
   endlayout;
  endGraph;
 end;
run;

data corrplot;
  infile cards missover;
  input Corr1 Corr2 CorrGroup &$18. CorrLabel :$7.
        xCircleLabel  yCircleLabel CircleLabel :$8.;
datalines;
-0.179 -0.268 Predictor Loading  S1 0  0.5 25%
 0.105  0.332 Predictor Loading  S2 0 -0.5 25%
-0.654  0.094 Predictor Loading  S3 0  0.707 50%
-0.653  0.685 Predictor Loading  S4 0 -0.707 50%
 0.096  0.059 Predictor Loading  S5 0  0.866 75%
 0.132  0.036 Predictor Loading  L1 0 -0.866 75%
 0.087  0.156 Predictor Loading  L2 0  1 100%
 0.940  0.160 Predictor Loading  L3 0 -1 100%
 0.607 -0.350 Predictor Loading  L4
 0.096  0.059 Predictor Loading  L5
-0.111 -0.534 Predictor Loading  P1
 0.003  0.256 Predictor Loading  P2
 0.293  0.551 Predictor Loading  P3
-0.480  0.643 Predictor Loading  P4
-0.096 -0.059 Predictor Loading  P5
 0.946  0.279 Response Loading  log_RAI
-0.196  0.403 Observation  1
 0.020 -0.001 Observation  2
-0.195  0.324 Observation  3
 0.021 -0.079 Observation  4
-0.009 -0.274 Observation  5
 0.567  0.294 Observation  6
-0.096 -0.059 Observation  7
 0.258  0.210 Observation  8
-0.104 -0.309 Observation  9
-0.187 -0.458 Observation  10
 0.051 -0.078 Observation  11
 0.017 -0.260 Observation  12
-0.621  0.372 Observation  13
 0.392  0.138 Observation  14
 0.080 -0.221 Observation  15
run;

proc sgrender data=corrplot template=ellipseparm;
  dynamic radius1=.50 radius2=.71 radius3=.87 radius4=1;
run;

Statement Summary

The ELLIPSEPARM statement plots an ellipse with specified semimajor and semiminor axis lengths, a specified slope for the major axis, and the ellipse center. The ellipse center is the point of intersection of the semimajor and semiminor axes.
An ELLIPSEPARM plot does not perform computations on input data to derive the location and shape of the ellipse. See ELLIPSE Statement for information about computed ellipses.
An ELLIPSEPARM statement can be used only within a 2-D overlay-type layout (for example, an OVERLAY, OVERLAYEQUATED, or PROTOTYPE layout). Another plot that is derived from data values that provide boundaries for the axis area must be included in the layout. It is typically overlaid with a scatter plot.
You can generate a single ellipse by specifying a constant for each required argument. You can generate multiple ellipses by specifying a numeric column for any or all required arguments. If any of the SEMIMAJOR=, SEMIMINOR=, XORIGIN= or YORIGIN= constants or columns contains a missing value, no ellipse is drawn. To request a vertical major axis, specify SLOPE=. ( missing value as a constant or column value).
If the GROUP= option is specified, then the group value must be a column (character or numeric). For each group value, there must be a numeric column value that does not contain missing values for SEMIMAJOR=, SEMIMINOR=, XORIGIN=, and YORIGIN=. The SLOPE= column might contain missing values. Under these circumstances, one or more ellipse might be drawn for each group value.

Required Arguments

SEMIMAJOR=number | numeric-column | expression
specifies half the length of the major axis for the ellipse.
Requirement: The SEMIMAJOR value must be positive.
Values are in the units of the data. The SEMIMAJOR value can be greater than, smaller than, or equal to the SEMIMINOR value.
Interaction: If a numeric column is specified and the column contains missing or negative values, no ellipse is drawn.
SEMIMINOR=number | numeric-column | expression
specifies half the length of the minor axis for the ellipse.
Requirement: The SEMIMINOR value must be positive.
Values are in the units of the data. The SEMIMINOR value can be greater than, smaller than, or equal to the SEMIMAJOR value.
Interaction: If a numeric column is specified and the column contains missing or negative values, no ellipse is drawn.
SLOPE=number | numeric-column | expression
specifies the slope of the major axis for the ellipse.
Slope can be positive or negative.
Setting SLOPE=0 creates a major axis parallel to the X-axis. Setting SLOPE=. (missing value) creates a major axis parallel to the Y-axis.
The slope value is in the data space and might or might not be maintained in the screen space. Thus, setting SLOPE=1 does not always generate a 45 degree line on the screen.
XORIGIN=number | numeric-column | expression
specifies the X coordinate of the center of the ellipse.
Values are in the units of the data.
By default, if the value specified for the XORIGIN= option is outside of the X-axis data range, then the data range is extended to include the specified point. This behavior can be changed with the CLIP= option.
YORIGIN=number | numeric-column | expression
specifies the Y coordinate of the center of the ellipse.
Values are in the units of the data.
By default, if the value specified for the YORIGIN= option is outside of the Y-axis data range, then the data range is extended to include the specified point. This behavior can be changed with the CLIP= option.

Options

Statement Option
Description
Specifies whether the data for the ellipse are considered when determining the data ranges for the axes.
Specifies the degree of the transparency of the ellipse fill color and outline.
Specifies whether to display an outlined ellipse, a filled ellipse, or an outlined and filled ellipse.
Specifies the appearance of the interior fill of the ellipse.
Creates a separate ellipse for each unique group value of the specified column.
Specifies indices for mapping line attributes (color and pattern) to one of the GraphData1 - GranphDataN style elements.
Specifies a label for use in a legend.
Assigns a name to a plot statement so that it can be referenced in other template statements.
Specifies the properties of the ellipse outline.
Specifies whether data are mapped to the primary X (bottom) axis or the secondary X2 (top) axis.
Specifies whether data are mapped to the primary Y (left) axis or the secondary Y2 (right) axis.
CLIP=boolean
specifies whether the data for the ellipse are considered when determining the data ranges for the axes.
Default: FALSE
FALSE
The data for the ellipse contribute to the data range for each axis. Each axis might be extended to force the display of the entire ellipse.
TRUE
The data for the ellipse are ignored when establishing axis scales. Each axis scale is determined by the other plots in the parent layout. This might result in the ellipse not being entirely displayed (clipped) if its data range is not within the data ranges of the other plots.
DATATRANSPARENCY=number
specifies the degree of the transparency of the ellipse fill color and outline.
Default: 0
Range: 0 (opaque) to 1 (entirely transparent)
DISPLAY=STANDARD | ALL | ( display-options )
specifies whether to display an outlined ellipse, a filled ellipse, or an outlined and filled ellipse.
Default: GraphEllipse:DisplayOpts style reference.
STANDARD
displays an outlined, unfilled ellipse
ALL
displays an outlined, filled ellipse
(display-options)
a list of features to be displayed. The list must be enclosed in parentheses and must include one of the following:
OUTLINE—displays an outlined ellipse
FILL—displays a filled ellipse
Use FILLATTRS= and OUTLINEATTRS= to control the appearance of the ellipse.
FILLATTRS=style-element | style-element (fill-options) | (fill-options)
specifies the appearance of the interior fill area of the ellipse. See General Syntax for Attribute Options for the syntax on using a style-element and Fill Options for available fill-options.
Default:
  • For non-grouped data, the GraphDataDefault style element.
  • For grouped data, the GraphData1 - GraphDataN style elements.
Interaction: For this option to have any effect, the fill must be enabled by the ODS style or the DISPLAY= option.
GROUP=column | expression
creates a separate ellipse for each unique group value of the specified column.
Default:
  • If DISPLAY=(OUTLINE), each distinct group value might be represented in the graph by a different combination of outline color and line pattern. Line color and pattern vary according to the ContrastColor and LineStyle attributes of the GraphData1 - GraphDataN style elements. Line thickness (for grouped and ungrouped data) is controlled by the OUTLINEATTRS= option.
  • If DISPLAY=(FILL), each distinct group value might be represented in the graph by a different fill color defined by the GraphData1:Color - GraphDataN:Color style references.
  • If DISPLAY=(FILL OUTLINE), each distinct group value might be represented in the graph by a different fill color, outline color, and outline pattern.
The representations that are used to identify the groups can be overridden individually. For example, each distinct group value might be represented by a different line pattern for the ellipses, but the PATTERN= suboption of the OUTLINEATTRS= option could be used to assign the same line pattern to all ellipse outlines, letting outline color distinguish group values.
Restriction: This option can be used only when a numeric column is specified for the SLOPE=, SEMIMAJOR=, and SEMIMINOR= arguments.
INDEX=positive-integer-column | expression
specifies indices for mapping line attributes (color and pattern) and fill attributes to one of the GraphData1 - GranphDataN style elements.
Default: no default
Interaction: For this option to have any effect, the GROUP= option must also be specified.
Interaction: All of the indexes for a specific group value must be the same. Otherwise, the results are unpredictable.
Interaction: If this option is not used, then the group values are mapped in the order of the data.
Interaction: The index values are 1-based indices. For the style elements in GraphData1 - GraphDataN, if the index value is greater than N, then a modulo operation remaps that index value to a number less than N to determine which style element to use.
Discussion: Indexing can be used to collapse the number of groups that are represented in a graph. For more information, see Remapping Groups for Grouped Data.
LEGENDLABEL= "string"
specifies a label for use in a legend.
Default: The string specified on the NAME= option.
Interaction: If the GROUP= option is specified, this option is ignored.
NAME="string"
assigns a name to a plot statement for reference in other template statements.
Default: no default
Restriction: The string is case sensitive, cannot contain spaces, and must define a unique name within the template.
Interaction: The string is used as the default legend label if the LEGENDLABEL= option is not used.
The specified name is used primarily in legend statements to coordinate the use of colors and line patterns between the graph and the legend.
OUTLINEATTRS=style-element | style-element (line-options) | (line-options)
specifies the attributes of the ellipse outline. See General Syntax for Attribute Options for the syntax on using a style-element and Line Options for available line-options.
Default:
  • For non-grouped data, the GraphDataDefault style element.
  • For grouped data, the GraphData1 - GraphDataN style elements.
XAXIS=X | X2
specifies whether data are mapped to the primary X (bottom) axis or to the secondary X2 (top) axis.
Default: X
Restriction: Another plot that establishes a data range for the designed axis must be included.
Interaction: The overall plot specification and the layout type determine the axis display. For more information, see How Axis Features are Determined.
YAXIS=Y | Y2
specifies whether data are mapped to the primary Y (left) axis or to the secondary Y2 (right) axis.
Default: Y
Restriction: Another plot that establishes a data range for the designed axis must be included.
Interaction: The overall plot specification and the layout type determine the axis display. For more information, see How Axis Features are Determined.