Dataplot Vol 2 Vol 1

# WINSORIZED CORRELATION

Name:
WINSORIZED CORRELATION (LET)
Type:
Let Subcommand
Purpose:
Compute the Winsorized correlation of a variable.
Description:
The standard correlation estimate can be heavily influenced by extreme values. The Winsorized correlation compensates for this by setting the tail values equal to a certain percentile value. For example, for a 90% Winsorized correlation, the bottom 5% of the values are set equal to the value corresponding to the 5th percentile while the upper 5% of the values are set equal to the value corresponding to the 95th percentile. Then the standard correlation formula (HELP CORRELATION for details) is applied.
Syntax:
LET <par> = WINSORIZED CORRELATION <y1> <y2>        <SUBSET/EXCEPT/FOR qualification>
where <y1> is the first response variable;
<y2> is the second response variable;
<par> is a parameter where the computed Winsorized correlation is stored;
and where the <SUBSET/EXCEPT/FOR qualification> is optional.
Examples:
LET A = WINSORIZED CORRELATION Y1 Y2
LET A = WINSORIZED CORRELATION Y1 Y2 SUBSET TAG > 2
Note:
The analyst must specify the percentages to Winsorize in each tail. This is done by defining the internal variables P1 (the lower tail) and P2 (the upper tail). For example, to Winsorize 10% of each tail, do the following:

LET P1 = 10
LET P2 = 10
LET A = WINSORIZED CORRELATION Y1 Y2
Note:
Support for the Winsorized correlation has been added to the following plots and commands:

WINSORIZED CORRELATION PLOT
BOOTSTRAP WINSORIZED CORRELATION PLOT
JACKNIFE WINSORIZED CORRELATION PLOT
CROSS TABULATE WINSORIZED CORRELATION PLOT
WINSORIZED CORRELATION INTERACTION STATISTIC PLOT

In addition, the command

SET CORRELATION TYPE WINSOR

can be used to specify that the command

LET C = CORRELATION MATRIX M

generates Winsorized correlations for a matrix (instead of the standard correlation coefficient normally generated).

Default:
None
Synonyms:
None
Related Commands:
 WINSORIZE = Winsorize a variable. WINSORIZED STANDARD DEVIATION = Compute a Winsorized standard deviation. WINSORIZED MEAN = Compute a Winsorized mean. WINSORIZED VARIANCE = Compute a Winsorized covariance. WINSORIZED COVARIANCE = Compute a Winsorized covariance. VARIANCE = Compute the variance. BIWEIGHT MIDCOVARIANCE = Compute the biweight midcovariance.
Applications:
Robust Data Analysis
Implementation Date:
7/2002
Program:
```DIMENSION 20 COLUMNS
SKIP 25
COLUMN LIMITS 20 80
READ AUTO79.DAT Y1 TO Y12
LET A1 = CORRELATION Y1 Y2
LET A2 = WINSORIZED CORRELATION Y1 Y2
```

Date created: 7/22/2002
Last updated: 4/4/2003
Please email comments on this WWW page to alan.heckert@nist.gov.