SED navigation bar go to SED home page go to Dataplot home page go to NIST home page SED Home Page SED Staff SED Projects SED Products and Publications Search SED Pages
Dataplot Vol 1 Vol 2

BOX COX LINEARITY PLOT

Name:
    BOX-COX LINEARITY PLOT
Type:
    Graphics Command
Purpose:
    Generates a Box-Cox Linearity Plot.
Description:
    A Box-Cox linearity plot is a graphical technique for determining the Box-Cox transformation that yields the maximum correlation between two variables. Specifically, the correlation between (y,T(x)) where

      \( T_{x} = \frac{x^{\lambda}}{\lambda} \)

    is essentially the power-transformation family (adjusted to include log transformations).

    The horizontal axis is the lambda parameter. The vertical axis is the computed correlation coefficient between <y> and the transformed <x> The lambda corresponding to the highest correlation is the appropriate transformation to use in linearizing the relationship between <y> and <x>

Syntax 1:
    BOX-COX LINEARITY PLOT <y> <x>
                            <SUBSET/EXCEPT/FOR qualification>
    where <y> is the first response variable;
                <x> is the second response variable;
    and where the <SUBSET/EXCEPT/FOR qualification> is optional.
Syntax 2:
    REPLICATED BOX-COX LINEARITY PLOT <y> <x> <tag1>
                            <SUBSET/EXCEPT/FOR qualification>
    where <y> is the first response variable;
                <x> is the second response variable;
                <tag1> is a group-id variable;
    and where the <SUBSET/EXCEPT/FOR qualification> is optional.

    A Box-Cox linearity plot will be generated for each distinct value of the group-id variable. These plots will be overlaid on the same plot.

Syntax 3:
    REPLICATED BOX-COX LINEARITY PLOT <y> <x> <tag1> <tag2>
                            <SUBSET/EXCEPT/FOR qualification>
    where <y> is the first response variable;
                <x> is the second response variable;
                <tag1> is a group-id variable;
                <tag2> is a group-id variable; and where the <SUBSET/EXCEPT/FOR qualification> is optional.

    The two group-id variables are cross-tabulated and a Box-Cox linearity plot will be generated for each distinct combination of values for the group-id variables. These plots will be overlaid on the same plot.

Examples:
    BOX-COX LINEARITY PLOT Y X
    REPLICATED BOX-COX LINEARITY PLOT Y X TAG
Note:
    The number of observations in the two response variables (and any group-id variables) must be equal.
Note:
    The TO syntax is supported for the BOX COX LINEARITY command.
Default:
    None
Synonyms:
    BOX COX LINEARITY PLOT
Related Commands: References: Applications:
    Exploratory Data Analysis
Implementation Date:
    Pre-1987
    2010/5: Support for REPLICATION option
Program 1:
     
    SKIP 25
    READ BERGER1.DAT Y X
    LABEL CASE ASIS
    Y1LABEL Correlation
    X1LABEL Lambda
    BOX COX LINEARITY PLOT Y X
        
    plot generated by sample program
Program 2:
     
    title case asis
    title offset 2
    title automatic
    label case asis
    multiplot corner coordinates 0 0 100 95
    tic mark offset units screen
    y1tic mark offset 2 0
    .
    reset data
    skip 25
    read nelson.dat y x tag
    .
    replicated box cox linearity plot y x tag
        
    plot generated by sample program
Date created: 11/30/2010
Last updated: 12/04/2023

Please email comments on this WWW page to alan.heckert@nist.gov.