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 2 Auxiliary Chapter

NORMXPPF

Name:
    NORMXPPF (LET)
Type:
    Library Function
Purpose:
    Compute the percent point function of a mixture of two normal distributions.
Description:
    The normal mixture distribution has the following cumulative distribution function:

      F(x,u1,sd1,u2,sd2,p)=p*norcdf(u1,sd1) +
 (1-p)*norcdf(u2,sd2)

    where norcdf(u,s) is a normal probability density function with mean u and standard deviation s, p is a real number between 0 and 1 that defines the mixing proportions, and x is a real number.

    The percent point function is the inverse of the cumulative distribution function. That is, given a probability value, it returns the corresponding x value. The percent point function for the mixture of two normal distributions is computed numerically.

Syntax:
    LET <y2> = NORMXPPF(<p>,<u1>,<sd1>, <u2>,<sd2>,<pmix>)
                            <SUBSET/EXCEPT/FOR qualification>
    where <p> is a number, parameter, or variable containing probability values between 0 and 1;
    <u1> is a number, parameter, or variable;
                <sd1> is a number, parameter, or variable;
                <u2> is a number, parameter, or variable;
                <sd2> is a number, parameter, or variable;
                <pmix> is a number, parameter, or variable in the range 0 to 1;
                <y2> is a variable or a parameter (depending on what <p> is) where the computed normal mixture ppf value is stored;
    and where the <SUBSET/EXCEPT/FOR qualification> is optional.
Examples:
    LET A = NORMXPPF(0.95,0,1,10,20,0.2)
    LET A = NORMXPPF(0.90,U1,SD1,U2,SD2,P)
    LET Y = NORMXPPF(P,U1,SD1,U2,SD2,PMIX)
Note:
    You can generate a probability plot for a normal mixture distribution as follows:

      LET U1 = <value>
      LET SD1 = <value>
      LET U2 = <value>
      LET SD2 = <value>
      LET P = <value>
      NORMAL MIXTURE PROBABILITY PLOT Y

    You can generate random numbers from a normal mixture distribution as follows:

      LET U1 = <value>
      LET SD1 = <value>
      LET U2 = <value>
      LET SD2 = <value>
      LET P = <value>
      LET Y = NORMAL MIXTURE RANDOM NUMBERS FOR I = 1 1 1000
Default:
    None
Synonyms:
    None
Related Commands:
    NORMXPDF = Compute the normal mixture probability density function.
    NORMXCDF = Compute the normal mixture cumulative distribution function.
    NORCDF = Compute the normal cumulative distribution function.
    NORPDF = Compute the normal probability density function.
    NORPPF = Compute the normal percent point function.
Reference:
    "Continuous Univariate Distributions: Volume 1", Johnson, Kotz, and Balakrishnan, John Wiley and Sons, 1994.
Applications:
    Distributional Modeling
Implementation Date:
    1998/5
Program:
    MULTIPLOT 2 2
    MULTIPLOT CORNER COORDINATES 5 5 95 95
    YLIMITS -5 15
    XLIMITS 0 1
    MAJOR XTIC MARK NUMBER 6
    MINOR XTIC MARK NUMBER 1
    LET U1 = 0
    LET SD1 = 1
    LET U2 = 5
    LET SD2 = 3
    TITLE P = 0.2
    PLOT NORMXPPF(P,U1,SD1,U2,SD2,0.2) FOR P = 0.01 0.01 0.99
    TITLE P = 0.4
    PLOT NORMXPPF(P,U1,SD1,U2,SD2,0.4) FOR P = 0.01 0.01 0.99
    TITLE P = 0.6
    PLOT NORMXPPF(P,U1,SD1,U2,SD2,0.6) FOR P = 0.01 0.01 0.99
    TITLE P = 0.8
    PLOT NORMXPPF(P,U1,SD1,U2,SD2,0.8) FOR P = 0.01 0.01 0.99
    END OF MULTIPLOT

    plot generated by sample program

Date created: 6/5/2001
Last updated: 4/4/2003
Please email comments on this WWW page to alan.heckert@nist.gov.