Logarithm of Cumulative Distribution Function

Laplace distribution logarithm of cumulative distribution function.

The cumulative distribution function for a Laplace random variable is

upper F left-parenthesis x semicolon mu comma b right-parenthesis equals one half plus one half s g n left-parenthesis x minus mu right-parenthesis left-parenthesis 1 minus exp left-parenthesis minus StartFraction StartAbsoluteValue x minus mu EndAbsoluteValue Over b EndFraction right-parenthesis right-parenthesis

where mu is the location parameter and b > 0 is the scale parameter.

Usage

var logcdf = require( '@stdlib/stats/base/dists/laplace/logcdf' );

logcdf( x, mu, b )

Evaluates the logarithm of the cumulative distribution function (CDF) for a Laplace distribution with parameters mu (location parameter) and b > 0 (scale parameter).

var y = logcdf( 2.0, 0.0, 1.0 );
// returns ~-0.07

y = logcdf( 5.0, 10.0, 3.0 );
// returns ~-2.36

If provided NaN as any argument, the function returns NaN.

var y = logcdf( NaN, 0.0, 1.0 );
// returns NaN

y = logcdf( 0.0, NaN, 1.0 );
// returns NaN

y = logcdf( 0.0, 0.0, NaN );
// returns NaN

If provided b <= 0, the function returns NaN.

var y = logcdf( 2.0, 0.0, -1.0 );
// returns NaN

y = logcdf( 2.0, 0.0, 0.0 );
// returns NaN

logcdf.factory( mu, b )

Returns a function for evaluating the logarithm of the cumulative distribution function of a Laplace distribution with parameters mu (location parameter) and b > 0 (scale parameter).

var mylogcdf = logcdf.factory( 3.0, 1.5 );

var y = mylogcdf( 1.0 );
// returns ~-2.026

y = mylogcdf( 4.0 );
// returns ~-0.297

Notes

  • In virtually all cases, using the logpdf or logcdf functions is preferable to manually computing the logarithm of the pdf or cdf, respectively, since the latter is prone to overflow and underflow.

Examples

var randu = require( '@stdlib/random/base/randu' );
var logcdf = require( '@stdlib/stats/base/dists/laplace/logcdf' );

var mu;
var b;
var x;
var y;
var i;

for ( i = 0; i < 100; i++ ) {
    x = randu() * 10.0;
    mu = randu() * 10.0;
    b = randu() * 10.0;
    y = logcdf( x, mu, b );
    console.log( 'x: %d, µ: %d, b: %d, ln(F(x;µ,b)): %d', x.toFixed( 4 ), mu.toFixed( 4 ), b.toFixed( 4 ), y.toFixed( 4 ) );
}
Did you find this page helpful?