All Downloads are FREE. Search and download functionalities are using the official Maven repository.

smile.stat.distribution.LogisticDistribution Maven / Gradle / Ivy

There is a newer version: 2.6.0
Show newest version
/******************************************************************************
 *                   Confidential Proprietary                                 *
 *         (c) Copyright Haifeng Li 2011, All Rights Reserved                 *
 ******************************************************************************/
package smile.stat.distribution;

import smile.math.Math;

/**
 * The logistic distribution is a continuous probability distribution whose
 * cumulative distribution function is the logistic function, which appears
 * in logistic regression and feedforward neural networks. It resembles
 * the normal distribution in shape but has heavier tails (higher kurtosis).
 * 

* The cumulative distribution function of the logistic distribution is given by: *

 *                   1
 * F(x; μ,s) = -------------
 *              1 + e-(x-μ)/s
 * 
* The probability density function of the logistic distribution is given by: *
 *                  e-(x-μ)/s
 * f(x; μ,s) = -----------------
 *              s(1 + e-(x-μ)/s)2
 * 
*

* The logistic distribution and the S-shaped pattern that results from it * have been extensively used in many different areas such as: *

    *
  • Biology - to describe how species populations grow in competition. *
  • Epidemiology - to describe the spreading of epidemics. *
  • Psychology - to describe learning. *
  • Technology - to describe how new technologies diffuse and substitute * for each other. *
  • Market - the diffusion of new-product sales. *
  • Energy - the diffusion and substitution of primary energy sources. *
* * @author Haifeng Li */ public class LogisticDistribution extends AbstractDistribution { private static final double PI_SQRT3 = Math.PI / Math.sqrt(3); private static final double PI2_3 = Math.PI * Math.PI / 3; private double mu; private double scale; /** * Constructor. */ LogisticDistribution(double mu, double scale) { if (scale <= 0.0) { throw new IllegalArgumentException("Invalid scale: " + scale); } this.mu = mu; this.scale = scale; } @Override public int npara() { return 2; } @Override public double mean() { return mu; } @Override public double var() { return PI2_3 * scale * scale; } @Override public double sd() { return PI_SQRT3 * scale; } @Override public double entropy() { return Math.log(scale) + 2; } @Override public String toString() { return String.format("Logistic Distribution(%.4f, %.4f)", mu, scale); } @Override public double rand() { return inverseTransformSampling(); } @Override public double p(double x) { double e = Math.exp(-(x - mu) / scale); return e / (scale * (1.0 + e) * (1.0 + e)); } @Override public double logp(double x) { return Math.log(p(x)); } @Override public double cdf(double x) { double e = Math.exp(-(x - mu) / scale); return 1.0 / (1.0 + e); } @Override public double quantile(double p) { if (p < 0.0 || p > 1.0) { throw new IllegalArgumentException(); } return mu + scale * Math.log(p / (1.0 - p)); } }




© 2015 - 2024 Weber Informatics LLC | Privacy Policy