Best probability density function for random sampled data

DOI10.3390/E11041001MaRDI QIDQ845443zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Donald J. Jacobs

Publication date 29 January 2010

Published in Entropy (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3390/e11041001

zbMATH Keywords

adaptive simulated annealingLagrange multipliersleast squares errorlevel-function momentsmaximum entropy methodprobability density functionsmoothing noise

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Exact distribution theory in statistics (62E15) Statistical distribution theory (62E99)

Review text

Summary: The maximum entropy method is a theoretically sound approach to construct an analytical form for the probability density function (pdf) given a sample of random events. In practice, numerical methods employed to determine the appropriate Lagrange multipliers associated with a set of moments are generally unstable in the presence of noise due to limited sampling. A robust method is presented that always returns the best pdf, where tradeoff in smoothing a highly varying function due to noise can be controlled. An unconventional adaptive simulated annealing technique, called funnel diffusion, determines expansion coefficients for Chebyshev polynomials in the exponential function.

Recommendations

• Efficient evaluation of the pdf of a random variable through the kernel density maximum entropy approach
• Estimation and optimization of MLE maximum entropy probability density
• Approximation of probability density functions by the multilevel Monte Carlo maximum entropy method
• Efficient numerical approximation of maximum entropy estimates
• Density reconstructions with errors in the data

Cites work

• A statistical minimax approach to the Hausdorff moment problem
• An information theoretical approach to inversion problems
• Hausdorff moment problem and maximum entropy: A unified approach
• Hausdorff moment problem via fractional moments
• Hausdorff moment problem: reconstruction of probability density functions
• scientific article; zbMATH DE number 1082203 (Why is no real title available?)
• Information Theory and Statistical Mechanics
• Numerical aspects of finite Hausdorff moment problem by maximum entropy approach
• Quantifying predictability through information theory: small sample estimation in a non-Gaussian framework
• The maximum entropy method
• Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems

Cited in

(3)

• Efficient evaluation of the pdf of a random variable through the kernel density maximum entropy approach
• Experimental modelling of physical laws
• Kernel density maximum entropy method with generalized moments for evaluating probability distributions, including tails, from a small sample of data

This page was built for publication: Best probability density function for random sampled data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q845443)