A modified uncertain maximum likelihood estimation with applications in uncertain statistics
Yang Liu, Baoding Liu
Abstract
In uncertain statistics, the uncertain maximum likelihood estimation is a method of estimating the values of unknown parameters of an uncertain statistical model that make the observed data most likely. However, the observed data obtained in practice usually contain outliers. In order to eliminate the influence of outliers when estimating unknown parameters, this article modifies the uncertain maximum likelihood estimation. Following that, the modified uncertain maximum likelihood estimation is applied to uncertain regression analysis, uncertain time series analysis, and uncertain differential equation. Finally, some real-world examples are provided to illustrate the modified uncertain maximum likelihood estimation.
Topics & Concepts
OutlierLikelihood functionMaximum likelihoodStatisticsMathematicsMaximum likelihood sequence estimationEstimation theoryToolboxMarginal likelihoodRestricted maximum likelihoodEstimationExpectation–maximization algorithmEconometricsComputer scienceEconomicsProgramming languageManagementFuzzy Systems and OptimizationMulti-Criteria Decision MakingAdvanced Statistical Methods and Models