Computing Maximum Likelihood Estimators of Convex Density Functions

  • Cahiers de recherche; 1995.16
Publication date1995

e consider the problem of estimating a density function that is known in advance to be convex. The maximum likelihood estimator is then the solution of linearly constrained convex minimization problem. This problem turns out to be numerically difficult. We show that interior point algorithms perform well on this class of optimization problems, though for large samples, numerical difficulties are still encountered. To eliminate those difficulties, we propose a clustering scheme that is reasonable from a statistical point of view. We display results for problems with up to 40000 observations. We also give a typical picture of the estimated density: a piece wise linear function, with very few pieces only

Citation (ISO format)
TERLAKY, T., VIAL, Jean-Philippe. Computing Maximum Likelihood Estimators of Convex Density Functions. 1995
  • PID : unige:5978

Technical informations

Creation04/15/2010 12:21:44 PM
First validation04/15/2010 12:21:44 PM
Update time03/14/2023 3:27:10 PM
Status update03/14/2023 3:27:10 PM
Last indexation01/15/2024 7:47:14 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack