Author's profile

Maria Dolores Martinez Miranda
University of Granada, Spain

Background

Author articles

  • Once widely used in construction, asbestos is known to cause several deadly diseases including the rare form of cancer known as Mesothelioma. Due to its long latency period and poor records of exposure, the number of cases of this disease is difficult to predict. This research compares two established methods of projection in order to determine which is more effective.

    12/11/2015 | 2,157
  • Our previous academic research into Double Chain Ladder demonstrated how the classical chain ladder technique can be broken down into separate components. In this paper, we continue our investigation of the double chain ladder, and illustrate a simple way to include prior knowledge of severity inflation and future zero claims into the framework of the model.

    13/05/2013 | 5,619
  • Kernel density estimation for truncated and censored data has not been widely studied. This in spite of the fact that survival data is omnipresent in statistical applications and the fact that the density still is one of the fundamental building blocks while constructing mathematical statistical models.

    In this paper the researchers develop cross-validation for this class of density estimators and show that the recent independent identical distributed double-crossvalidation method of Mammen, Martinez-Miranda, Nielsen and Sperlich (2011) works well also in this more general context.

    14/01/2013 | 5,115