Kullback-Leibler information and statistical modeling

prof. Gabriele Soffritti

  • Date:

    05 FEBRUARY
    -
    08 FEBRUARY 2019
     from 11:00 to 13:00

  • Event location: Seminar room

  • Type: Cycle 34 - Mandatory Courses

All dates: Department of Statistics, Via Belle Arti 41, Bologna

Prof. Gabriele Soffritti

Tue  05/02 11:00 - 13:00 a.m. - Seminar Room 1st floor
Wed 06/02 11:00 - 13:00 a.m. - Seminar Room 1st floor
Thu  07/02 11:00 - 13:00 a.m. - Seminar Room 1st floor
Fri    08/02 11:00 - 13:00 a.m - Seminar Room 1st floor

 

Topics

  • Statistical models. Model identification and (mis)specification.
  • Kullback-Leibler information, expected log-likelihood and their estimators.
  • Kullback-Leibler information as a criterion for evaluating statistical models that approximate the true distribution of the data.
  • Asymptotic properties of the maximum likelihood estimator in the presence of model misspecification.

 

References:

S. Konishi and G. Kitagawa (2008). “Information criteria and statistical modeling”. Springer, New York (Chapter 3).
H. White (1982). “Maximum likelihood estimation of misspecified models”. Econometrica, Vol. 50, No. 1. (Jan. 1982), pp. 1-25.