Week of November 30 - December 4 

Monday, November 30

12:30 APPLIED MATHEMATICS SEMINAR  - Room 400 MSC

 3:30 ANALYSIS SEMINAR  - Room 459 MSC
      Mihaela Marcusanu, Mathematics and Statistics, BGSU 
      "Universal primitives"

Tuesday, December 1

10:30 ALGEBRA SEMINAR  - Room 459 MSC
      Warren McGovern, Mathematics and Statistics, BGSU 
      "Lattice-ordered groups: hyper-archimedean l-groups"

 3:30 GROUPS AND GEOMETRIES SEMINAR  - Room 459 MSC
      Sergey Shpectorov, Mathematics and Statistics, BGSU 
      "The Leech lattice and Conway groups"

Wednesday, December 2

 2:30 STATISTICS SEMINAR  - Room 459 MSC
      Lisa Cocchi and Diane Conway, Applied Statistics 
        and Operations Research, BGSU

Thursday, December 3

 3:30 GROUPS AND GEOMETRIES SEMINAR  - Room 459 MSC
      Sergey Shpectorov, Mathematics and Statistics, BGSU 
      "The Leech lattice and Conway groups"

Friday, December 4

 3:30 Coffee
 3:45 COLLOQUIUM  - Room 459 MSC
      Edsel Pena, Mathematics and Statistics, BGSU 
      "Time-to-event analysis"
      Abstract: In many studies in the natural and social sciences, in
        biomedical settings, and in engineering/reliability
        situations, the characteristic or variable of interest is the
        time to the occurrence of an event of interest.  Examples of
        such events are death or relapse of patients in biomedical
        studies, breakdown of a marriage in a sociological setting,
        failure of a mechanical/electronic component, first mating of
        organisms in an ecological study, committing a criminal
        offense by a delinquent, acceptance of a manuscript for
        publication, an error in a Tom Wolfe novel, insurance claim in
        an actuarial setting, occurrence of an earthquake in a
        geological investigation, and many others. A statistical
        problem in such situations is to estimate nonparametrically
        the unknown distribution function of the time to occurrence of
        the event on the basis of a possibly incomplete data.

        In this talk, starting from basic probability principles, the
        main ideas behind the modern stochastic process approach to
        the analysis of such time-to-event data will be
        discussed. This modern framework will then be applied to the
        nonparametric estimation of the distribution function of the
        interoccurrence times of events when the event of interest is
        of a recurring type.  This will be illustrated using data from
        a gastroenterology study.