Week of April 5 - 9

Monday, April 5

 2:30 GROUPS AND GEOMETRIES SEMINAR  - Room 459 MSC
      Sergey Shpectorov, Mathematics and Statistics, BGSU 
      "Orthogonal and symplectic groups and geometries"

 3:30 ANALYSIS SEMINAR  - Room 459 MSC
      Rebecca Sanders, Mathematics and Statistics, BGSU 
      "Salas' results on hypercyclic bilateral shifts"

Tuesday, April 6

 4:00 STATISTICS SEMINAR  - Room 459 MSC
      Gabor Szekely, Mathematics and Statistics, BGSU 
      "A unified approach for some non-parametric tests"

Wednesday, April 7

 2:30 GROUPS AND GEOMETRIES SEMINAR  - Room 459 MSC
      Sergey Shpectorov, Mathematics and Statistics, BGSU
      "Orthogonal and symplectic groups and geometries"
                                                             
 3:30 ALGEBRA SEMINAR  - Room 459 MSC
      To be announced; check the department's web page.

 3:30 STATISTICS SEMINAR  - Room 304 MSC **** Note room ****
      G. P. Patil, Distinguished Lukacs Professor, BGSU
      C. Taillie, Senior Research Associate 
      Senin Banga, Graduate Research Assistant 
      Center for Statistical Ecology and Environmental Statistics,
      Department of Statistics, Penn State University
      "Statistical issues related to the implementation of benchmark
       dose method"
      Abstract: The seminar(s) will discuss the following and related
        problems of mathematical and computational statistics:

        Develop likelihood-based procedures for calculating
        confidence limits on risk function and effective dose
        (benchmark dose, BMD) for continuous responses with emphasis
        on skew (nonnormal) distributed responses. Assess the
        sensitivity to model mis-specification.  Examine the
        statistical validity of BMD-determination by inversion of an
        upper confidence curve on the risk function.
  
        A benchmark dose (BMD) for continuous responses may be defined
        as a lower confidence limit on the effective dose
        corresponding to a specified risk level r. However,
        calculating such a confidence limit is not straightforward.
        By contrast, it is technically easier to obtain confidence
        limits on the risk function R(d).  One approach that has been
        suggested for BMD-determination is to first obtain a pointwise
        upper confidence curve U(d) on the risk function and then to
        invert this relationship by solving the equation U(d)=r.  The
        solution d is purported to be the desired BMD, i.e., a lower
        confidence limit on the effective dose corresponding to the
        risk level r.

      Background: The current approach to risk assessment for toxic
        noncarcinogenic chemicals is based on the assumption that
        there exists a threshold below which no adverse noncancer
        health effects are expected under lifetime exposure.  Various
        regulatory agencies estimate a ``safe'' exposure by first
        determining an exposure level which has been shown to cause no
        adverse effect in animals or humans and then apply
        ``uncertainty'' factors to account for missing information.

        Problems were identified with this methodology shortly after
        it was adopted some 30 years ago.  The risk assessment
        community has been searching for improved methods since that
        time.  One suggestion that has received a great deal of
        attention is to base the methodology on dose-response
        modeling.  The idea is to estimate the effective dose (ED)
        that causes some critical effect in a specified percentage of
        the test animals (e.g., $ED_{05}$ or $ED_{10}$) and then to
        designate the lower confidence limit for the effective dose as
        the ``benchmark dose.''  This benchmark dose may then be
        adjusted by uncertainty factors to arrive at the reference
        dose (RfD) or reference concentration (RfC).

        In spite of the fact that it is generally agreed that the
        benchmark dose method addresses many of the shortcomings of
        the current methodology, more than a decade has passed since
        the benchmark dose method was suggested as an alternative.
        One reason for this delay is that there are a number of
        difficult statistical issues remaining.  While the potential
        benefits have been recognized, risk assessors have been
        understandably reluctant to adopt a methodology which is not
        yet completely understood.

Thursday, April 8

 4:00 STATISTICS SEMINAR  - Room 459 MSC
      G. P. Patil, Distinguished Lukacs Professor, BGSU
      "Statistical issues related to the implementation of benchmark
       dose method"
      Continuation of Wednesday's seminar; see above
      
Friday, April 9

 3:30 Refreshments
 3:45 Department of Mathematics and Statistics and
      Department of Applied Statistics and Operations Research
      JOINT COLLOQUIUM  - *** Room 116 Business Administration Building ***
      Dennis K. J. Lin, Pennsylvania State University
      "Designing computer experiments"
      Abstract: Computer models/simulations can describe complicated
        physical phenomena, such as performance characteristics of
        integrated circuits.  However, to use these models for
        scientific investigation, their generally running times and
        mostly deterministic nature require a special designed
        experiments.  Standard factorial designs are inadequate; in
        the absence of one or more main effects, their replication
        cannot be used to estimate error but instead produces
        redundancy.  A number of alternative designs have been
        proposed, but many can be burdensome computationally.  This
        paper presents a new class of designs developed from the
        rotation of a factorial design.  These rotated factorial
        designs are very easy to construct and preserve many of the
        attractive properties of standard factorial designs: they have
        equally-spaced projections to univariate dimensions and
        uncorrelated regression effect estimates (orthogonality).
        They also rate comparably to maximin Latin hypercube designs
        by the minimum interpoint distance criterion used in the
        latter's construction.

      About the speaker: Dr. Dennis Lin is a Professor of Management
        Science and Statistics at the Penn State University.  His
        research interests are quality engineering, industrial
        statistics (design of experiment, reliability, statistical
        process control, quality assurance) and response surface.  He
        has published more than 50 papers in a wide variety of
        journals, including Technometrics, Journal of the Royal
        Statistical Society, Ser. C., Journal of Quality Technology,
        and IEEE Transactions on Reliability.  Currently, he serves as
        managing editor for Statistics Sinica; associate editor for
        The American Statistician and Journal of Quality Technology;
        and on the Applied Statistics Committee for the American
        Statistical Association.  Dr. Lin is an elected fellow of the
        American Statistical Association (ASA), an elected member of
        the International Statistical Institute (ISI), a senior member
        of the American Society for Quality (ASQ), a lifetime member
        of the International Chinese Statistical Association (ICSA), a
        fellow of the Royal Statistical Society, and has received the
        Most Outstanding Presentation Award from SPES and ASA.

 Midwest Group Theory Conference (tentative schedule)
   See http://www-math.bgsu.edu/~sergey/conference.html for more
   information.
 Room 117 Olscamp Hall

 10:30-11:20 Sasha Ivanov 
 11:30-12:20 Antonio Pasini 

 2:30-3:20 Ernie Shult 
 3:30-4:20 Mark Ronan 
 4:30-4:50 Valery Vermeulen 
 5:00-5:20 Richard Weiss 

Saturday, April 10

 10:00 Spring Swing 99
       Golf scramble organized by BGSU Actuarial Science Society and
         the History Society
       For more information contact Jeff Faber, Actuarial Science
         Society President at jfaber@bgnet.bgsu.edu or 372-1178

 Midwest Group Theory Conference (tentative schedule)
 Room 095 Overman

  9:30-10:20 Michael Aschbacher 
 10:30-11:20 Gernot Stroth 
 11:30-11:50 Alexander Stein 

 2:30-3:20 Ulrich Meierfrankenfeld 
 3:30-4:20 Ron Solomon