Smith College Applied Statistics Lecture series (2010-2011)

All lectures are free and open to the public. No prior exposure to statistics is assumed.

  1. The Statistics Behind the Scenes at Consumer Reports
    Abbe Herzig, Consumers Union of U.S.; Statistical Program Leader, Consumer Reports Health
    Tuesday October 19, 2010, noon, Burton Forum (3rd floor) (Clark Science Center), lunch provided, please bring your own drink.

    Consumers Union is an independent, nonprofit organization whose mission is to work for a fair, just, and safe marketplace for all consumers and to empower consumers to protect themselves. The organization was founded in 1936 when advertising first flooded the mass media, and so we have just begun our 75th year of this important work. CU publishes Consumer Reports, ConsumerReports.org, and a number of other specialty publications, both in print and online. In 2008, CU also launched ConsumerReportsHealth.org and the Consumer Reports Health Ratings Center, which serve to educate and empower consumers to make more informed health-care decisions and to help change the market. In this presentation, Abbe Herzig will talk about the statistical work that feeds many of the ratings in Consumer Reports and on the health website in particular, drawing examples from her over 20 years of experience as a statistician at Consumer Reports, working on projects as diverse as car road tests and reliability, bicycle helmets, house paint, breakfast cereal, and hospital infection rates.

  2. Developing Statistical Reasoning Using Randomization
    Sandra Madden, Assistant Professor, Department of Teacher Education and Curriculum Studies, University of Massachusetts/Amherst
    Tuesday, November 30, 2010, noon, Burton Forum (3rd floor) (Clark Science Center), lunch provided, please bring your own drink.

    "Comparing distributions" as a big statistical idea was used to design professional development experiences for high school mathematics teachers. Randomization testing and dynamic technological tools were instrumental in the design and implementation of the professional learning experience. In this talk, I'll will introduce randomization testing as enacted in this learning environment and describe the ways in which it was determined that randomization testing was a productive statistical and teaching device.

  3. Tales of Randomness
    Kavita Ramanan, Professor, Applied Mathematics, Brown University
    Tuesday, February 22, 2011, noon, Burton Forum (3rd floor) (Clark Science Center), lunch provided, please bring your own drink.

    This talk will discuss various aspects of randomness, including how it can help, how it can hurt and some elegant mathematical properties that it exhibits.

  4. The Combinatorics of Card Shuffling
    Sami H. Assaf, C. L. E. Moore Instructor, Massachusetts Institute of Technology
    Tuesday, March 1, 2011, noon, Burton Forum (3rd floor) (Clark Science Center), lunch provided, please bring your own drink.

    Ever wonder how many times you should shuffle a deck of cards? Or what really happens if you don't shuffle enough? In this talk, we'll give a simple mathematical model for card shuffling (the Gilbert-Shannon-Reeds model) and show how Bayer and Diaconis used this model to prove that, for a standard deck of 52 cards, you should shuffle about 7 times. We'll also present recent joint work with Diaconis and Soundararajan that shows how the number of times you should shuffle depends on what game you're playing. This talk will involve four decks of cards, three volunteers, two magic tricks and lots of great combinatorics.

  5. Uncovering Changes in Time Series Data
    Stacey Hancock, Assistant Professor, Department of Math and Computer Science
    Tuesday, March 29, 2011, noon, Burton Forum (3rd floor) (Clark Science Center), lunch provided, please bring your own drink.

    Many time series data sets exhibit structural breaks in a variety of ways, the most obvious being a mean level shift. In this case, the mean level of the process is constant over periods of time, jumping to different levels at times called "change-points". These jumps may be due to outside influences such as changes in government policy or manufacturing regulations. Structural breaks may also be a result of changes in variability or changes in the spectrum of the process. The goal is to estimate where these structural breaks occur and to provide a model for the data within each stationary segment.
    One application of change-point analysis is detecting changes in sound waves. In particular, the National Park Service is interested in estimating the proportion of manmade sound in the National Parks. In this talk, we will start with an overview of time series models, then consider the change-point problem applied to sound waves.

Thanks to the Department of Mathematics and Statistics and the Center for Women in Mathematics for support of the series.

Applied Statistics Lecture series (2009-2010)

Other 5 college seminars of interest:
University of Massachusetts Statistics and Probability Seminar Series

University of Massachusetts Biostatistics and Epidemiology Seminar Series

Organized by Nicholas Horton.
Last updated August 16, 2011