Abstracts for STAT 303 Grand Finale Lectures

April 18, 2023
 Bharat N. Anand
Vice Provost for Advances in Learning at Harvard University and the Henry R. Byers Professor of Business Administration at Harvard Business School

In this talk I will offer a perspective on how, and why, digital technologies have shaped pedagogy and the practice of teaching over the last decade at Harvard, and what this means for the future. Specifically, I will examine: Where can digital technologies reshape education and where has their value been overestimated? What are the enablers of organizational innovation in a university setting? How is teaching and learning likely to evolve in the future, at and beyond Harvard?

------

April 26, 2022
Kelly McConville
Senior Lecturer in the Department of Statistics

For survey statistics practitioners, it sometimes feels like the sky is falling.  Response rates are declining.  Data collection costs are increasing.  Federal budgets are shrinking.  For survey statistics researchers, the sky isn’t falling but is raining exciting, new data sources and modeling techniques.  In this talk, I will present one modern, but cautious, approach to survey estimation where predictive models link survey data with additional data sources.   Drawing on my collaborations with the U.S. Bureau of Labor Statistics and the U.S. Forest Inventory and Analysis Program, we will explore the performance of this approach and consider some lessons learned.  I will close out with thoughts on what makes a good statistics talk.

------

April 26, 2021
Joseph Blitzstein
Professor of the Practice in the Department of Statistics

-----

April 25, 2017
Shigehisa Kuriyama
Chair of the Department of East Asian Languages and Civilizations and a Harvard College Professor
"Magic Lessons: Communication as the Art of Illusion"
I propose, in this lecture, to relate the art of presentation to the art of close-up magic. My aim is protreptic: I shall urge that performance magic deserves our attention, not only for its useful lessons on how to communicate more effectively, but also for its surprisingly deep insights into how human beings relate to each other and to the world.

------

April 26, 2016
Roger B. Porter
IBM Professor of Business and Government, Harvard University
"Presidential Decision Making: How Decisions Are Made in the White House"
U.S. presidents must constantly make decisions on issues about which they are not expert. Accordingly, they must rely on others for information, analysis, options, assessments, and recommendations. How presidents approach this challenge has varied widely. Examining the decision making processes used by presidents reveals much about the factors that can contribute to producing informed decisions that are successfully implemented.

------

April 28, 2015
Homi Bhabha
Anne F. Rothenberg Professor of the Humanities, Director of the Mahindra Humanities Center, Harvard University
"On Trying Not to Re-invent the Wheel"
My lecture will attempt to raise questions about the pedagogical and cultural value of the Humanities. I will engage with literary texts and cultural issues to elaborate on practices of interpretation, judgment, memory and ethics associated with humanistic learning and teaching.

------

April 22, 2014
Karen Thornber
Professor of Comparative Literature, Professor of East Asian Languages and Civilizations, Harvard University
"Literature and Health: Statistics, Stigmas, Struggles"
Drawing from my current book project - Global World Literature and Health: Moderating Expectations, Generating Possibilities - I explore in this presentation some ways in which literature from Asia, Africa, and the Americas has grappled with the fraught relationships societies have had with the data surrounding disease, everything from ignoring data when embracing it would alleviate suffering, and embracing data when putting it into greater perspective would alleviate suffering.

------

April 23, 2013
Alyssa Goodman
Professor of Astronomy, Harvard University
"Seeing More in Data"
Some scientists still think that good data visualization is only necessary when presenting work to "the public". In truth, thinking hard about how to learn the most from any data set should always involve some form of graph, map, chart, or other visual statistical display. This talk will demonstrate how visualization techniques that include so-called "linked views" offer new insights to researchers visualizing large and/or diverse data sets. In particular, the talk will highlight a few high-dimensional visualization examples where ideas about linked views first put forth by John Tukey are extended beyond two-dimensional displays and point clouds. Examples will be principally drawn from astronomy and medical imaging, and software highlighted will include the Universe Information System known as "WorldWide Telescope" (worldwidetelescope.org) and a new python-based linked-view system called "Glue" (glueviz.org).

------

April 16, 2012
Harry R. Lewis
Gordon McKay Professor of Computer Science (Harvard School of Engineering and Applied Sciences), Harvard University
"Pedagogical Full Circle"
For decades my lectures kept getting better, my enrollments kept going up, and the number of warm bodies in the lecture hall kept going down. I have gone to the opposite extreme in my new course, CS 20, "Discrete Mathematics for Computer Science." Attendance is mandatory. We meet MWF 10-11, and at every class, starting on day one, we assign homework due at the next class. Problem sets are not accepted after 10:15am. Students must do reading before each class, and watch a 15-minute video mini-lecture on the topic of the day. Then the entire class hour is spent with the students broken up into groups of four around small tables, solving problems and writing the solutions on their whiteboards. The course staff wanders around, prompting, correcting, challenging, and calling on the most insecure member of the group to explain its solution. I gather that pedagogical pros call this "Active Learning," though it’s more familiar to me as the way they teach kindergarten.

The results? Typical comments from the midterm questionnaire: "I've found this to be the most helpful teaching method at Harvard." "In-class problem solving is the best. More courses should be taught this way." "Oh my goodness, the in-class problem solving is beautiful! We need more of it." I will share my experience teaching CS 20, and try to report whether anyone is learning anything.

------

April 25, 2011
Judith D. Singer
James Bryant Conant Professor of Education (Harvard Graduate School of Education), Senior Vice Provost for Faculty Development and Diversity, Harvard University
"Anatomy of a Successful Applied Statistics Course: Lessons from 25 Years of Teaching"
You're getting a PhD in statistics because you love the subject. But many of your future students -- at Harvard or elsewhere -- will take your classes because they either need to or are required to do so. So what "works" for you (pedagogically speaking) is unlikely to work for them. In this session, we'll illustrate a variety of strategies for engaging these kinds of students in an applied regression course (non-calculus based) that I've taught for over 25 years at the Harvard Graduate School of Education. Lessons to be discussed include the benefits of: "hooking students in" using real relevant data (the more controversial, the better); adopting a "cognitive apprenticeship" approach that helps students learn to "think like a statistician;" developing perspective-taking skills that allow you to appreciate your students' "zone of proximal development;" promoting active, peer-to-peer and small group learning; and devising authentic assessments that evaluate students on how well they can use what they've learned (not how well they can reproduce it).

------

April 26, 2010
Eric Mazur
Balkanski Professor of Physics and of Applied Physics, Harvard University
"Confessions of a Converted Lecturer"
I thought I was a good teacher until I discovered my students were just memorizing information rather than learning to understand the material. Who was to blame? The students? The material? I will explain how I came to the agonizing conclusion that the culprit was neither of these. It was my teaching that caused students to fail! I will show how I have adjusted my approach to teaching and how it has improved my students' performance significantly.

------

April 27, 2009
Allan Brandt
Amalie Moses Kass Professor of the History of Medicine (Harvard Medical School), Professor of the History of Science, Harvard University
"The Tobacco Pandemic: History, Culture, and Science"
The lecture will examine the historical and cultural forces that led to an epidemic of tobacco-related disease in the twentieth century. It will also assess the rise of new strategies for epidemiological and statistical inference that resulted in causal understanding of the substantial harms of smoking. Finally, the lecture will evaluate the ongoing impact of smoking on health in a global perspective.

------

April 28, 2008
Robert A. Lue
Director of Life Sciences Education, Professor of Molecular and Cellular Biology, Harvard University
"Transforming the Freshman Curriculum in the Life Sciences"
Despite the explosive growth of the life sciences in the past several decades, the way that we introduce students to these fields has not changed for more than 30 years. It is therefore unsurprising that today's inter-connected world challenges our traditional modes of teaching science in separate bins. This talk will focus on recent efforts to re-imagine a foundational experience of science that better reflects where we are today while preparing our students for the future.

------

April 30, 2007
Benedict H. Gross
George Vasmer Leverett Professor of Mathematics, Harvard University
"Archimedes and the Area of the Circle"
In this talk, we describe two great results of Archimedes, which appear in his paper "On the measurement of the circle." The first states that a circle of radius r has the same area as a right triangle, whose base is the circumference C and whose height is the radius r. In modern notation, this says that if π is the constant defined by the equality C = 2 π r, then the area A is given by the formula A = π r 2. He proves this result by the method of exhaustion. The second is Archimedes' estimate for the constant π : 3 10⁄71 < π < 3 1⁄7.

------

May 1, 2006
Peter K. Bol
Charles H. Carswell Professor of East Asian Languages and Civilizations, Harvard College Professor, Harvard University
"Spatial Ontologies in China's Past"
The challenge for an historical GIS for China is to provide a means of representing historical data with spatial attributes in a manner that reflects the operative conceptualization of space and place when the data was collected. The problem is that spatial ontologies are not constant, either across civilizations or through time. The lecture will take up this problem with reference to the last 2000 years of China's history and the China Historical GIS project.