Posts Tagged ‘critical thinking’

In the last semester at Berkeley, I worked as a Graduate Student Instructor (GSI, the name for teaching assistant in the UC system). The course was an undergraduate intro statistics class and the instructor is David Freedman. When I got his email asking me to be his TA, I had no choice except agreeing. In my advisor’s words, “When he asks someone to be his TA, treat it as an honor and just do it.”

When David passed away in October 2008 at age 70, the press release from Berkeley noted:

“Freedman’s transition from being a mathematical statistician to a creative practitioner of applied statistics occurred in part, by his own account, in response to the challenges of undergraduate teaching on the UC Berkeley campus,” Collier said. “His students were bored with statistics courses and with the abstracted examples that were standard fare in textbooks,” leading Freedman to dig up practical examples in many applied areas. [……]

He wrote six textbooks, including the highly regarded undergraduate text, “Statistics,” with co-authors Robert Pisani and Roger Purves, now in its fourth edition. The book is “a widely used undergraduate textbook, crystal clear, a delight to read and to teach from, broad, deep and meticulously accurate in every detail,” Stark said. “It transformed the way many people taught statistics from a formula-driven, plug-in-the-numbers approach to a focus on critical thinking.”

At first, it seemed strange that he insisted me to attend all his lectures. Being a TA, I have never been required to attend the lecture. Sometimes, you just got to do what you were told to do :). I went to his lectures every time and I had to admit at the end that I learned things I have never thought about. He had constantly drawn straightforward but misled conclusions from data and challenged the students to criticize his arguments. You almost never knew he is telling you what to believe or what not to believe before he turned the face of the card. However, he always gave a convincing concluding remark to summarize the whole discussion. It is fascinating to see critical thinking in full display.

I clearly remember two pieces of advises he gave me during that semester. When I asked him for advise on job interviews before I went on to my first one, he told me, “Look, I’m a famous statistician. However, I know nothing about what you are doing. When you gave the talk, you are the most knowledgeable person on these topics in the room. Just tell your story and be yourself. If they like you, they will hire you. If they don’t, there is nothing you can do and nothing to worry about.” His words gave me confidence to behave just like myself without worrying.

He offered me another piece of advisor after we finished grading the finals in his house. As I was walking towards the door, I somehow felt emotional and wanted to say a few words to him. I wanted to thank him for his support and guidance. He looked calmly and told me, “Just do what you feel right to do, and don’t look around.” It was the last time I talked to him. Very often, I feel I owe him so much. I cannot pay anything back to him and the best I can do is passing what I learned from him to others. This is the main reason why I’m writing these blog posts — it just feels right.

Read Full Post »

Just suit up for the first time since the job interview season of Winter 2005. As one of those who got promoted this year, I attended the Faculty Recognition Program today and got a chance to look closely at the book, “Statistical Models, Theory and Practice” by David A. Freedman, that I “donated” (the university is paying for it) to the library. I’m honored to be able to pay my tribute to him, who open my world of useful statistics.

The firs time I met David was when I took his applied statistic class at Berkeley. At that time, I passed my Ph.D. qualify exam, started with some research projects and felt like I knew Statistics. In his class, I learned quickly that I knew NOTHING about Statistics except some abstract mathematical symbols.

The first meeting of the class was the most wield period I have sit thought as a student. Several days before the first class, every student got his email in which a list of three papers were assigned for reading. We were good students so we all read the paper carefully, I assume at least. Then here came the first meeting of the class. David came in and explained several things about the course structures before we went to the more serious business, paper discussion.

The discussion started like this. He calmly sit in a chair and asked “questions?”. Silence, …, silence, …, and longer silence. We had not expected that we were supposed to “initiate” the discussion instead of “participating”. Then he asked gain, “questions on the paper?”. We just sit there for more than 10 minutes, flipping through papers  and trying to find a meaning question to ask. Seems like we would sit there forever if we did not come up with any questions. It felt like the longest class I have ever taken.

The format of the class kept the same way for the whole semester. Students first read the assigned papers and come up with questions about anything and everything about the paper. David entertained every question. The questions ranges from “why have the authors picked this model?” to “why have the authors NOT picked that model?”, from “Does the model fit the data well?” Do the data support the model at all?”, from “Does the evidence support the conclusion?” to “Is the evidence related to the conclusion?”. The interesting part is that about one third of the papers we discussed were written by him. We have to (at least try to) criticize the paper and he enjoys doing do as well. Sometime he would defend the paper for while and then add his own critics.

Trying to recall what I have learned from the class, the most striking thing is that I cannot remember what models or methods we went over (there are a lot of them). I have to admit that I have a really bad memory. At the same time, I do remember one thing: Check the model assumptions and check them again and again.

In an age of having so much computation power and advanced software packages to run almost any analysis in a short period time, our ability in drawing proper conclusion from data through mathematical inference is not necessarily improved unless we carefully check if we are using the right tools to answer the right questions. Thinking critically about each step of any analysis is the key to a proper conclusion. This is the first lesson I learned from David.

[To be continued ……]

Read Full Post »