My journey to learn Econometrics

I took my first course in Econometrics in Fall 2005 from Gautam Tripathi. At that point I had taken only one course in statistics and was never exposed to econometric modelling before. Gautam’s class was challenging for me not because I was unable to understand the stat part but because I was not able to visualize the real world significance. I was not able to grasp the intuition behind the different estimation methods, their assumptions, their application etc. I think, it would have helped if I could have spent time reading econometric books, but I had too many other things going on. So when I was done with my comprehensives, I decided to read some econometrics.

Phase 1: I first started with “Basic Econometrics by Gujarati”. It is an undergrad level book but it explain many things in plain English and this helps to generate some intuition. Besides Gujarati, I also read some parts of “Introductory Econometrics by Wooldridge”.

Phase 2: After finishing Gujarati cover to cover, I started reading “Econometric Analysis by Greene”. This book has a lot of explanation in maths. I forgot, before reading this book I spent some time in understanding vector calculus. I was delighted that the explanation in math was not haunting me anymore and I was also able to correlate math and plain English part. I read about 80% of this book and moved on to “Econometric Analysis of Cross Section and Panel Data”. I didn’t want to move on inbetween but I had to show my advisor some output and the rest of Greene was the part that I wouldn’t require for sometime. I read about 60% of Wooldridge diligently and skimmed about another 20% and I hate to say, but didn’t even touch the rest 20%. Besides these 2 books, I also read some part of “Estimation and Inference in Econometrics by Davidson and MacKinnon”. I also did back excercises (data modeling and interpretation one, and not theoretical) from Greene and Wooldridge. This helped me a lot to understand the subject better.

I have also taken 2 courses this fall- Applied Multivariate and Nonparameteric Econometrics to broaden my toolkit.

But now I am facing other problem. Many times when I read papers I question the econometric analysis done by authors. I can think of two reasons behind this-  my understanding of subject is still not good enough or authors sometimes are sloppy. Well before jumping to the second reason, I would like to work on the first reason and hence, the phase 3.

Phase 3: I wanted to finish the things from Greene and Wooldridge. If I get the chance then may be from Davidson & MacKinnon also. From time to time I will also like to read things from “Handbook of Econometrics” particularly its panel data part.

Right now, I have started reading HLM from “Multilevel and Longitudinal Modeling using Stata”. I know this book should be used as a helpbook to use Stata rather than understanding the basic concept. But since our field is the application of econometric and not econometric itself, this is my pretext to straightaway learn the application. Not a good thing, but I guess, this would be the best usage of my time. Sharpening the axe is a good thing, but ultimate aim is to cut trees or write papers in my case.

After finishing this book, I plan to read “An Introduction to Survival Analysis using Stata”. Again not a perfect learning approach but a more pragmatic one, I guess.

It will be tough to even reach to Phase 3 because I am:

• teaching Operations Management this Spring
• taking two courses- Bayesian and Econometrics 3
• reading the Stata book for HLM and Survival Analysis
• planning to complete and send my WITS paper by mid January 07, and start working on another projects

The biggest of all, I and Sheena are expecting a baby so need to start spending time with her. I have not done this from last few years and need to make up now. 🙂

Rohit Aggarwal

My experience at WITS and ICIS 2006

My experience at WITS and ICIS 2006. It was the first time when I went to any conference and it was a great experience. I attended a good number of papers presented in Econ IS track of ICIS and some presentations in WITS.  I met many people and it was good to talk to them. Reading some big names on a paper is one thing, but when you meet and talk to them, then it is totally different experience. For example I met some well known people of our field – Prabuddha De, Vijay Mookerjee, Ramayya Krishnan.

I also met Yong Tan. I was looking forward to meet him from a long time. I bet he is going to be one the greatest researchers in our field. I used to think that it will be tough to get a mentor like Eric Walden but Yong proved me wrong. Meeting Eric after two years was good. At first I did not recognize him due to his changed hair style. He is still the same good old mentor- always encouraging and considerate. I, Param, Vishal and Nitin went to dinner with Eric.

Besides Yong and Eric, it was fun to talk to other faculty at University of Washington and University of Texas at Dallas. To name few people from UW- Ming Fan, Subodha Kumar, Anjana Susarla, Arvind Tripathi and few people from UTD- Vijay Mookerjee, Radha Mookerjee, Zhiqiang Zheng, Wei Yue. Ming is enthusiastic and nice. The best part in him is his friendly smile. Subodha has a good sense of humor and always have some joke to crack. Arvind, an alumni of my university, was very friendly. Few people from other places whom I enjoyed talking:

• Akhil Kumar from Penn State
• Karthik Kannan from Purdue
• Gautam Pant from Utah
• Yonghua Ji, Ray Patterson, Ofer Arazy from Univ. of Alberta
• Marshall Van Alstyne from MIT and BU
• Ramayya Krishnan from CMU
• Gurpreet Dhillon from Virginia Commonwealth
• Alok Gupta from Minnesota
• Andrew Burton-Jones from UBC
• Sinan Aral from NYU

Andrew Burton-Jones won the best dissertation award of ICIS 2006 and was also the chair of the session in which I presented at WITS. Sinan, Marshall and Brynjolfsson won the best paper award at ICIS. Marshall was very generous in releasing some of their proprietary softwares to the research community. He later explained to me that the software was used to get e-mails from company’s server without data loss and the software was also capable of masking the messages for privacy.

People whom I met but did not get the chance to talk much are: 

• Prabuddha De, Alok Chaturvedi from Purdue
• Sumit Sarkar, Varghese Jacob, Indranil Bardharn from UTD
• Balaji Padmanabhan, Kartik Hosanagar from Wharton
• Michael D. Smith, Rahul Telang  from CMU
• Amit Basu from SMU
• Anindya Ghose from NYU

Some of the earlier faculty of my department were also there: Ravi Bapna from ISB, Kumar Mehta from George Masson, Mukul Gupta from UTSA

I also met some PhD students: Pankaj from Michigan State, Animesh from Maryland, Nachiketa Sahoo from CMU, Dmitry from Minnesota, Grace from Washington.

The biggest fun of the conference was to hang out with old buddies Param and Vishal Middha. I also got to meet two of my undergrad classmates- Raveesh and Tejinder. Tejinder lives with his wife in Milwaukee and they hosted a dinner for me, Param and Vishal.

Overall, I spent a lot of money in attending the two conferences, but I feel it was money worth spent.

Rohit Aggarwal

Robot librarians – Chicago State University

“Biblio Tech … The new library at Chicago State University has one ironclad rule: No students allowed in these stacks – only robots.  Every book, CD, and DVD in the school’s $38 million facility is tagged with a radio-frequency ID chip.  When a borrowed item slides through the return slot, the system identifies and sorts it. ”

Link:   http://www.wired.com/wired/archive/15.01/start.html

I love the technology that makes life easier and gives more work to IS people. 🙂

via Techmeme

Vista security flaws

“Flaws Are Detected in Microsoft’s Vista  —  Microsoft is facing an early crisis of confidence in the quality of its Windows Vista operating system as computer security researchers and hackers have begun to find potentially serious flaws in the system that was released to corporate customers late last month. ”

Source:   New York Times  via Techmeme

Rohit Aggarwal

Econometric Analysis Wooldridge

 Useful links:

• Solutions of Introductory Econometrics [2]
• PPT on single equation analysis using panel data both for static and dynamic cases [1]

1. Wooldridge, Jeffrey M. 2002. Econometric Analysis of Cross Section and Panel Data. The MIT Press
2. Wooldridge, Jeffrey M. 2003. Introductory Econometrics: A Modern Approach. Thomson, 2e

Rohit Aggarwal

Swivel "YouTube for Data"

Techcrunch describes Swivel:

“That’s a good start for someone trying to understand it, because the site allows users to upload data – any data – and display it to other users visually. The number of page views your website generates. Or a stock price over time. Weather data. Commodity prices. The number of Bald Eagles in Washington state. Whatever. Uploaded data can be rated, commented and bookmared by other users, helping to sort the interesting (and accurate) wheat from the chaff. And graphs of data can be embedded into websites. So it is in fact a bit like a YouTube for Data.

But then the real fun begins. You and other users can then compare that data to other data sets to find possible correlation (or lack thereof). Compare gas prices to presidential approval ratings or UFO sightings to iPod sales. Track your page views against weather reports in Silicon Valley. See if something interesting occurs. “

Rohit Aggarwal