News

February 2, 2016

SRITNE Knowledge Seminar talk on Information Quality: A Framework for Evaluating Empirical Studies

Tomorrow (Feb 3, 2016), I'll deliver a talk on "Information Quality: A Framework for Evaluating Empirical Studies", as part of the SRITNE Knowledge Seminar at the Indian School of Business. I will introduce InfoQ and also mention recent developments of the framework for authors and reviewers of empirical papers.

Time and Location: Indian School of Business (Gachibowli, Hyderabad), AC3 MLT, 11:00-12:30.


January 16, 2016

Received the E.SUN Bank Academic Award

During our Chinese New Year Banquet this week, I received an award for publishing in a top journal: The E.SUN Academic Award (see news coverage). This generous award, established by E.SUN bank, is given to faculty at the top four management schools in Taiwan who publish in one of the few top journals in their field. NTHU joined the program in 2015.
As part of the award ceremony, I briefly presented the two papers for which I won the award (see my slides):

  1. "A Tree-Based Approach for Addressing Self-selection in Impact Studies with Big Data", with Inbal Yahav (Bar Ilan University) and Deepa Mani (Indian School of Business), forthcoming in MIS Quarterly
  2. "One Way Mirrors In Online Dating: A Randomized Field Experiment", with Ravi Bapna (Minnesota), Jui Ramprasad (McGill), and Akhmed Umyarov (U Minnesota), forthcoming in Management Science.

I'm extremely grateful to my co-authors -- it's been incredible to collaborate with these out-of-the-box thinkers with incredible knowledge and creativity. Research is always exciting in these collaborations, making the painful publication process tolerable and worthwhile.

E.SUN Bank's investment in academic research - recognizing and incentivizing top research in management schools in Taiwan - is a wonderful signal highlighting the importance of academic research to industry as well. Thanks to E.SUN Bank leadership for the award! It is my honor to bring NTHU its first E.SUN Academic Award. Thanks also to my colleagues at the Institute of Service Science and the College of Technology Management for their support.

Announcement on our college website (in Chinese, but possible to translate with Google Chrome!)


November 5, 2015

Explain or Predict @ Microsoft Research

The Microsoft Research group in NYC invited me to give a talk on "To Explain or To Predict? How Prediction Can Advance Research". I spent half a day on Nov 3, 2015 at their beautiful lab and learned what "computational social scientists" study. The audience in my talk included folks with a computer science background from the computational social science and machine learning groups and others. The lively discussion touched on what the scientific method means and requires in social science research.

Special thanks to Shawndra Hill, Duncan Watts, and Hanna Wallach for super interesting conversations and hearty hospitality.


November 1, 2015

Talk @ INFORMS: Trees for Detecting Simpson's Paradox in Big Data

Tomorrow at INFORMS's Data Mining Cluster @ 1:30pm, I'll be presenting my work (with Inbal Yahav) "The Forest or the Trees? Tackling Simpson’s Paradox with Classification and Regression Trees". I'll show the special use of the tree structure that we take advantage of in order to detect whether a dataset has Simpson's Paradox (reversal of a causal direction when disaggregating the data). See our working paper on SSRN for more details.


October 27, 2015

Tree based approach for addressing self-selection in Big Data: forthcoming in MIS Quarterly

My paper A Tree-Based Approach for Addressing Self-Selection in Impact Studies with Big Data with Deepa Mani (Indian School of Business) and Inbal Yahav (Bar-Ilan University) is forthcoming in MIS Quarterly, in the special issue on Transformational Issues of Big Data and Analytics in Networked Business. The paper introduces a novel method based on a classification and regression tree - a tool typically used for prediction in data mining - for use in studies that might suffer from self-selection bias, where observations self-select the treatment/control group. We present an alternative to the well-known Propensity Score approach, which is more automated, simpler to understand, more flexible in terms of assumptions and data types, and especially useful with Big Data.

A working paper of an earlier version is available on SSRN.


Pages