November 18, 2016

Paper on trees for addressing self-selection in impact studies now published in MIS Quarterly

Many studies use quasi-experiments, which are similar to randomized experiments except that subjects are not randomly assigned to the treatment and control groups. The result is what's called "self-selection bias", which requires special analysis correction for valid inference about the treatment effect. In a joint paper with Deepa Mani (ISB) and Inbal Yahav (Bar-ilan U) we propose a new method that is based on classification and regression trees: "A Tree-Based Approach for Addressing Self-Selection in Impact Studies with Big Data", MIS Quarterly, vol 40 no 4, pp. 819-848. Useful also for randomized experiments and observational impact studies.

Check out the slide deck for a quick walk-through.

November 3, 2016

Interview on Analytically Speaking

Next week I'll be headed to SAS headquarters in Cary, NC for an interview on Analytically Speaking. I look forward to Anne Milley's thought-provoking questions! The announcement promises to walk through several of my research areas:

In her highly acclaimed paper, To Explain or to Predict?, Galit Shmueli writes “statistical modeling is a powerful tool for developing and testing theories by way of causal explanation, prediction, and description.” But while it is common to conflate explanation and prediction, understanding the distinction is crucial.
On the table for discussion:
Four important tensions between explaining and predicting.
Information quality.
Hacking data mining for causality.
How to spark student curiosity in statistics.
What is behavioral big data?

Expertise: explanatory modeling, causality, predictive modeling, predictive power, statistical strategy, data mining, scientific research

The interview will be recorded. You can register for the free webcast.

November 3, 2016

Talk on "Research with Behavioral Big Data" in Kaohsiung, Taiwan (Nov 4, 2016)

I'm heading south to Kaohsiung's National Sun Yat-sen University to give a talk about "Research Using Behavioral Big Data" at the College of Management, MIS department, tomorrow (Friday, Nov 4, 12:30pm). For more information on what, when, and where, see the announcement page.

October 24, 2016

Experimenting with quantitative self

Talking about behavioral big data is one thing. Analyzing it is another. But generating it? I wrote about my personal experience with a wearable device in the blog post Experimenting with quantified self: two months hooked up to a fitness band

October 8, 2016

Knock-knock: Forecasting MOOC opening in a week!

The Business Analytics Using Forecasting free online course (MOOC) that I designed is opening in a week! As of today, 3000+ learners have joined from around the world and all ages. The welcome discussion board reveals an amazing crowd of grad students, professionals in a variety of fields, and even instructors.

Together with our excellent team of PhD students (Tonny Kuo, Nicholas Danks, Mahsa Ashouri, and Suneel Chatla) and the NTHU studio team, we've been working tirelessly to create a great resources and a meaningful learning experience.

My colleague Ron Kenett forecasted that the course will have 10,000 learners. If you have a different forecast, please cast it now on Twitter (tag @gshmueli and use hashtag #FLbizanalytics)! The most accurate forecast for the number or learners as of midnight Oct 17, 2016 (according to the FutureLearn clock) will receive a free Practical Time Series Forecasting: A Hands-On Guide" Kindle book (the R or XLMiner edition).