Control variables in regressions — better don’t report them!

A while ago I wrote a short blog post with a pretty simple message: “Don’t Put Too Much Meaning Into Control Variables”. And I must say I was surprised by the many positive responses it got. The respective tweet received more than 1000 likes and nearly 400 retweets. And the blog post even got mentioned in an internal newsletter by the World Bank. So clearly there seems to be some demand for the topic. That’s why my coauthor Beyers Louw (PhD student at Maastricht University) and I decided to turn it into a citable research note, which is now available on arXiv:

“On the Nuisance of Control Variables in Regression Analysis” 

Abstract: Control variables are included in regression analyses to estimate the causal effect of a treatment variable of interest on an outcome. In this note we argue that control variables are unlikely to have a causal interpretation themselves though. We therefore suggest to refrain from discussing their marginal effects in the results sections of empirical research papers. 

Please use it and save yourself a paragraph or two in your next research paper! :)

Causal Inference in Business Practice – Survey

My colleagues and I are currently looking for data scientists to take part in a short survey (5–10 min) on causal inference in business practice. Is data-driven decision making important in your job? Then we’d love to hear your perspective:

Please help us reaching more people by sharing the above link with friends and colleagues, or by retweeting this tweet:

Thank you for your help!

Innovation,unemployment and subjective well-being

These days, everybody is talking about the losers of globalization and how they made Trump and Brexit happen. People in industrialized countries lose their jobs due to offshoring and international competition, which leads them to vote for right-wing populists, so the common narrative goes. That might not be the full story though. Continue reading Innovation,unemployment and subjective well-being

How important is social mobility for innovation and growth?

Raj Chetty is a rising star in economics. After graduating from Harvard at the age of 23, he became an assistant professor at Berkeley, where he got tenure only four years later. Since then he won the John Bates Clark Medal in 2013 and moved to Stanford in 2015. His latest research is concerned with the question of upward mobility in society and how it affects innovation and economic growth. Continue reading How important is social mobility for innovation and growth?

This isn’t a scientific revolution

Two weeks ago I’ve been at the Annual Meeting of the Academy of Management (see this post). And you might have guessed, big data was a huge topic. There is tremendous potential for the use of data science in the business world. Continue reading This isn’t a scientific revolution

Theory Horse Races

I just came back from the 76th Annual Meeting of the Academy of Management in Anaheim, California. The conference was great, not just because of the location. Lots of participants and lots of interesting sessions. Every year they have “professional development workshops”, which are a great opportunity to learn, not only for young scholars.

I attended one of those workshops called “Writing Better Theory”. We all know that the standards for how to develop theory are quite different in management science compared to economics. Therefore I was particularly interested in this session. The panel consisted of very distinguished speakers, e.g., Lorraine Eden from Texas A&M University, who is former Editor-in-Chief of JIBS. They gave good advice on how to make your arguments more concise and develop a real contribution to the theory.

But I lost some sleep over one remark by Alvaro Cuervo-Cazurra, reviewing editor of JIBS and AIB fellow (okay, I was also severely jet lagged). He urged people not to run what he called “horse races” between conflicting theories, but rather to stick to one paradigm and develop your arguments from there. I recall his point like this. If theory 1 predicts A and theory 2 predicts B, you might be inclined to conduct an empirical test, and if the data (clearly) show B you will discard theory 1 in favor of theory 2. According to Cuervo-Cazurra this is a bad idea because of two reasons:

  1. Either you encounter reviewer one who always thought that theory 1 was wrong to begin with and who will think your paper is obvious.
  2. Or, there will be reviewer two who strongly believes in theory 1 and who will find every single flaw in your study in order to reject your paper.

Take a moment to let that sink in… This strategy might actually increase your chances to publish, especially if you’re new in the profession. But running empirical tests in order to falsify theories and to discriminate between competing explanations, isn’t that exactly what science is about? What other way is there to “keep your house clean” and to prevent the accumulation of more and more theories with low predictive power?

I was too shocked to raise a question anymore. But I could have simply gotten something wrong here. After all it was early in the morning. Anyways, I would love to hear your thoughts on this!

Econ 101: The merits of a market economy

The efficiency of a market-based allocation of goods is something taught very early on to students of economics. But once in a while it’s good to remind ourselves of it, especially since it sounds like propaganda in the ear of some. Ask yourself, in which bus shelter would you rather prefer to wait for the bus. The new and shiny one on the picture above where you’re exposed to the latest fashion advertising. Or the neutral one below? Continue reading Econ 101: The merits of a market economy