Covid-19 Vaccine Trials Are a Case Study on the Challenges of Data Literacy.
Harvard Business Review.
It’s dangerously easy to misinterpret data, especially when it’s reported in percentages rather than absolute numbers. The author showcases a number of dangers by focusing on the vaccine-efficacy results reported in November of 2020. He then shows how similar dangers can apply in business contexts, and offers three main lessons for managers hoping to make good decisions using data: be wary of big data, be wary of precision, and beware of post-diction.
Leading with Decision-Driven Data Analytics.
MIT Sloan Management Review. With Stefano Puntoni.
If you were to ask any major CEO about good management practices today, data-driven decision-making would invariably come up. Companies have more data than ever, but many executives say their data analytics initiatives do not provide actionable insights and produce disappointing results overall. In practice, making decisions with data often comes down to finding a purpose for the data at hand. Companies look for ways to extract value from available data, but that doesn’t necessarily mean data analysts are answering the right questions. It’s also not a safeguard against the influence of preexisting beliefs and incentives. The solution is simple: Instead of finding a purpose for data, find data for a purpose. We call this approach decision-driven data analytics.
The Dangers of Categorical Thinking.
Harvard Business Review. With Philip Fernbach.
Human beings are categorization machines, taking in voluminous amounts of messy data and then simplifying and structuring it. That's how we make sense of the world and communicate our ideas to others. But according to the authors, categorization comes so naturally to us that we often see categories where none exist. That warps our view of the world and harms our ability to make sound decisions--a phenomenon that should be of special concern to any business that relies on data collection and analysis for decision making. Categorical thinking, the authors argue, creates four dangerous consequences. When we categorize, we compress category members, treating them as more alike than they are; we amplify differences between members of different categories; we discriminate, favoring certain categories over others; and we fossilize, treating the categorical structure we've imposed as static. In the years ahead, companies will have to focus attention on how best to mitigate those consequences.
The Idea of "Investing in What You Know" Is More Dangerous Than You Think.
Harvard Business Review. With Andrew Long and Philip Fernbach.
Linear Thinking in a Nonlinear World.
Harvard Business Review. With Stefano Puntoni and Richard Larrick.
The human brain likes simple straight lines. As a result, people tend to expect that relationships between variables and outcomes will be linear. Often this is the case: The amount of data an iPad will hold increases at the same rate as its storage capacity. But frequently relationships are not linear: The time savings from upgrading a broadband connection get smaller and smaller as download speed increases. Would it surprise you to know that upgrading a car from 10 MPG to 20 MPG saves more gas than upgrading from 20 MPG to 50 MPG? Because it does. As fuel efficiency increases, gas consumption falls sharply at first and then more gradually. This is just one of four nonlinear patterns the authors identify in their article. Nonlinear phenomena are all around in business: in the relationship between price, volume, and profits; between retention rate and customer lifetime value; between search rankings and sales. If you don't recognize when they're in play, you're likely to make poor decisions. But if you map out relationships in data visualizations, you can actually see whether they are nonlinear and how--and then make choices that maximize your desired outcome.
High Online User Ratings Don't Actually Mean You're Getting a Quality Product.
Harvard Business Review. With Philip Fernbach and Donald Lichtenstein.