My introduction to “omitted variable bias” | MBA Learnings
First-year student Rohan Rajiv is blogging once a week about important lessons he is learning at Kellogg. Read more of his posts here.
One of the nicest things about being in graduate management school is that the classes have a lot to do with many of the things I have been reading about over the past few years. So, I’m excited to share some of my favorite learnings from classes under the “MBA Learnings” series.
Today’s learning is a concept called “Omitted variable bias.” The origin of this idea lies in statistics but we all see this nearly every day of our lives. Most of the false claims we hear fall prey to omitted variable bias. And, let’s face it, we hear many false claims.
Here’s an example of a claim: “People who eat _____ (insert healthy product) have low cholestrol/better health in some other way.” That might be true on the surface, but the equation misses variables like the person’s existing health and the amount of time they exercise. Without considering the entire picture, the claim is false. Badly conducted studies see one event frequently connected to another and incorrectly assume one event causes the other.
The omitted variable bias, thus, points to our tendency to frequently miss the entire picture. An application that comes straight to mind is when we interview for a new job/role. If things go well, we feel really pleased with ourselves (“I prepared really well”) and, when things go bad, we feel demoralized. There are a couple of important variables we often neglect:
1. The biases of our interviewers. Companies and interviewers select people they “get.” If your interviewers are strait-laced suit-wearing types, the chances that you’ll get a job you are well qualified for in jeans and a t-shirt is low. You only really influence one part of the outcome of an interview. A lot lies in the hands of your interviewers.
2. The culture of the firm. The interview process beautifully illustrates the power of culture. If a firm has a fairly homogeneous culture and, let’s face it, most great firms do. Then, being on the right side of the culture line puts you in great stead. If you have a “Googliness” rating of 9/10, you are likely going to be a hit with most of your interviewers at Google.
3. The dynamics within the firm. There’s a lot going on within the firm – internal candidates are being pushed for the job, your hiring manager is feeling the pressure because of a failed quarter, the company’s earnings call didn’t go great, etc. All of this stuff adds up.
So, what happens when we take omitted variable bias into consideration? First, we learn not to overstate or understate our contribution. Yes, our contribution matters. But, only so much. There’s a lot that lies beyond our control and there’s no need for the manic high or the depressive low.
Second, we learn that to distinguish between actions and outcomes. There is a saying that life is 10% action and 90% reaction. Perhaps interviews aren’t any different. Now that we’ve realized that people’s reaction to our actions is a large part of what happens to us, it helps to just direct our focus to that important 10%. By being the best we can be, we give ourselves a shot at maximizing the impact of that 10%. That’s all we can do. Once it’s done, focus on the next action as any time spent worrying about outcomes is time taken away from that next action.
From omitted variable bias to interview learnings to philosophy – you’ve got to love statistics!
Rohan Rajiv is a first-year student in Kellogg’s Full-Time Two-Year Program. Prior to Kellogg he worked at a-connect serving clients on consulting projects across 14 countries in Europe, Asia, Australia and South America. He blogs a learning every day, including his MBA Learnings series, on www.ALearningaDay.com.