Cognitive biases: We all have them and we regularly encounter them in everyday life. But how do data analysts actually experience these biases? And how can you recognise them? In this series we will discuss cognitive biases in the context of analysts. Each blog picks out 3 biases from 20 categories.
In this blog, we have two biases from the “Not Enough Meaning” spectrum: Curse of Knowledge and the Hindsight Bias and a bias from the “Need To Act Fast” Spectrum: the Hard-Easy Effect.
This bias says that we struggle to imagine what other people don’t know. So you’re actually cursed by your own knowledge. Significance, factors, overfitting, variance, homoscedasticity (OK, maybe not that one) – when you talk about all these things, you implicitly assume that the other person knows what you’re talking about. They are concepts that are entirely ordinary for a data analyst and so it might be difficult for you to understand that another person might only slightly understand them (if at all). So try to empathise with the other person when you are giving a presentation or explaining your analysis. Because nobody wants to be that old physics teacher from high school that nobody could ever possibly understand.
The hindsight bias says that when you know the outcome of an event, the whole process of that event suddenly feels logical and predictable, even though there is absolutely no reason for it to be so. Just imagine: after hours and hours of sweat and tears, you finally come up with a good churn forecasting model. As soon as you’ve made that model, all the steps you had to go through to get to that point suddenly actually feel obvious: Of course you had to impute the missing values with the average and not the median. And of course you could have known that this one predictor variable wouldn’t be normally distributed and that you would need to transform it. Watch out for that one colleague who thrives on the hindsight bias and constantly says things like “you didn’t notice that before”. That’s easy for you to say after the event!
When you were making the churn forecasting model, you probably hadn’t expect beforehand that it would be so difficult. That’s exactly what the Hard-Easy Effect is about: the likelihood of success in difficult tasks is overestimated and the likelihood of success in easy tasks is underestimated. Of course, you can fire off one of those forecasting models with your eyes closed, so it was disappointing that you had to work so hard for it this time. For difficult tasks, it’s the other way around: you block out loads of time to do it, you know it’s going to be tough, you do everything you possibly can to make sure it works out. Result: the task feels easier than it actually was. This can be solved in the future by always expecting everything to be a difficult task, so that you feel euphoric and relieved afterwards. The question remains whether your scrum master will be pleased with you estimating everything as 100 points.
Also read the other parts:
Part 1: Self-relevance effect, Confirmation bias and the Bias blind spot.
Part 2: Availability heuristic, Contrast effect and Clustering illusion.
Part 3: Essentialism, the Positivity Effect and the Appeal to Probability Fallacy.
Part 5: Sunk Cost Effect, the IKEA effect and the Google Effect.
Part 6: Ambiguity Bias, Appeal to Novelty and False-Consensus Effect.
Do you want to know more about this subject? Please contact us on +31 (0)33 258 28 30 or firstname.lastname@example.org.
21 February 2022
Plan your calendar free and make sure you have plenty of party clothes in your closet,... read more
7 April 2021
In these boring lockdown-times we are all desperately looking for ways to still interact with our... read more