One of the skills that's being tested during a case interview is something I call data sufficiency.
Basically, you have a bunch of data and the question is do you have ENOUGH data to make a particular conclusion.
This is certainly something that is tested during a live, in-person, face-to-face case interview.
It is also a skill that is often tested in a variety of formats including written tests before the first in-person case interview question is asked.
An example of this is the McKinsey Problem Solving Test which evaluates your data sufficiency skills (among others).
In parts of the McKinsey Problem Solving Test, you are given a bunch of data and some possible conclusions.
Your job is to figure out which conclusions are or are NOT supported by the facts presented.
Now this test is not intended to torture you (though I know some people might argue with me on this one).
It turns out this is a very important skill once you're on the job as a management consultant, especially as a first year analyst or associate.
In addition to a live case interview, the McKinsey Problem Solving Test, other firms have used similar tests (Monitor has done this from time to time) OR have given an in-person case interview where the candidate is presented with a written document consisting of various facts, figures and other data… and the data sufficiency skill is tested verbally.
These are all variations of the same thing.
Given a set of data, will you determine the correct, logical, and factually supported conclusion every time?
So bottom line, this skill is pretty important and based on the many emails I've been receiving from aspiring consultants around the world, it seems many people are having a difficult time figuring out how to practice these skill.
So just for kicks, I thought I'd give you an actual data sufficiency type question that a McKinsey Partner in the Los Angeles office asked me when I interviewed there for my final round several years ago.
Before I give you the question (which is posted on my blog), I strongly recommend that you read the question and then immediately hit the "post comment" button to post your answer on my blog.
(You can do so with just your first name or initials if you want to be a anonymous)
The key is to post your answer WITHOUT seeing other people's answers!
(otherwise it sort of defeats the purpose of practicing, and there really are very few opportunities to practice this skill.).
I will be "grading" all the answers posted in a day or two.
Here's the question:
Volvo recently ran an advertisement that said:
Volvo - The Safest Car in the United States*
* New US government report shows that fewer people die in a Volvo than in any other car brand in America
(Note: A prior version of this blog post indicated that Volvo was the Safest Car in the World. My intention was to write U.S., so some of the answers you see may reflect this.)
Assess the validity of this statement, you have 3 - 5 minutes to do so. You are NOT permitted to ask any clarifying questions. Please be SPECIFIC in your answers. Go!
Click Here to Post Your Response
(Remember: Don't cheat by looking at everyone else's response first, look at them AFTER you post your response.)
Scroll down to see the hundreds of answers submitted by readers of my blog.
To see my answer to this question (ideally AFTER you try to answer the question yourself FIRST), click here: McKinsey Problem Solving Test - Example 1 Answers.
If you found this post useful, I suggest becoming a registered member (it's free) to get access to the materials I used to pass 60 out of 61 case interviews, land 7 job offers, and end up working at McKinsey.
Members get access to 6 hours of video tutorials on case interviews, the actual frameworks I used to pass my interviews, and over 500 articles on case interviews.
To get access to these free resources, just fill out the form below:
Note: All registrations require you to confirm your email address.
Please type your email address carefully, entering your email also subscribes you to my Case Secrets Email Newsletter.
Tagged as:mckinsey problem solving test, understand the question
Technical data scientist interview questions
Statistics and machine learning are important technical skills for data scientists. These questions help measure knowledge, plus the ability to explain complex topics. Some of the questions are also designed to bring out the art and science of data science.
- What is the curse of dimensionality and how should one deal with it when building machine-learning models?
- Why is a comma a bad record separator/delimiter?
- Explain the difference between a compiled computer language and an interpreted computer language.
- How do you determine “k” for k-means clustering? Or, how do you determine the number of clusters in a data set?
- What’s more important: predictive power or interpretability of a model?
- Explain finite precision. Why is finite precision a problem in machine learning?
- Explain the “bias-variance trade-off” and why it is fundamental to machine learning.
Practical experience data scientist interview questions
Technical skills are important, but they must be applied to solve problems. Your data science candidates should be able to describe projects they have worked on, and how they turned out. They also should be able to articulate what aspects of their technical training have been important in their day-to-day data scientist tasks, and how they can apply their skills to your business.
“Remember that the candidate’s practical experience does not need to be within your industry,” says Udo Sglavo, Senior Director of Advanced Analytics R&D at SAS. “I’ve heard from hiring managers who say their best hires have been people outside their industries who can look at problems from a fresh perspective.”
Evaluate practical skills by asking some of these questions:
- Describe a recent use of logistic regression.
- Describe an analysis you have recently completed, including strategies and findings. How were the findings used by the business? (This can be from a student research project or thesis if the candidate is a recent graduate.)
- Give examples of data cleaning techniques you have used in the past.
- What subjects would you include in a one-day data science crash course? And why?
- Describe a situation where you had to decide between two different types of analyses – and why you chose the one you did.
- Explain the benefits of test-driven software development; or explain the benefits of unit testing.
Communication-focused data scientist interview questions
Last but not least is communication. Even the smartest statistician in the room will fail if she cannot explain the relevance of her results. Data scientists need to understand their data and explain its significance to the problem at hand.
“Data visualization and storytelling are two important ways to communicate results,” says Patrick Hall, Senior Machine Learning Scientist at SAS. “And communicating up the chain of command is very important.”
With these questions, you are seeking to evaluate the candidate’s ability to communicate clearly and persuasively.
- Explain to the leaders of this company what model lift is and why they should care.
- How do you identify and overcome obstacles (during projects, with customers, with decision makers, etc.)
- Tell me about a project you worked on that succeeded in part because of the way results were communicated. What were the factors that made it a success?
- Tell me a compelling story about data that you have analyzed.
- What is your favorite data visualization book or blog? And why?
- How would you design a chart or graph for a color-blind audience?
- Explain to a business analyst the trade-off between the predictive power and the interpretability of a model – and why this matters.
Ultimately, you are looking for someone who is tech savvy, quant savvy and business savvy. He should be persuasive and credible, but also creative and passionate.
Data scientists are in short supply, but hiring a good data scientist can help anticipate customer needs, optimize prices, prevent fraud – and more. We hope these data scientist interview questions can help you find someone with a range of technology skills and a knack for communicating complex subjects to a variety of audiences.