Statistics & Experimentation Interview Questions

Review this list of 83 Statistics & Experimentation interview questions and answers verified by hiring managers and candidates.

+ Share interview

Describe a situation where an A/B test would not be appropriate. What type of test would you run instead? Why? Has video answer
1 answer
Design a test to measure the effectiveness of a new rider-driver matching algorithm. Has video answer
1 answer
Tell me about a time when you had to design an A/B experiment.
2 years ago
Why is the standard deviation more useful than the range in describing the variability of a dataset?
6 answers
Identify success metrics for a marketing campaign to get new users, then design an experiment to determine if the campaign should continue. Has video answer
10 months ago1 answer
Get your questions answered
Our question database is made possible by user contributions. What were you asked in your most recent interview?
Share
When experimentation is constrained, how do you make decisions using imperfect or historical data?
8 months ago
Two machines produce light bulbs: Machine A produces 60% of the bulbs while machine B produces the remaining. Machine A produces defective bulbs at a rate of 5%, while machine B produces defective bulbs at a rate of 3%. If a randomly selected bulb is defective, what is the probability that it was produced by machine A? Has video answer
1 answer
A PM at Meta asked you to describe the distribution of daily minutes spent on Facebook per user. How would you describe it?
a year ago1 answer
How do you determine sample size based off a certain power you want? Has video answer
3 answers
What assumptions does the t-test make? Has video answer
Design a test to measure the success of adding a new reaction feature to Stories. Has video answer
How do you design an experiment to avoid common pitfalls in interpreting results?
8 months ago
How do concepts like R-squared, multicollinearity, and statistical tests (T-test vs. F-test) help evaluate linear regression models and interpret their results effectively? Has video answer
1 answer
How would you analyze the results of an A/B test for one-click checkout if it’s only available for one payment method? Has video answer
What if you're on a tight on time and want to run your A/B test faster, or you don't have a large enough sample size for statistical significance? Has video answer
1 answer
Given multiple engagement metrics for a single experiment, how would you adjust the p-value thresholds for your experiment and why? Has video answer
1 answer
Hypothesis Testing: Suppose a PM claims that users, on average, spend about $50 per month on Amazon. However, you doubt this claim and believe the average should be higher. You sample 100 users and find the sample mean is $85. Would you reject the PM's claim? Assume population standard deviation is 20.
a year ago1 answer
In what cases should you use the median instead of the mean?
2 years ago1 answer
You have two versions of email campaigns. How would you determine which campaigns will lead to higher sales? Has video answer
1 answer
How much incremental revenue can a food delivery company make if it expands to a new vertical? Has video answer
1 answer

Showing 21-40 of 83

Popular roles

Data Scientist Data Analyst Business Analyst Product Analyst Product Manager

Interviewed recently?

Help improve our question database (and earn karma) by telling us about your experience

+ Share interview experience

Trending companies

Statistics & Experimentation Interview Questions

Describe a situation where an A/B test would not be appropriate. What type of test would you run instead? Why? Has video answer

Design a test to measure the effectiveness of a new rider-driver matching algorithm. Has video answer

Tell me about a time when you had to design an A/B experiment.

Why is the standard deviation more useful than the range in describing the variability of a dataset?

Identify success metrics for a marketing campaign to get new users, then design an experiment to determine if the campaign should continue. Has video answer

When experimentation is constrained, how do you make decisions using imperfect or historical data?

A PM at Meta asked you to describe the distribution of daily minutes spent on Facebook per user. How would you describe it?

How do you determine sample size based off a certain power you want? Has video answer

What assumptions does the t-test make? Has video answer

Design a test to measure the success of adding a new reaction feature to Stories. Has video answer

How do you design an experiment to avoid common pitfalls in interpreting results?

How do concepts like R-squared, multicollinearity, and statistical tests (T-test vs. F-test) help evaluate linear regression models and interpret their results effectively? Has video answer

How would you analyze the results of an A/B test for one-click checkout if it’s only available for one payment method? Has video answer

What if you're on a tight on time and want to run your A/B test faster, or you don't have a large enough sample size for statistical significance? Has video answer

Given multiple engagement metrics for a single experiment, how would you adjust the p-value thresholds for your experiment and why? Has video answer

In what cases should you use the median instead of the mean?

You have two versions of email campaigns. How would you determine which campaigns will lead to higher sales? Has video answer

How much incremental revenue can a food delivery company make if it expands to a new vertical? Has video answer

Explore questions by company

Explore questions by role

Follow Us