Foundations

Math and statistics interview questions

Statistics questions in a data science interview are rarely about deriving a formula. They test whether you can say what a number means to someone who has to act on it: what a p-value of 0.03 does and doesn’t tell a product manager, why a confidence interval describes the method rather than this one interval, and when the central limit theorem lets you treat an average as normal.

The traps are familiar ones. Reading a p-value as the chance the result is real. Running twenty tests and reporting the one that cleared 0.05. Assuming a distribution without checking what the data looks like. A strong answer says the precise thing in plain words, then names the assumption it rests on.

Try one now

Friendly

A product manager asks what "p = 0.03" means on your A/B test readout. How do you explain it, and what doesn't it tell them?

Free, no sign-up. The interviewer asks follow-ups on your reasoning, then rates your answer.

What the 25 questions cover

  • Distributions worth knowing10
  • Confidence intervals5
  • Hypothesis testing5
  • ANOVA4
  • Probability rules and conditional probability3
  • Standard error3
  • p-values3
  • Central limit theorem2
  • t-test2
  • Multiple testing correction (Bonferroni, Benjamini-Hochberg)2
  • Maximum likelihood estimation2
  • Linear algebra for ML (vectors, matrices, eigenvalues)1
  • Sampling methods1
  • Bootstrapping1
  • Degrees of freedom1
  • Bayesian vs frequentist inference1

A question can cover more than one topic, so the counts add up to more than 25.

How the practice works

  1. The AI interviewer asks the question and follows up on your answer, the way an interviewer would.
  2. Stuck? Ask for a hint. Each one gives a little more away, so you can get unstuck without being handed the answer.
  3. Get a written debrief. Four ratings, each from Needs work to Interview-ready, tied to what you actually said, and what to study next.

More foundations questions

See all categories