← 📊 Evaluation & ML FoundationsNEXT IN EVALUATION & ML FOUNDATIONSHypothesis Testing and p-values→
Core
CLT, Sampling, and Confidence Intervals
The central limit theorem says a sample mean is approximately normal no matter the underlying distribution, which is why so much inference relies on the normal curve. Standard error captures how much a sample mean wobbles and shrinks as sample size grows, unlike standard deviation. AI, ML, and GenAI engineer interviews probe this because it fixes how wide a confidence interval is and therefore how long an A/B test must run.
a free account unlocks the core curriculum tier · no card
RELATED CONCEPTS
PRACTICE THIS IN REAL QUESTIONS
Machine Learning & Data ScienceDesign an A/B test for a model change: power, sample size, significance, and the peeking problem.→Machine Learning & Data ScienceExplain the Central Limit Theorem, and the difference between correlation and causation (with Simpson's paradox).→Machine Learning & Data ScienceYour A/B test shows the control and treatment groups differ before the treatment even applies. What's wrong?→System Design for AI in ProductionDesign an A/B testing platform for LLM features (prompts, models, retrieval) with trustworthy metrics.→Machine Learning & Data ScienceExplain MCMC and Metropolis-Hastings: why does the chain sample from the posterior?→ML System Design (Product)Design an evaluation framework for an ads-ranking system.→
COMPANIES THAT ASSUME THIS