Statistics
What to Know
Statistics questions cover descriptive and inferential concepts used to interpret data. Know measures of center (mean, median, mode) and spread (range, variance, standard deviation, interquartile range), and when the median is preferred for skewed data. Understand distributions: normal, uniform, binomial, and Poisson, plus skewness and outliers. Inferential topics include sampling methods and bias, the central limit theorem, confidence intervals, hypothesis testing (null and alternative hypotheses, p-values, Type I and Type II errors, significance level), and correlation versus causation. Also know A/B testing basics: randomization, sample size, and practical versus statistical significance.
Traps
A p-value is not the probability the null is true; it is the probability of data this extreme given the null. Failing to reject the null is not proof the null is true. Watch for confusing standard deviation (original units) with variance (squared units), and mean versus median under skew. Sampling traps: survivorship bias, selection bias, and non-response bias. Multiple comparisons inflate false positives. Confidence interval traps: a 95% interval does not mean 95% probability the parameter lies inside for a given sample. Correlation does not imply causation, and a lurking variable may explain both.
Worked Example
A/B test results show a 2% lift with p = 0.03 at alpha = 0.05. You reject the null of no difference, but the lift may be too small to matter commercially. Rule of thumb: statistical significance answers whether an effect likely exists; practical significance asks whether it is large enough to act on. Report effect size and confidence interval alongside the p-value.