Rank correlation (Spearman's rho): ρ = 1 - 6Σd²/(n(n²-1)), where d = rank difference. Non-parametric (doesn't assume normality). Range: -1 to +1. Advantages: Works for ordinal data; robust to outliers. Disadvantages: Less powerful than Pearson for normal data. Example: Two judges rank 5 products. Judge A: 1,2,3,4,5. Judge B: 2,1,3,5,4. Rank differences: 1,1,0,1,1. d²=4. ρ = 1 - 6×4/(5×24) = 1 - 24/120 = 0.8 (strong agreement). Solving: Rank both variables. Calculate differences. Apply formula. Exam tip: Use when data ordinal or non-normal. Understand non-parametric advantages. Practice: Ranking and agreement problems.