Classical Assumptions (Gauss-Markov, BLUE)
When OLS is the best you can do, and what breaks when each assumption fails.
Definition
The conditions under which OLS is BLUE (best linear unbiased estimator): linearity, random sampling, no perfect collinearity, exogeneity, homoskedasticity.
Key equation
Key condition: E[u|X] = 0 (exogeneity), its failure breaks unbiasedness itself
The intuition
Each assumption maps to a specific disease and fix: heteroskedasticity → robust SEs (efficiency lost, unbiasedness fine); endogeneity → IV (everything lost). Diagnosing WHICH assumption failed is the entire skill of applied econometrics.
Exam tip
Rank the assumptions: exogeneity failure biases estimates; heteroskedasticity only mis-sizes standard errors.
Want this one as a full interactive graph? Votes decide the build order, and an email means we can tell you when it ships.