These materials cover what to do when the classical OLS assumptions fail: how to test for heteroskedasticity and serial correlation, and how to construct standard errors and hypothesis tests that remain valid when they are present. The tutorial applies each test to concrete estimated regressions, and the solutions sheet works every answer in full.
What these materials cover
- The White test for heteroskedasticity, and tests against specific (e.g. linear) forms of heteroskedasticity
- Heteroskedasticity-robust (White) standard errors and robust Wald tests of parameter restrictions
- Testing for serial correlation and the consequences of ignoring it
- When robust inference changes conclusions: worked regression output
- Full step-by-step solutions to every tutorial question
Download
Free to download and use for personal study. Written for my own university teaching; shared here as evidence of teaching style and depth.
Lecture slides: Diagnostic testing & robust inference (29 slides) (PDF) Tutorial sheet: heteroskedasticity & serial correlation exercises (PDF) Tutorial solutions, fully worked (PDF)
Who this is for
MSc and final-year undergraduate econometrics students working on diagnostic testing, and anyone whose empirical project needs defensible standard errors.
Working on this topic?
Send the module topic list, the problem set and where you're stuck. A free consultation diagnoses whether the difficulty is definitions, derivations or software output — and proposes a plan.
Related free resources
- Cross-Section Econometrics — full study-note hub
- Diagnostic testing in linear regression — study note
- Autocorrelation and serial correlation — study note
- Hypothesis testing from first principles
- All teaching materials — notes, exercises and solutions
One-to-one help
For help with this material — or the module it belongs to — see econometrics tuition or PhD econometrics support. The first consultation is free, with no obligation.
Free worked video lectures: @economaths on YouTube.