The White test for heteroscedasticity

This video explains the intuition and motivation behind the White test for heteroscedasticity. Check out ben-lambert.co... for course materials, and information regarding updates on each of the courses. Quite excitingly (for me at least), I am about to publish a whole series of new videos on Bayesian statistics on youtube. See here for information: ben-lambert.co... Accompanying this series, there will be a book: www.amazon.co....

[@meghna617]

How this man explains these topics so beautifully under 8 minutes when my lecturer does half the job in double the time will always be a mystery to me...

[@AClassOldie]

UOL also?

[@berke-ozgen]

Every student needs a lecturer like you. Thanks Ben.

[@SpartacanUsuals]

Hi Sai, many thanks for your messages. If you have any specific requests for topics in econometrics which you would like videos for then please let me know. Thanks, Ben

[@upanshumahawar7671]

why do we use u cap squared?

[@beckfordsaied4]

Ben Lambert please start doing tutorials on how to perform these tests on R, stata or spss

[@nadanidi]

Thank you! You've helped me out a lot. I'm wondering though who is downvoting this?

[@chirasreepal]

Ben, excellent lectures. Thank you for sharing these.

[@james3032]

Perfect explanation.
My lecturer somehow spent 40 minutes talking about the White-Test.

[@senaklnc1494]

YOU ARE THE BEST.

[@ndumisolushaba2403]

Mr Lambert outcha saving my semester,

[@erhardvespucci9803]

This video is so helpful, thank you for posting these!

[@VeanZann]

Man! Make more explaining videos! It is reaaaaaaly clean 😊

[@jvenkatesan1977]

Excellent logical explanations in understandable format

[@pablodelpino494]

you are saving my exams 🙏🏻🙏🏻🙏🏻

[@christianseybold5871]

awesome videos! really helpful. I think its great, that someone puts that much effort into something to help other people!

[@chrinnicolas7862]

I linked your channel to my students. Very good stuff!

[@leafj.9243]

Excellent lectures !!!

[@ivansuarez8751]

Hi, i don't know if you could help me but, tomorrow I have an exam and one question of the profesor is "What assumes the white test regarding the squared error term and the exogenous variables ?
I got many other questions but this is an important one
thank you

[@wolfgangi]

did you ever figure out what the answer was?

[@abbydavidson1663]

These are so incredibly helpful! Thank you so much!

[@wolfgangi]

why are you adding those power and product terms?

[@elainerubinstein7610]

Your videos have been extremely helpful. Is it possible to get transcripts for any of them? Thanks! Elaine

[@guilllouv]

Thanks! I encountered a problematic case though, what do you do when y~x is an horizontal line? Then ŷ is constant, and you can't perform the White's test? Wouldn't generalized least squares be able to tell about heteroscedasticity more generally?

[@nichananwanchai9910]

thank you so much

[@kristopherkellaway3031]

nice job Ben.

[@ngkiu1183]

That's awesome n useful!! Thank you Ben!

[@5minuteFin]

Hi there, Thank you so much for your lectures. I am working on a data set of stocks return which I have already converted into log returns in Excel then imported it in the Eviews. I am facing the problem of heteroskedasticity even after changing it the estimation option at Huber-white and then Breush pagan test which shows improved values but still heteroskedastic. I am confused with if I can use log log model or not because the data has already been transformed into log model. however if I use Harvey method my results seems to have homoskedacity. waiting for your reply. Thank you so much for the good work.

[@troysullivan9404]

At about the 6:30 mark, Ben says that the product terms in the x regression are subsumed by the y^2 term in the White test. Can anyone explain for me why that is?
Is it related to the fact that we have assumed that there are no serial correlations in xi in our y_hat model?
Thank you,

[@kielanlemoine-kowalski8172]

I think you're overthinking it. The X terms are assumed because Y hat represents those x terms (i.e., y is a product of all those x terms)

[@LordOfNoobstown]

I was thinking the same, why would we also have interaction terms by using y_hat and y_hat^2 ...

[@seanstroud5107]

Df for f-test? is it F k, n-(k+1)?
Where k is the number of variables in Aux regression

[@Web3Future333]

Thanks greetings from Mexico

[@andrewelmarj3351]

Thank you so much !!

[@rahmatdavies]

Nice lectures

[@saithiha525]

Thanks a lot it is very helpful

[@piotrp88]

Thank you for this video and the one about the Breusch-Pagan test. I read the original two articles (from White and from Breusch and Pagan), but the theory seems a little more complex than your explanation and it seems quite difficult for me to reconduct to your learning. Is there a reference from where I can read what you taught in the video? Just for completeness.
Many thanks
Pietro

[@xiao6322]

THANKS AGAIN

[@ahmadfawzilafi]

amazing