Two Stage Least Squares - example

This video provides an example of 'Two Stage Least Squares' estimation. 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....

[@RogerKlauser]

That explanation at the end was money. Definitely going to help me w/ my econometrics final this Sat!

[@brandonjacobs5452]

Ben, brother, you are saving my life right now

[@olivier306]

This belongs in a museum

[@patiencedzigbordiakosuakor5171]

Thanks a lot. This is going to help me a lot in my current thesis.

[@vladrosca6785]

Thank you very much, Ben!

[@fancy841014]

You explain the concept so clearly! Thx a lot!

[@AnevaSee]

Thanks. great ideas are explained with simple words, perfect!

[@3foss191]

Thks grand Prof.

[@dhruvsadarangani755]

thanks love your videos

[@rudraguha4618]

Thank you so much for your work.Helped a lot :)

[@filippopovic8514]

Dear all,
I would really appreciate if someone could explain me why does Ben include SAT variable in estimating CA in first stage of 2SLS. Aren't distance and quality of public transportation enough to estimate CA.
Thanks

[@MrThefonzzi]

Yeah... why does he include SAT in CA? Would you get highly correlated estimates in the new regression? i.e. beta1 and beta2 being highly correlated...

[@SomethingSoOriginal]

I also would like to know this

[@jzureich2121]

Filip Popovic I have been wondering the same thing. I think it may have something to do with the fact we have already established/assumed it has a 0 covariance with the error term in which case it is beneficial to include in the first stage of regression.

[@fjosh457]

it is a significant variable for the data generation process of scores. That reflects previous knowledge and background of some particular topic. even tough attendance for some particular students is zero; then scores would be influenced by IQ or any other training in the past.

[@ireneisme8747]

But how can we know INTEREST is in the error term, what if DISTANCE, PTRANS are also in the error term?

[@62294838]

This is sooooo good an explanation!!

[@njungohfozaopascaline6277]

Thanks very much. It helped

[@karlkani9]

Very Helpful, thank you very much !!

[@sarahyuan8635]

Thank you

[@Noelson]

If you regress CA on SAT and IVs and find out that the coefficient of SAT is significant, isn't that suggesting multicollinearity which should have been avoided?

[@SomethingSoOriginal]

+Yuchen Li Yeah that's what i was wondering to, why SAT is included in the first-stage

[@yanfengli4821]

Yes, I am wondering too. Can anyone explain why include SAT in both first and second stage? I think in the second stage, CA hat and SAT will have multicolinearity problem.

[@mm22sapphire50]

hi! can you use the lagged value of the endogenous variable as an instrument using 2SLS model

[@patiencedzigbordiakosuakor5171]

Also interested to know

[@lemonsqueezy09]

Wow when you say "Exogenous " contra "Endogenous", they sound really familiar.

[@SomethingSoOriginal]

Thanks, very helpful

[@Lukas-md3bk]

You rock dude!!

[@faithlangat2510]

awesome