Bootstrapping made easy (wonkish)

LARS P. SYLL


In Gretl it’s extremely simple to do this kind of bootstrapping. Run the regression and you get an output-window with the regression results. Click on Analysis at the top of the window and then on Bootstrap and select the options Confidence interval and Resample residuals. After having selected the coefficient for which you want to you get bootstrapped estimates, you just clickOK and a window will appear showing the 95% confidence interval for the coefficient. It’s as simple as that!

View original post

Author: Damian Merciar

Damian Merciar is Managing Director of Merciar Business Consulting, http://www.merciar.com, a niche business economics consultancy founded in 1998. He has over twenty years experience in the areas of commercial Business Strategy. He is experienced in the transition environments of nationalized to private sector state utilities and the senior practice of commercial management, advisorial consultancy, and implementation. He has carried out policy advisory work for government ministries and been an adviser to institutional bodies proposing changes to government. He holds an MSc Economics from the University of Surrey’s leading Economics department and an MBA from the University of Kent. Also attending the leading University in the Middle East, studying International Relations and Language, for which he won a competitive international scholarship, and has a BA (Hons) in Economic History and Political Economy from the University of Portsmouth. He is currently based in London.

Leave a Reply

Fill in your details below or click an icon to log in:

Gravatar
WordPress.com Logo

You are commenting using your WordPress.com account. ( Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. ( Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. ( Log Out /  Change )

Cancel

Connecting to %s

%d bloggers like this: