MLE or NLS in Multiple Ordered Regression

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

Whitefeather
Posts: 3
Joined: Fri Apr 18, 2014 9:13 am

MLE or NLS in Multiple Ordered Regression

Postby Whitefeather » Fri Apr 18, 2014 9:23 am

Hi,

I'm writing my bachelor thesis together with two lovely girls at Lunds University. It's regarding credit ratings and am now trying to learn some econometrics.

We need to do a Multiple Ordered Regression and for me to understand what the computer really does I need to know if Eviews8 uses NLS (Non linear least square) or MLE (Maximum likelihood estimation) to calculate it/to make the regression?

I also wonder which tests that are reasonable/interesting/vital for a Multiple Ordered Regression? Wald, coefficient matrix and a normality check of the residuals with a histogram?

Attached is my work file if it helps you help me.

Extremely thankful for help and Happy Easter to all of you!

PS. recently stumbled across econometrics and eviews and I'm loving it, don't kill this feeling ;P
Attachments
Rating_G.xlsx
My work file
(19.05 KiB) Downloaded 294 times

Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 23 guests