Regression for Binary DV and Ordinal IV?

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

Posts: 1
Joined: Fri Sep 19, 2014 4:03 pm

Regression for Binary DV and Ordinal IV?

Postby Bfernandez » Fri Sep 19, 2014 4:15 pm

Hi guys!

Just started at a new company having graduated this year, theyve got me analysing data and producing some key driver analytics. Thing is, although ive been studying econometrics for years its always been with a tutor checking results, where as now i'm producing results which shape reports and go straight to the client; I'm slightly apprehensive that I'm going to mess up! Furthermore the first project i'm doing has categorical IV and DV, i'm used to analysing nice linear data! Would anyone be able to offer a bit of advice? FYI, using SPSS (albeit an ancient version)

Two cases; firstly, I have binary DV's and ordinal IV's, i'm using a binary logit regression, I am interpreting the Cox & Snell R-squared value as the model fit (as a %), and (Exp(B)-1)*100 as the % increase in the DV per unit the IV increase. Is this right?

In the second case I have Ordinal IV's and DV's and am using an Ordinal Logit, similar interpretation.

If anyone has any help/advice, or suggestions for where I could find some good material for marketing/key driver analysis that would be amazing!

Thank you!


Who is online

Users browsing this forum: No registered users and 3 guests