"Tolerance = .000 limits reached" during hierarchical regression due to 1 control variable

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

hierarchregress
Posts: 1
Joined: Thu Apr 14, 2016 8:47 am

"Tolerance = .000 limits reached" during hierarchical regression due to 1 control variable

Postby hierarchregress » Thu Apr 14, 2016 9:01 am

Dear all,

perhaps you can help me with one problem.
I am conducting a hierarchical regression (First block: controls; second block: main effects; third block: moderations; fourth block: three-way-interactions) with a sample N = >500.

The model is running smoothly including a number of different controls (for dummy variables, I integrate one less dummy than there are categories that are represented).
I can even add more controls and the model is still working.

However, whenever I add a control variable such as GDP/capita (gross domestic product) in any form (ln, normal, ...) I get the error "Tolerance = .000 limits reached" and another variable gets kicked out during the calculation. I have tried this with other similar variables such as HDI (human development index) etc. with the same result

The sample consists of responses from individuals from 4 countries, thus I have 4 different values of GDP only. At the same time, two of my moderator variables are cultural dimensions (e.g. "uncertainty avoidance") which are characterized also by the country of the respondent. Thus, there I also have 4 different values.

I cannot kick out the two moderator variables and I need to have them included simultaneously in the model.

Do you know of any other ways to get the model running?
Thanks for your help!!!
GerineL
Moderator
Posts: 1477
Joined: Tue Jun 10, 2008 4:50 pm

Re: "Tolerance = .000 limits reached" during hierarchical regression due to 1 control variable

Postby GerineL » Mon Apr 18, 2016 12:10 pm

This means that there is some redundency in your model.
Could it be that you have for instance a variable for country, and this perfectly corresponds to for instance GDP?
i.e., if country is 2, GDP is always 3?

Who is online

Users browsing this forum: No registered users and 3 guests

cron