Urgent question centering regressor

#1
Dear community,

I have a very urgent question. Do I center a regressor before I exclude outliers from the dependent variable or after? It would change the mean of the regressor because the data points that are an outlier for the dependent variable, their value of the regressor wil not be included in the mean of the regressor that is used to center it. Is there a convention in what order it should be done?

I hope I put my question in words correctly.

I would apppreciate every hint very much.
 

hlsmith

Not a robit
#2
For clarification, you are asking if you should center your independent variable before examining whether you should remove outliers?

Why do you want to get rid of outliers? Do you have a reason to believe they are not valid? What is this analysis for, is it homework or real life analysis?
 
#3
For clarification, you are asking if you should center your independent variable before examining whether you should remove outliers?

Why do you want to get rid of outliers? Do you have a reason to believe they are not valid? What is this analysis for, is it homework or real life analysis?
Thanks for your response. It is the data for my bachelor thesis. I have concrete reasons to think they are not valid. Yes this is my question. The outliers are not in the independent variable but in the dependent variable (but as they are linked, values of the indenepent regressor would be excluded as well und thus change the mean with which I want to center the independent variable)
 

hlsmith

Not a robit
#4
Depends on the issue, but I didn't think centering data would get rid of an outlier - it just rescales it, right.

Were you always planning to center the variable or just because of this?

Well if it is a truly erroneous value that is nonsensical, just delete it and document that you did this. Make this very transparent. The removal of presumed outliers is one of the etiologies of the Flint MI water crisis.