Tags:
create new tag
, view all tags, tagging instructions

Rescaled Predictors

In regression models with a numeric predictor, the estimated effect is that associated with a 1 unit increase in the predictor. In some cases, one unit may be too small or too large to be readily interpretable. Our regression modeling macros attempt to detect this situation and supplement the results with the estimated effect associated with increases that may be more easily interpretable. For example, an estimated effect associated with every 1 year increase in age may be supplemented with a line showing the rescaled effect per 10 year increase in age. This is not an additional predictor, but just another way of presenting the same age effect shown on the line above.

Topic revision: r4 - 14 Apr 2009 - 17:30:45 - CTSpediaAdmin
 

Copyright & by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding CTSPedia? Send feedback