On Feb 18, 2011, at 14:20 , Jan wrote:
One of the references you googled suggests that intercepts should never be omitted. Is this true even if I know that the physical reality behind the numbers suggests an intercept of zero?
No. That'll be a piece of pragmatic advice caused by the experience that people too often get it wrong and e.g. try to remove anything with a high p-value from a model. If your model meaningfully implies a zero intercept, as it does in some physical and biological models (no displacement at time zero, no growth at zero sunlight, etc.) then of course you can fit a model that incorporates this knowledge.
Peter Dalgaard, Professor, Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: pd.mes at cbs.dk Priv: PDalgd at gmail.com