Frankenstein Functions

I read a great article on math-blog.com under history. ( http://math-blog.com/2010/10/12/frankenstein-functions/ )  The article talks about over complication of new ideas normally lead to mistakes.  When you are making the best conjectures keep them simple.  The same happens in statistics under extrapolation.  The higher degree polynomial we fit for prediction, the better we will predict the data set.  When using the high degree polynomial for predictions you will find the function useless.  The same goes for confounding factors in multiple regression.  Keep things simple including only variables that relate scientifically and you will most likely produce your best model.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s