Bootstapping in curve fitting

Hi all,

 I am facing a problem in interpreting the results of bootstrap in curve fitting. I have a set of raw data. I have resampled the data set for 1000 times using bootstrap technique and for each time I have fitted 5 different types of curve (linear, poly2, poly3, poly4 and poly5) and got the coefficients. I have computed the mean and standard deviations of the coefficients of each type. Now how can I decide which one is the best fit?