Selecting the Best Linear Model using Resampling

The link below is to an Excel spreadsheet that fits a linear statistical model to data of the form

,

where Y_i is the ith observation and X_ij is the observed value of the jth explanatory variable in the ith observation. The errors are mutually independent and normally distributed:

~ .

The spreadsheet also implements resampling methods discussed in Cheng (2009) for selecting the best subset of explanatory variables using Mallow’s statistic.

Here is the link: Linear Model Fitting

Reference: Cheng, R.C.H. ‘Computer Intensive Model Building’, Chapter 3 in ‘Advancing the Frontiers of Simulation’, Eds C. Alexopoulos, D. Goldsman and J. R. Wilson, Springer International Series in Operations Research and Management Science, Vol 133. (2009).