Nonparametric Estimation

Nonparametric Estimation - Economics 245A Project...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Economics 245A Project Nonparametric Density Estimation Standard Gaussian Density For a sample size of 50, both least-squares cross-validation (LSCV) and maximum- likelihood cross-validation (MLCV) have average smoothing parameter values that ex- h in accord with theory. The computation time is slight for both methods, although the longer time for MLCV is probably due to the grid search that I wrote (LSCV employs an IMSL opti- mization subroutine). Although faster, the IMSL optimization subroutine does present unique minimizing value of h . Expanding the initial search range from ( : 25 ; 1 : 00) to ( : 25 ; 1 : 50) results in a reported minimum for sample 3, but does not result in a unique minimum for samples 4 and 6. For these two samples, I restrict the search range to ( : 5 ; 1 : standard Gaussian density, in each case the resulting integrated squared error (ISE) is samples the minimum value in the range (.25) is selected. Each time the minimum bandwidth is selected, the ISE for LSCV is quite large. The three large values of ISE that occur with
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 12/26/2011 for the course ECON 245a taught by Professor Staff during the Fall '08 term at UCSB.

Page1 / 2

Nonparametric Estimation - Economics 245A Project...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online