Testing for Lack of Fit via the Generalized Neyman Smooth Test

  • Published : 1998.09.01

Abstract

Smoothing tests based on an L$_2$ error between a truncated courier series estimator and a true function have shown good powers for a wide class of alternatives, These tests have the same form of the Neyman smooth test whose performance depends on the selected order, a basis, the farm of estimators. We construct flexible data driven Neyman smooth tests by changing a basis, combining model selection criteria and different series estimators. A simulation study shows that the generalized Neyman smooth test with the best basis provides good power for a wider class of alternatives compared with other data driven Neyman smooth tests based on a fixed form of estimator, a fixed basis and a fixed criterion.

Keywords

References

  1. Technical Report Department of Statistics Automatic decomposition by basis pursuit Chen, S.;Donoho, D.
  2. Progress in Wavelet Analysis and Applications, Editions Frontieres Adapted waveform analysis and denoising Coifman, R.;Majid, F.;In Y. Meyer(eds.);R. Roques(eds.)
  3. Biometrika v.81 Ideal spatial adaptation by wavelet shrinkage Donoho, D.;Johnstone, I.
  4. Journal of the American Statistical Association v.91 Test of signifcance based on wavelet theresholding and Neyman's truncation Fan, J.
  5. Nonparameteric smoothing and Its Applications in Lack-of-Fit Testing Haet, J. D.
  6. Biometrika v.77 Asympototically potimal difference-based estimation of variance in nonparametric regression Hall, P.;Kat, T. W.;Titterington, D. M.
  7. Journal of Nonparameteric Statisticas v.7 Smoothing-based lack-of-fit tests: Mariations on a theme Kuchibhatla, M.;Hart, J. D.
  8. Journal of the American Statistical Association v.89 Data driven version of Neyman's smooth test of fit Ledwina, T.
  9. Ph. D. dissertation A Statistical Wavelet Approach to Model Selection and Data Driven Neyman Smooth Tests Lee, G. H.
  10. Statistics Probability Letters v.39 An L₂ Error Test with Order Selection and Thresholding Lee, G. H.;Hart, J. D.
  11. Annals of Statistics v.12 Bandwidth choice for nonprarametric regression Rice, J.
  12. Annals of Satistics v.24 Adaptive hypothesis testing using wavelets Pokoiny, V. G.