Penalized least squares for single index models

@inproceedings{Peng2010PenalizedLS,
  title={Penalized least squares for single index models},
  author={Heng Peng and Tao Huang},
  year={2010}
}
The single index model is a useful regression model. In this paper, we propose a nonconcave penalized least squares method to estimate both the parameters and the link function of the single index model. Compared to other variable selection and estimation methods, the proposed method can estimate parameters and select variables simultaneously. When the dimension of parameters in the single index model is a fixed constant, under some regularity conditions, we demonstrate that the proposed… CONTINUE READING
10 Citations
29 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 29 references

Generalized partially linear singleindexmodels

  • R. J. Carroll, J. Fan, I. Gijbels, M. P. Wand
  • Journal of the American Statistical Association
  • 1997
Highly Influential
11 Excerpts

Slicing regression : a linkfree regression method

  • N. Duan, K.-C. Li
  • Annals of Statistics
  • 1991
Highly Influential
7 Excerpts

Semiparametric estimation of index coefficients

  • J. L. Powell, J. M. Stock, T. M. Stoker
  • Science in Sports and Exercise
  • 1989
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…