Abstract
In this note, we revisit the single-index model with heteroscedastic error, and recommend an estimating equation method in terms of transferring restricted least squares to unrestricted least squares: the estimator of the index parameter is asymptotically more efficient than existing estimators in the literature in the sense that it is of a smaller limiting variance.
Original language | English |
---|---|
Pages (from-to) | 1898-1901 |
Number of pages | 4 |
Journal | Journal of Multivariate Analysis |
Volume | 101 |
Issue number | 8 |
DOIs | |
Publication status | Published - Sept 2010 |
Scopus Subject Areas
- Statistics and Probability
- Numerical Analysis
- Statistics, Probability and Uncertainty
User-Defined Keywords
- Asymptotical efficiency
- Least squares estimation
- The single-index model