Name
Abstract | ||
|---|---|---|
Sufficient dimension reduction methods, such as the sliced inverse regression one (SIR) and the sliced average variance estimate one (SAVE), usually put restrictions on the regressor: X being elliptical or normal. We propose a new effective method, called the generalized gradient direction method (GGD), for solving sufficient dimension reduction problems. Compared with SIR, SAVE etc., GGD makes very weak assumptions on X and performs well with X being a continuous variable or a numerical discrete variable, while existing methods are all developed with X being a continuous variable. The computation for GGD is very simple, just like for SIR, SAVE etc. Moreover, GGD proves robust compared with many standard techniques. Simulation results in comparison with results from other methods support the advantages of GGD. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1016/j.csda.2009.10.019 | Computational Statistics & Data Analysis |
Keywords | Field | DocType |
sliced inverse regression,standard technique,numerical discrete variable,generalized gradient direction method,sliced average variance estimate,continuous variable,simulation result,sufficient dimension reduction method,sufficient dimension reduction problem,new effective method,direct method,dimension reduction | Gradient method,Econometrics,Dimensionality reduction,Effective method,Regression analysis,Sliced inverse regression,Statistics,Numerical analysis,Sufficient dimension reduction,Mathematics,Computation | Journal |
Volume | Issue | ISSN |
54 | 4 | Computational Statistics and Data Analysis |
Citations | PageRank | References |
0 | 0.34 | 1 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Junlong Zhao | 1 | 0 | 2.37 |
| Xiuli Zhao | 2 | 0 | 0.34 |