1. Zhang, X., Mai, Q. and Zou, H. (2018). The maximum separation subspace in sufficient dimension reduction with categorical response. Submitted.
2. Mai, Q. and Zhang, X. (2019+). An iterative penalized least squares approach to sparse canonical correlation analysis. Biometrics, accepted.
See the Software section at the bottom of this page for implementation of sparse canonical correlation analysis.
3. Zhang, X. and Mai, Q. (2019+). Efficient integration of sufficient dimension reduction and prediction in discriminant analysis. Technometrics, accepted.
4. Pan, Y.*, Mai, Q. and Zhang, X. (2019+). Covariate-adjusted tensor classification in high dimensions. Journal of the American Statistical Association, accepted.
5. Mai, Q. , Yang, Y. and Zou, H. (2019). Multiclass sparse discriminant analysis. Statistica Sinica, 29, 97-111.
6. Zhang, X. and Mai, Q. (2018). Model-free envelope dimension selection. Electronic Journal of Statistics, 12, 2193-2216.
7. Mai, Q. and Zou, H. (2015). The fused Kolmogorov filter: a nonparametric model-free screening method. The Annals of Statistics, 43, 1471-1497.
8. Mai, Q. and Zou, H. (2015). Semiparametric sparse discriminant
analysis. Journal of Multivariate Analysis, 35, 175-188.
9. Mai, Q., and Zou, H. (2014). Nonparametric variable transformation in sufficient dimension reduction. Technometrics, 57, 1-10.
10. Mai, Q. (2013). A review of discriminant analysis in high dimensions. Wiley Interdisciplinary Reviews: Computational Statistics, 5, 190-197.
11. Mai, Q., and Zou, H. (2013). A note on the equivalence of three sparse
linear discriminant methods. Technometrics, 55, 243-246.
12. Mai, Q., and Zou, H. (2013). The Kolmogorov filter for variable
screening in high-dimensional binary classification. Biometrika, 100, 229-234.
13. Mai, Q., Zou, H. and Yuan, M. (2012). A direct
approach to sparse discriminant analysis in ultra-high dimensions.
Biometrika, 99, 29-42.
R packages:
dsda: performs direct sparse discriminant analysis.
msda: performs multiclass sparse discriminant analysis.
catch: performs covariate-adjusted tensor classification.
SCCA: performs sparse canonical correlation. This package contains all the functions to reproduce the results in our paper. But if you want to play more with our method,
such as cross validation with unequal tuning parameters, you can use the code in the file SCCA-code with the readme file and the example.