Ph.D. (1995) University of North Carolina, Chapel Hill

Li-Shan Huang Associate Professor of Biostatistics     Contact Information: University of Rochester Dept of Biostatistics and Computational Biology 601 Elmwood Avenue Box 630 Rochester, New York 14642   Office: MRBX G-11311A Phone: (585) 275-2576 Fax: (585) 273-1031 E-mail: LHuang (at) bst.rochester.edu

Research Interests

My research focuses on nonparametric curve estimation, to relax assumptions on the form of the regression or density function. This is a flexible and useful approach that allows the data to determine a curve for itself. Applications of nonparametric techniques include time series and generalized linear models.

A different research interest involves environmental statistics. With the development of high-speed computers and computer graphics, one can better visualize the environmental data structure and analyze the nonhomogeneity present in data with appropriate statistical methods.

Technical reports

• Huang, L.-S. and Chen, J. (2005). Analysis of Variance, Coefficient of Determination, and F-test for Local Polynomial Regression. (Technical Report 05/02, revised August 2007). This paper has been accepted by The Annals of Statistics.
• Huang, L.-S. and Su, H. (2006). Nonparametric F-Tests for Nested Global and Local Polynomial Models.(Technical Report 06/08).
• He, H. and Huang, L.-S. (2006). Double-smoothing for Bias Reduction in Local Linear Regression (Technical Report 06/13).
• Huang, L.-S. and Davidson, P.W. (2007). Analysis of Variance and F-Tests for Partial Linear Models with Applications to Environmental Health Data (Technical Report 07/01).
      Abstract: For partial linear models, we study analysis of variance (ANOVA) inference tools and provide a unified framework covering estimation, ANOVA, and significance tests. Using the asymptotic projection matrix for local linear regression by Huang and Chen (2006), the new parametric estimator achieves root-n consistency, the new nonparametric estimate is in a form of a projection estimator, and together they can be viewed as penalized least squares estimators. The ANOVA decomposition explicitly gives the proportion of variation explained by fitting a partial linear model and separates the contributions from the parametric and nonparametric components. The ANOVA decomposition is utilized to construct semiparametric F-tests under the normality assumption. The proposed F-tests are applicable to testing significance of the parametric, nonparametric, or a combination of both terms. Simulation results demonstrate that the performance of the new estimators and semiparametric F-tests are comparable to alternative methods in practical applications. The methodology is applied to the Seychelles Child Development Study data to explore nonlinear relationships of prenatal methylmercury exposure through fish consumption during maternal pregnancy to child development.
  

Selected References

• Fan, J., Gijbels, I., Hu, T.-C. and Huang, L.-S. (1996). An asymptotic study of variable bandwidth selection for local polynomial regression. Statistica Sinica 6, 113-127.
• Huang, L.-S. (1997). Testing goodness-of-fit based on a roughness measure. Journal of the American Statistical Association 92, 1399-1402.
• Huang, L.-S. and Fan J. (1999). Nonparametric estimation of quadratic regression functionals. Bernoulli 5, 927-949.
• Huang, L.-S. and Smith, R.L. (1999). Meteorological-dependent trends in urban ozone. Environmetrics 10, 103-118.
• Fan, J. and Huang, L.-S. (1999). Rates of convergence for the pre-asymptotic substitution bandwidth selector. Statistics and Probability Letters 43, 309-316.
• Huang, L.-S. (2001). Testing the adequacy of a linear model via critical smoothing. Journal of Statistical Computation and Simulation 68, 281-294.
• Hall, P., Huang, L.-S., Gifford, J. and Gijbels, I. (2001). Nonparametric estimation of hazard rate under the constraint of monotonicity. Journal of Computational and Graphical Statistics 10, 592-614.
• Hall, P. and Huang, L.-S. (2001). Nonparametric kernel regression subject to monotonicity constraints. Annals of Statistics 29, 624-647.
• Fan, J. and Huang, L.-S. (2001). Goodness-of-fit tests for parametric regression models. Journal of the American Statistical Association 96, 640-652.
• Huang, L.-S. (2001). A roughness-penalty view of kernel smoothing. Statistics and Probability Letters 52, 85-89.
• Hall, P. and Huang, L.-S. (2002). Unimodal density estimation using kernel methods. Statistica Sinica 12, 965-990.
• Myers, G.J., Davidson, P., Cox, C., Shamlaye, C., Palumbo, D., Cernuchiarti, E., Sloane-Reeves, J., Wilding, G. E., Kost, J., Huang, L.-S., and Clarkson, T. (2003). Prenatal methylmercury exposure from ocean fish consumption in the Seychelles child development study. Lancet 361, 1686-1692.
• Huang, L.-S., Cox, C., Wilding, G.E., Myers, G.J., Davidson, P., Cernuchiarti, E., Sloane-Reeves, J., Shamlaye, C. and Clarkson, T. (2003). Using measurement error models to assess effects of prenatal and postnatal methylmercury exposure in the Seychelles child development study. Environmental Research 93, 115-122.
• Huang, L.-S., Wang, H., and Cox, C. (2005). Assessing interaction effects in linear measurement error models. Journal of the Royal Statistical Society Series C Applied Statistics 1, 21-30.
• Braun, W. J. and Huang, L.-S. (2005). Kernel spline regression. Canadian Journal of Statistics 33, 259-278.
• Huang, L.-S., Cox, C., Myers, G.J., Davidson, P., Cernuchiarti, E.,
  Sloane-Reeves, J., Shamlaye, C. and Clarkson, T. (2005). Exploring nonlinear association between prenatal methylmercury exposure
  from fish consumption and child development: Evaluation of
  the Seychelles Child Development Study nine-year data using
  semiparametric additive models. Environmental Research 97, 100-108.