Dr Pi-Wen Tsai [cv in Chinese]


Address : Department of Mathematics [web]

National Taiwan Normal University [web]
88, Section 4, Ting Chou Road,
Taipei 116, Taiwan, ROC.
Telephone: +886 (0)2 7734 6615
Fax: +886 (0)2 2933 2342
E-Mail: pwtsai@math.ntnu.edu.tw

蔡碧紋的行事曆

Teaching


98 學年度 機率導論, 統計方法 (I)

   Taught courses
Some useful links:
  Statistcal Package: R
  A Simple Guide to Latex/Lyx: Rice University
  大 家來學 LaTeX By Edward G. J. Lee 李果正老師

EDUCATION

Ph.D. Applied Statistics, The University of Reading, UK.
M.Sc. Industrial Engineering and Management, National Chiao-Tung University, Taiwan.
B.Sc.. Industrial Engineering and Management, National Chiao-Tung University, Taiwan.

PROFESSIONAL EXPERIENCE

Assistant Professor Aug 06 to present Department of Mathematics, National Taiwan Normal University.
Assistant Investigator Aug 04 to July 06 Division of Biostatistics and Bioinformatics, National Health Research Institutes.
Postdoctoral fellow Sep 02 to Aug 04 Institute of Statistical Science, Academia Sinica.
Assistant Professor May 02 to July 02 Department of Finance and Banking, Yuda Institute of Business Technology.

RESEARCH INTERESTS

Design and analysis of microarray gene expression data

The design aspect of microarray experiments is extremely important. We have identified a feature that the array is a plot and that some microarray inferences involve subplot comparisons and some involve between-plot comparisons. The recognition of the error structure has important implications for the choice of design, power and sample size.
Design of experiments --- generalized criteria for multifactor experimental designs under model uncertainty

Traditionally, factor-screening designs have been used for studying main effects only, by assuming that the interactions are negligible. We went beyond this tradition by considering designs that allow efficient estimation of two-factor interactions as well as main effects. We developed a criterion based on the average performance of a design over the low-dimensional sub-models to compare designs when experimenters do not in advance know what the final model is. Many new and efficient designs were found. This criterion is currently revisited and extended with an idea exploiting prior information about model uncertainty. In addition, the relationships between these criteria and other related criteria are explored.


Documents and programs for Tsai and Gilmour (2009)

Links for R and some outputs.

PUBLICATIONS

  1. Li, J.-W., Yeung, C. K.-L., Tsai, P.-W., Lin, R.-C., Yeh, C.-F., Yao, C.-T., Le, M.-H., Han, L., Wang, Q.-S, Ding, P., Li, S.-H. (2010) Rejecting strictly allopatric speciation on a continental island: Prolonged post-divergence gene flow between Taiwan (Leucodioptron taewanus, Passeriformes Timaliidae) and Chinese (L. canorum canorum) hwameis, Molecular Ecology (to appear)

  2. Tsai, P.-W. and Gilmour, S.G. (2010) A General Criterion for Factorial Designs under Model Uncertainty, Technometrics (to appear).

  3. Cheng, C.-S. and Tsai, P.-W. (2009) Optimal Two-Level Regular Fractional Factorial Block and Split-Plot Designs. Biometrika. 96, 83-93. [pdf]

  4. Tsai, P.-W., Gilmour,S.G. and Mead,R. (2007) Three-level designs exploiting prior information about model uncertainty. J. Statist. Planng. Inf. 137, 619-627. [pdf]

  5. Tsai, P.-W., Gilmour, S.G. and Mead, R. (2006) Statistical isomorphism of three-level fractional factorial designs. Utilitas Mathematica, 70, 3-9. [pdf]

  6. Tsai, P.-W. and Lee, M.-L. T. (2005) Split-plot microarray experiments: issues of design, power and sample size. Applied Bioinformatics, 4, 187-194.

  7. Tsai, P.-W., Gilmour, S.G. and Mead, R. (2004) Some new three-level orthogonal main effects plans robust to model uncertainty. Statistica Sinica, 14, 1075-1084. [pdf]

  8. Tsai, P.-W., Gilmour, S.G. and Mead, R. (2000) Projective three-level main effects designs robust to model uncertainty. Biometrika, 87, 467-475. [pdf]

  9. Tsai, P.-W.(1998) Three-level designs robust to model uncertainty. PhD thesis. The University of Reading. U.K.

  10. Tsai, P.-W., Gilmour, S.G. and Mead, R. (1996) Letters to the Editors: An alternative analysis of Logothetis's plasma-etching data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 45 , 498-503. [pdf]

  11. Tsai, P.-W., Gilmour, S. G. and Mead, R. (1996) An alternative analysis of Logothetis's plasma-etching data. Technical Report 96/2, Applied Statistics. The University of Reading. U.K.

Recent Presentations



Taught Courses
97 (II) 統計計算專題, 統 計學一
97 (I) 機率導論, 統計方法 (I),, 導師時間
96 (II) Calculus II, Statistics I
96 (I) Calculus I, Probability I, 導師時間[mentor]
95 (II) Calculus II, Probability & Statistics II , Applied Statistical Method I
95 (I)
 Calculus I, Probability & StatisticsI ,Applied Statistical Method I