Title page for etd-0629105-143720


[Back to Results | New Search]

URN etd-0629105-143720
Author Hung-Ming Lin
Author's Email Address No Public.
Statistics This thesis had been viewed 5067 times. Download 1678 times.
Department Applied Mathematics
Year 2004
Semester 2
Degree Master
Type of Document
Language English
Title On minimally-supported D-optimal designs for polynomial regression with log-concave weight function
Date of Defense 2005-05-26
Page Count 15
Keyword
  • log-concave
  • Gershogorin Circle Theorem
  • minimal-supported desing
  • approximate D-optimal desing
  • weighted polynomial regression
  • Abstract This paper studies minimally-supported D-optimal designs for polynomial regression model with logarithmically concave (log-concave) weight functions.
    Many commonly used weight functions in the design literature are log-concave.
    We show that the determinant of information matrix of minimally-supported design is a log-concave function of ordered support points and the D-optimal design is unique. Therefore, the numerically D-optimal designs can be determined e┬▒ciently by standard constrained concave programming algorithms.
    Advisory Committee
  • Mong-Na Lo Huang - chair
  • Mei-Hui Guo - co-chair
  • Fu-Chuen Chang - advisor
  • Files
  • etd-0629105-143720.pdf
  • indicate access worldwide
    Date of Submission 2005-06-29

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys