Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


ucin1227293204.pdf (1.63 MB)

ETD Abstract Container

Abstract Header

Bayesian Solution to the Analysis of Data with Values below the Limit of Detection (LOD)

Jin, Yan
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1227293204

Abstract Details

2008, PhD, University of Cincinnati, Arts and Sciences : Mathematical Sciences.
In this dissertation, Bayesian solutions have been given to the repeated measure model (chapter II), the nested random effects repeated measure model (chapter III), the mixture model consisting of a censored lognormal distribution and a point mass distribution (chapter IV), and the mixture model with random effects (chapter V), for the analyses of data with values below the Limit of Detection (LOD). The Markov chain Monte Carlo methods (Gibbs sampler and Metropolis-Hastings algorithm) were implemented to generate posterior samples for model parameters from the full conditional distributions. The Deviance Information Criterion (DIC) was calculated in MCMC in order to compare the fit and complexity between Bayesian models. SAS macros written in PROC IML were developed to output Bayesian estimates and the DICs for all the models discussed in this dissertation.
James A. Deddens, PhD (Committee Chair)
Siva Sivaganesan, PhD (Committee Member)
Paul S. Horn, PhD (Committee Member)
Xiaodong Lin, PhD (Committee Member)
Seongho Song, PhD (Committee Member)
92 p.
Mathematics; Statistics
Bayesian; Censored data; Limit of detection; LOD; Censoring; Repeated measure; Nested random effects; Mixture model; Gibbs sampling; Metropolis-Hastings algorithm; DIC

Recommended Citations

Citations

  • Jin, Y. (2008). Bayesian Solution to the Analysis of Data with Values below the Limit of Detection (LOD) [Doctoral dissertation, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1227293204

    APA Style (7th edition)

  • Jin, Yan. Bayesian Solution to the Analysis of Data with Values below the Limit of Detection (LOD). 2008. University of Cincinnati, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1227293204.

    MLA Style (8th edition)

  • Jin, Yan. "Bayesian Solution to the Analysis of Data with Values below the Limit of Detection (LOD)." Doctoral dissertation, University of Cincinnati, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1227293204

    Chicago Manual of Style (17th edition)

ucin1227293204
901
© 2008, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.