Statistical methods for colon carcinogenesis /
An important problem in studying the etiology of colon cancer is understanding the relationship between DNA adduct levels in cells within colonic crypts in distal and proximal parts of the colon, following treatment with a carcinogen and different types of diets. In particular, it is important to u...
| Main Author: | |
|---|---|
| Format: | Thesis Book |
| Language: | English |
| Published: |
[Place of publication not identified] :
[publisher not identified] ;
2000.
|
| Subjects: | |
| Online Access: | http://proxy.library.tamu.edu/login?url=http://proquest.umi.com/pqdweb?did=727726351&sid=1&Fmt=2&clientId=2945&RQT=309&VName=PQD |
| Summary: | An important problem in studying the etiology of colon cancer is understanding the relationship between DNA adduct levels in cells within colonic crypts in distal and proximal parts of the colon, following treatment with a carcinogen and different types of diets. In particular, it is important to understand whether rats who have elevated adduct levels in particular positions in distal region crypts also have elevated levels in the same positions of the crypts in proximal regions, and whether this relationship depends on diet. I cast this problem as estimating the correlation function of two responses as a function of a covariate for studies where both responses are measured on the same experimental units but not the same subsampling units. The measurements of the responses are taken at the subsampling level for various levels of the covariate. Parametric and nonparametric methods are developed and applied to a data set from an ongoing study, leading to potentially important and surprising biological results. Theoretical calculations suggest that the nonparametric method, based on nonparametric regression, should in fact have statistical properties nearly the same as if the functions nonparametrically estimated were known. This analysis was based on using a proxy for the true value of the covariate. Given a partial sample of true covariates, the analysis was redone from a Bayesian perspective accounting for the unusually structured missing data, with little change in results. |
|---|---|
| Item Description: | Vita. "Major Subject: Statistics". |
| Physical Description: | xi, 61 leaves : illustrations ; 28 cm. Issued also on microfiche from University Microfilm Inc. |
| Bibliography: | Includes bibliographical references (leaves 46-47). |