Polychotomous regression applied to futility analysis and expected points modeling /
Polychotomous regression is an important topic in statistical research. I explore two main methodologies: tiered logistic regression and futility analysis. Concerning tiered logistic regression, I formulate a general model and use this model to estimate an expected points function. The expected p...
| Main Author: | |
|---|---|
| Format: | Thesis Book |
| Language: | English |
| Published: |
[Place of publication not identified] :
[publisher not identified] ;
2000.
|
| Subjects: |
| Summary: | Polychotomous regression is an important topic in statistical research. I explore two main methodologies: tiered logistic regression and futility analysis. Concerning tiered logistic regression, I formulate a general model and use this model to estimate an expected points function. The expected points function is applied to ranking NFL quarterbacks. My futility analysis research involves a Bayesian approach to clinical trials. Given a trial that is at an interim stage, I determine a predictive distribution of the unobserved observations and use this distribution to predict the probability that the treatment will be significant at the end of the trial. The research is based on a real-life study where the outcome variable was either 1, 2, 3, 4, or 5, representing the severity of a disease. |
|---|---|
| Item Description: | Vita. "Major Subject: Statistics". |
| Physical Description: | xiii, 125 leaves : illustrations ; 28 cm. Issued also on microfiche from Lange Micrographics. |
| Bibliography: | Includes bibliographical references (leaves 123-124). |