PubMed Health⌕ Search

Biomedical subjects

A B Troxel

Publications and source records attributed to A B Troxel.

5 recordsLinked to original sources
PubMed1997

Weighted estimating equations with nonignorably missing response data.

We propose weighted estimating equations for data with nonignorable nonresponse in order to reduce the bias that can occur with a complete case analysis. A survey concerning medical practice guidelines, malpractice litigation, and settlement provides the framework. The survey was sent to recipients in two waves: those who responded on the first or second wave are used to estimate a nonignorable nonresponse model, while the fraction of recipients who never responded is used to allow the percentage of missing data to change with each wave. We use the structure of the GEE of Liang and Zeger (1986, Biometrika 73, 13-22), adding weights equal to the inverse probability of being observed. We present simulations demonstrating the bias that can occur with an unweighted analysis and use the survey data to illustrate the methods.

Bias↗
PubMed1993

Phase II study of goserelin for patients with postmenopausal metastatic breast cancer.

PURPOSE: To determine the response rate of postmenopausal breast cancer patients to the gonadotropin-releasing hormone (GN-RH) agonist, Zoladex (goserelin; ICI Pharma, Wilmington, DE). PATIENTS AND METHODS: A multi-institutional single-agent trial in postmenopausal patients was conducted. Serum levels of follicle-stimulating hormone (FSH), testosterone, and estradiol were requested before and after Zoladex treatment. RESULTS: For estrogen receptor-positive (ER+) patients, the response rate was 11%, with one complete response (CR) and three partial responses (PRs) among 36 eligible patients. Responses were of short duration. There were no responses among 16 estrogen receptor-negative (ER-) patients. CONCLUSION: GN-RH agonists have activity in ER+ postmenopausal patients, but response rates are not as high as with other available endocrine therapies and the duration of response is short.

Aged↗
PubMedDate not supplied

Statistical analysis of quality of life with missing data in cancer clinical trials.

We summarize issues that arise when considering quality of life (QOL) data in cancer clinical trials, especially those related to missing data. We describe different types of missing data mechanisms, and discuss ways of assessing and testing missing data mechanisms. A section on presentation of study design and results describes how graphical displays can effectively document the extent of the missing data problem, as well as describe its impact on interpretation of results. Finally, we describe several different statistical methods used to analyse repeated measures, with an emphasis on their properties and their ability to adequately handle different types of missing data mechanisms. We make recommendations as to the most appropriate methods, and suggest important directions for future research.

Data Interpretation, Statistical↗
PubMedDate not supplied

A comparative analysis of quality of life data from a Southwest Oncology Group randomized trial of advanced colorectal cancer.

Longitudinal quality of life measurements from an advanced-stage cancer clinical trial are analysed using a variety of methods, and the results compared. The methods used require different assumptions about the mechanism that produces the missing data. They include analyses that require the data to be missing completely at random; fixed-effects models and weighted generalized estimating equations, which require missing at random data; and a fully parametric approach where the outcomes and the missingness mechanism are jointly modelled, allowing non-ignorable missing data. The data show evidence of non-random missingness, but a formal test of non-ignorable missing data is not significant.

Colorectal Neoplasms↗