PubMed · 16374307
The source did not provide an abstract. Follow the original record for more information.
Explore connections, maps & timelines
Mark O M Tso, Morton F Goldberg, Gordon Gund. 2005. Preface.. https://doi.org/10.1097/00006982-200512001-00001
Cite the original work for its findings. Save a collection to share your selection of sources.
KEEP EXPLORING
This paper addresses the modelling of missing covariate data with the logistic regression model. The aim of this paper is to evaluate the properties of an efficient score for logistic regression in a two-phase design. Simulation studies show that the efficient score is more efficient than two other pseudo-likelihood methods when the correlation between the missing covariate and its surrogate is high or the sampling proportion is small. These methods are illustrated with data from the National Wilms Tumor Study Group. Results from the example confirm the simulation study findings with the exception that the pseudo-likelihood approach produces more reliable estimates than the weighted pseudo-likelihood approach.
A tree procedure is proposed to check the adequacy of a fitted logistic regression model. The proposed method not only makes natural assessment for the logistic model, but also provides clues to amend its lack-of-fit. The resulting tree-augmented logistic model facilitates a refined model with meaningful interpretation. We demonstrate its use via simulation studies and an application to the Pima Indians diabetes data.
BACKGROUND: Recently it was reported that a Swedish professor in environmental health has for decades worked as a consultant for Philip Morris without reporting his employment to his academic employer or declaring conflicts of interest in his research. The potential for distorting the epidemiological assessments of hazard and risk through paid consultants, pretending to be independent, is not exclusive to the tobacco industry. METHODS: Documentation is drawn from peer reviewed publications, websites, documents from the Environmental Protection Agency, University reports, Wellcome Library Special Collections and the Washington Post. RESULTS: Some consulting firms employ university researchers for industry work thereby disguising industry links in the income of large departments. If the industry affiliation is concealed by the scientist, biases from conflicting interests in risk assessments cannot be evaluated and dealt with properly. Furthermore, there is reason to suspect that editors and journal staff may suppress publication of scientific results that are adverse to industry owing to internal conflict of interest between editorial integrity and business needs. CONCLUSIONS: Examples of these problems from Sweden, UK, and USA are presented. The shortfalls cited in this article illustrate the need for improved transparency, regulations that will help curb abuses as well as instruments for control and enforcement against abuses.