Outcome modelling strategies in epidemiology: traditional methods and basic alternatives

Outcome modelling strategies in epidemiology: traditional methods and basic alternatives

Controlling for too many potential confounders can lead to or aggravate problems of data sparsity or multicollinearity, particularly when the number of covariates is large in relation to the study size. As a result, methods to reduce the number of modelled covariates are often deployed. We review several traditional modelling strategies, including stepwise regression and the 'change-in-estimate...

Modelling Methods for Evaluating Alternatives

Epidemiology of pemphigus and treatment outcome in Kerman

The usual outcome of pemphigus whitout treatment is death. The introduction of corticosteroids has greatly reduced the mortality of this condition, though a significant morbidity remains. The patients who are receiving high- dose steroids together with other immunosuppressive agents are at risk and may cause death through drug side effects and opportunitic infections. The descriptive study has ...

[Traditional epidemiology, modern epidemiology and public health].

There have been significant developments in epidemiologic methodology during the past century, including changes in basic concepts, methods of data analysis, and methods of exposure measurement. However, the rise of modern epidemiology has been a mixed blessing, and the new paradigm has major shortcomings, both in public health and scientific terms. The changes in the paradigm have not been neu...

Alternatives to animal experimentation in basic research.

In contrast to animal testing required by law to guarantee minimum safety standards for the licensing of drugs and chemicals, there are no regulations in basic research forcing scientists to perform animal tests. By (usually) free choice, questions are posed and hypotheses are examined which, in many cases, can only be answered by means of animal tests. Just as easily, different questions could...