Frequent methodological errors in clinical research. / Errores metodológicos frecuentes en la investigación clínica.

Several errors that are frequently present in clinical research are listed, discussed and illustrated. A distinction is made between what can be considered an "error" arising from ignorance or neglect, from what stems from a lack of integrity of researchers, although it is recognized and documented that it is not easy to establish when we are in a case and when in another. The work does not intend to make an exhaustive inventory of such problems, but focuses on those that, while frequent, are usually less evident or less marked in the various lists that have been published with this type of problems. It has been a decision to develop in detail the examples that illustrate the problems identified, instead of making a list of errors accompanied by an epidermal description of their characteristics.

Estudios de casos y controles en psiquiatría: causalidad, diseño y advertencias / Case-control studies in psychiatry: casualty, design and warning

El presente trabajo es de naturaleza esencialmente metodológica y se ha escrito con la expectativa de ayudar a que la investigación en psiquiatría se lleve adelante con creciente calidad, así como para contribuir a que los lectores de trabajos ajenos dispongan de pautas valorativas adecuadas. Se reflexiona brevemente en torno a las condiciones más importantes que necesariamente han de cumplirse para probar una hipótesis de causalidad, independientemente del diseño de investigación de que se trate. Sin embargo, el núcleo central del texto se destina a examinar e ilustrar el problema que tales condiciones plantean a quien diseñe y conduzca un estudio de caos y controles, que constituye la expresión dominante en la investigación observacional contemporánea. Además de reseñar los aspectos básicos en materia de diseño y análisis, áreas profusamente ilustradas con ejemplos de la literatura actual sobre casos y controles en psiquiatría, se ofrece un conjunto de advertencias sobre aspectos que suelen no contemplarse y cuyo olvido deteriora y ocasionalmente invalida las investigaciones desarrolladas con este importante método (AU)

This present paper in manly methodological and has been written with the aim of helping researchers in psychiatry to produce results with higher quality and help readers to have adequate assessment values of others. Brief reflection is made on the most important conditions that must be fulfilled to prove a causality hypothesis, regardless of the investigation design used. However, the main purpose of the text is to examine and illustrate how these conditions work under a case-control study environment. Besides outlining the basic aspects concerning design and analysis, areas extremely illustrated with examples of case and controls in psychiatry found in the literature, a number of suggestions to avoid pitfalls that can invalidate research efforts developed using case-control methodology is offered (AU)

[Case-control studies in psychiatry: causality, design and warnings]. / Estudios de casos y controles en psiquiatría: causalidad, diseño y advertencias.

This present paper is mainly methodological and has been written with the aim of helping researchers in psychiatry to produce results with higher quality and help readers to have adequate assessment values of others. Brief reflection is made on the most important conditions that must be fulfilled to prove a causality hypothesis, regardless of the investigation design used. However, the main purpose of the text is to examine and illustrate how these conditions work under a case-control study environment. Besides outlining the basic aspects concerning design and analysis, areas extremely illustrated with examples of case and controls in psychiatry found in the literature, a number of suggestions to avoid pitfalls that can invalidate research efforts developed using case-control methodology is offered.

Debate sobre métodos frecuentistas vs bayesianos / Debate on frequentialist vs. Bayesian methods

No disponible

[Risk markers and high blood pressure. The Cienfuegos global project. Longitudinal study 1992-1994]. / Marcadores de riesgo e hipertensión arterial. Proyecto global de Cienfuegos. Estudio longitudinal 1992-1994.

OBJECTIVE: To determine the significance of the selected risk markers in the development of high blood pressure in a relatively short period of time. DESIGN: Longitudinal or cohort study of a sample of a population from the municipality of Cienfuegos, as a second measurement of the Cienfuegos Global Project. CONTEXT: Community. Municipality of Cienfuegos; geographic area of the subject-object intervention-investigation of the Cienfuegos Global Project. SUBJECT: 1,369 adults aged 15 years of more (619 men and 750 women; 1,294 alive and 75 dead) were followed from January 1992 to February 1994, which constitutes an alleatory, stratified, equiprobabilistic sample by age and sex. Persons diagnosed as hypertensive in the initial evaluation of Cienfuegos Global Project were excluded, so that the new series for hypertensive patients was constituted by 731 individuals with 125 new patients when the risk markers age, sex, color of skin, family history of high blood pressure, salt consumption, sedentarism, alcoholism and tobaccoism were studied. The association of the risk markers hypercholesterolemia or risky cholesterolemia and obesity was studied with another series formed by a second sample of 417 individuals, this sample introduced 74 new cases of high blood pressure. MAIN OUTCOME: It was intended to estimate the odds ratio for high blood pressure for the different risk markers studied, in those patients exposed or not to them. RESULTS: The odds ratio for each of the risk markers was determined. The odds related to age increased from 1.37, to 1.86 in males and decreased to 0.64 in white individuals. These 3 results were statistically significant as risk markers for high blood pressure. The odds ratio for the remaining risk markers had no statistical significance. CONCLUSION: The age, male sex, and black race, in the comparatively short term--slightly over two years--are the main risk markers that will markedly favor the appearance of high blood pressure.

[The use of statistical methods in 2 medical journals with high impact factor]. / Uso de métodos estadísticos en dos revistas médicas con alto factor de impacto.

This paper intends to contribute to the discussion about the use of statistical techniques within the current biomedical and health investigation. We hypothesized that statistical methods necessary to go ahead with most high level research were rather small. Two high impact factor journals about epidemiology and health sciences were selected: New England Journal of Medicine and American Journal of Epidemiology. Both represent what we have called "successful research". The 2386 original and special articles which were published along the 1986-1990 period were carefully examined. Each statistical technique was classified into one of four complexity levels. Each paper was eventually classified on the same grounds. The frequency of each method was used within each level was then accounted. Statistical cited literature was also registered for each article. Finally, a descriptive examination of this information was developed. The results show that techniques widely dominant are those classified as from lower levels. Only the 12% for New England Journal of Medicine, and 17% for American Journal of Epidemiology belong to the most complex type. It was shown that current biomedical research dismisses, to a large extent both, complex statistical techniques and specialized statistical literature. In general, it limits itself to resources no more ahead than elementary multivariate procedures. It was concluded that simpler statistical methods are useful enough not only to understand what is currently published in journals like the ones studied but to produce high level results as well.