Showing papers by "Ingram Olkin published in 1998"

Comparison of meta-analysis versus analysis of variance of individual patient data

Abstract: Meta-analysis is a method of synthesizing the results of independent studies. We consider the case in which there are multiple treatments and a control, with the goal of estimating the relative effect of each treatment based on continuous outcomes. Even when all data are available, rather than only summary data, it has become common to use meta-analytic estimators of treatment contrasts. Alternatively, we could use a two-way analysis of variance model with no interaction in which one factor is study and one factor is treatment. For the unbalanced case, we obtain the surprising result that the standard meta-analysis estimates of treatment contrasts are identical to the least squares estimators of treatment contrasts in the linear model. Because a meta-analysis of individual patient data can be considerably more costly in terms of data retrieval than a meta-analysis of summary data, this equivalence provides for cost-efficient analysis.

Mejora de la calidad de los informes de los ensayos clínicos aleatorio controlados. Recomendaciones del grupo de trabajo CONSORT

Abstract: This summary corresponds to the translation into Spanish of the Special Communication published in the Journal of the American Medical Association in August 1996, along with the editorial published in the same issue "How to report Randomized Controlled Trials. The Consort Statement". It describes the Consolidated Standars for Preparation of Controlled Clinical Trials, prepared by a work group made up of members of the SORT Group and of the Asilomar Work Group, along with the editor of a magazine and the author of the report on a clinical trial. The work was carried out by means of a Delphy process and the result was a check list and a process diagram. The check list is made up of 21 items that mainly refer to methods, results and discussions on the report of a controlled clinical trial, identifying the necessary information in order to be able to evaluate the internal and external value of the report, judging the improvement to be positive for the patient, the editors and the reviewers of the magazines.

Symmetrically dependent models arising in visual assessment data

Abstract: Summary. Given data from bilateral visual assessments on N subjects at k occasions, we consider inference for contralateral correlations (C) between fellow eyes and lateral correlations (L) among p different assessments of the same eye. Under permutation symmetric dependence structure between observations from fellow eyes and among observations from the same eye, we obtain maximum likelihood estimates of L, C, and L –- C. Based on the large-sample estimates of the corresponding covariance structures, we test the hypothesis that the association between fellow eyes is constant across time and the hypothesis that lateral and contralateral associations between any two occasions are the same.