On Some Analyses

Abstract

There are methodological errors being made in statistical analyses, resulting in flawed results. Examples are in the studies by Hiasa et al 1 Hiasa G Hamada M Saeki A et al. Cardiac sympathetic nerve activity can detect congestive heart failure sensitively in patients with hypertrophic cardiomyopathy. Chest. 2004; 126: 679-686 Abstract Full Text Full Text PDF Scopus (15) Google Scholar and Oudiz et al. 2 Oudiz RJ Schilz RJ Barst RJ et al. Treprostinil, a prostacyclin analogue in pulmonary arterial hypertension associated with connective tissue disease. Chest. 2004; 126: 420-427 Abstract Full Text Full Text PDF PubMed Scopus (203) Google Scholar The problem is the authors’ use of two-sample t tests, analysis of variance, or analysis of covariance to compare means, which assumes the normality and equality of unknown variances in the groups considered. The Central Limit Theorem justifies normality for mean inferences, but unknown variances need not be equal, making these methods not generally applicable to comparing means. This problem is not removed by futilely 3 Kendall MG Stuart A The advanced theory of statistics. vol 2. Charles Griffin and Co., London, UK1973: 484 Google Scholar testing for the equality of variances. Function of the Günther Tulip Vena Caval FilterCHESTVol. 128Issue 3PreviewAs an interventional radiologist with a strong interest in vena caval filters, I read the evidence-based guidelines of the Seventh ACCP Conference with careful attention. In the second part of the publication, Antithrombotic Therapy for Venous Thromboembolic Disease,1 Dr. Buller and colleagues have made a citation error in Section 4.5, vena caval interruption for the initial treatment of pulmonary embolism. They state that the Günther Tulip filter (Cook; Bloomington, IN) appears to be “less satisfactory.” To support this they provide a reference from 1992. Full-Text PDF