StATS: Interesting websites, publications and quotes for the month of March (updated March 29, 2006) Category: Interesting stuff

Note: any quotations on this page have been moved to Category: Interesting quotes.

Issues in data monitoring and interim analysis of trials. AM Grant, DG Altman, AB Babiker, MK Campbell, FJ Clemens, JH Darbyshire, DR Elbourne, SK McLeer, MKB Parmar, SJ Pocock, DJ Spiegelhalter, MR Sydes, AF Walker, SA Wallace. Health Technolgoy Assessment 2005: 9(7); [Medline] [Abstract] [PDF]

Offering results to research participants. E. M. Dinnett, M. M. Mungall, C. Gordon, E. S. Ronald, A. Gaw. Bmj 2006: 332(7540); 549-50. [Medline] [Excerpt] The distinction between giving a general summary of trial results to study participants and providing them with their own trial results is not made clear in the paper by Dixon-Woods et al or the accompanying editorial. Investigators may provide patients with a summary of the trial results, but even if they do not they should be aware that study participants may access these results elsewhere. The provision of personalised trial results, and in particular treatment allocation (unblinding), is quite a different matter and much debated. This is the more likely of the two to result in emotional consequences for the participants.

One-time general consent for research on biological samples. D. Wendler. Bmj 2006: 332(7540); 544-7. [Medline] [Excerpt] It is now recognised that people should give informed consent for use of their biological samples in research. The literature on individuals' views supports one-time general consent as the best approach for this purpose.

Wonder Drug Inspires Deep, Unwavering Love Of Pharmaceutical Companies. The Onion, Published in Issue 42-10, March 6, 2006. Accessed on 2006-03-09. [Excerpt] The Food and Drug Administration today approved the sale of the drug PharmAmorin, a prescription tablet developed by Pfizer to treat chronic distrust of large prescription-drug manufacturers. Pfizer executives characterized the FDA's approval as a "godsend" for sufferers of independent-thinking-related mental-health disorders.

Flame Warriors. Mike Reed. Accessed on 2006-03-08. [Excerpt] Some years ago, a minor pat ignited a searing falme war that threatened to consume a one-placid discussion forum. While the forum burned, I amused myself by caricaturing the chief antagonists. Confounded at seeing themselves thus revealed, the combatants fled the field in disarray. Over time the roster of online belligerents expanded and eventually congealed into the netizen's guide to Flame Warriors. My own bad internet behavior would certainly have provided sufficient material to populate an extensive rogue's gallery, but suggestions and comments from astute observers continue to enrich the Flame Warriors collection. Please report immediately any sightings of new Warrior variants.

A Regression Model for Dependent Gap Times. Robert L. Strawderman. The International Journal of Biostatistics 2006: 2(1); 1-34. [Abstract] A natural choice of time scale for analyzing recurrent event data is the "gap" (or soujourn) time between successive events. In many situations it is reasonable to assume correlation exists between the successive events experienced by a given subject. This paper looks at the problem of extending the accelerated failure time (AFT) model to the case of dependent recurrent event data via intensity modeling. Specifically, the accelerated gap times model of Strawderman (2005), a semiparametric intensity model for independent gap time data, is extended to the case of multiplicative gamma frailty. As argued in Aalen & Husebye (1991), incorporating frailty captures the heterogeneity between subjects and the "hazard" portion of the intensity model captures gap time variation within a subject. Estimators are motivated using semiparametric efficiency theory and lead to useful generalizations of the rank statistics considered in Strawderman (2005). Several interesting distinctions arise in comparison to the Cox-Andersen-Gill frailty model (e.g., Nielsen et al, 1992; Klein, 1992). The proposed methodology is illustrated by simulation and data analysis.

ZumaStat. James Jaccard. Accessed on 2006-03-03. [Excerpt] ZumaStat offers stand alone statistical programs that can be integrated easily with the menu bars of SPSS and Excel. The programs work with summary statistics (such as means, standard deviations, percentages, and correlations) to perform a wide range of statistical tests and power analyses (e.g., test of difference between two percentages, test of difference between two correlations, single degree of freedom interaction contrasts, t tests for means). ZumaStat also has a special SPSS utility (called Z Plus) that makes using SPSS much easier and more flexible.

Understanding the design matrix in linear models for microarray experiments. Natalie Thorne, University of Cambridge, The Hutchison/MRC Research Center. Accessed on 2006-03-03.

These two articles have not been published yet, but I will track down the information when they appear:

Monitoring and ensuring safety during clinical research. M. A. Morse, R. M. Califf, J. Sugarman. Jama 2001: 285(9); 1201-5. [Medline] [Abstract] [Full text] [PDF] Increased numbers of clinical trials, many of which are large, multicenter, and sometimes international, and the marked shift of funding for clinical trials to industry have made apparent the inadequacy of mechanisms for protecting human subjects that were developed when clinical research was generally carried out on a small scale at single institutions. To address concerns regarding the protection of human subjects, a group of professionals with expertise in various aspects of clinical trials was assembled in May 2000. Participants described and evaluated the mechanisms by which clinical trials are monitored, focusing on adverse event reporting and the processes by which various parties with oversight responsibilities interact in the course of these trials. In this article, we describe the manner in which adverse event reporting might function to enhance safety and the role of data monitoring committees in using aggregate data from these reports, outline the problems that now exist for institutional review boards as they are faced with multiple adverse event reports from clinical trials while conducting continuing review, and offer recommendations for improving the current approach.

Analysis of Covariance Primer [PDF]. Dennis Roberts, Penn State University. Accessed on 2006-03-02. [Excerpt] In the normal experimental design, Ss are randomly assigned to different treatment levels. and then we might perform a simple ONE factor ANOVA to test the null hypothesis of no treatment effects in the overall populations. Consider the simplest of these “experiments”, a two group study where 20S have been randomly assigned (n=10 to each group) to two conditions: Experimental and Control. In the data table below, YE means the dependent variable data (% correct scores on a science test) for the Experimental group and YC is the comparable data for the Control group. With the DESC output, you will note that the mean E is 68.1 and the mean C is 61. Then question here of course is whether we would, after our statistical test, reject the null hypothesis.

Guidance on Research Involving Coded Private Information or Biological Specimens [PDF]. Office for Human Research Protections, Department of Health and Human Services, Published August 10, 2004. Accessed on 2006-03-02. (Ethics, Privacy) [Excerpt] Scope: This document applies to research involving coded private information or human biological specimens (hereafter referred to as “specimens”) that is conducted or supported by HHS. This document does the following: (1) Provides guidance as to when research involving coded private information or specimens is or is not research involving human subjects, as defined under HHS regulations for the protection of human research subjects (45 CFR part 46). (2) Reaffirms OHRP policy (see OHRP guidance on repository activities and research on human embryonic stem cells) that, under certain limited conditions, research involving only coded private information or specimens is not human subjects research. (3) Clarifies the distinction between (a) research involving coded private information or specimens that does not involve human subjects and (b) human subjects research that is exempt from the requirements of the HHS regulations. (4) References pertinent requirements of the HIPAA Privacy Rule that may be applicable to research involving coded private information or specimens.

HRPP Blog. Jeffrey Cohen. Accessed on 2006-03-02. [Excerpt] The purpose of this blog is to share my experience with human research protections programs.

Creative Commons License This work is licensed under a Creative Commons Attribution 3.0 United States License. It was written by Steve Simon.

This page was written by Steve Simon while working at Children's Mercy Hospital. Although I do not hold the copyright for this material, I am reproducing it here as a service, as it is no longer available on the Children's Mercy Hospital website. Need more information? I have a page with general help resources. You can also browse for pages similar to this one at