Interesting quotes, web pages, and publications for the month of June (June 21, 2005)

This page is being phased out.

Meta Analysis. Dallal G. Accessed on 2005-06-21.

Excerpt: Sometimes there are mixed reports about a treatment's effectiveness. Some studies may show an effect while others do not. Meta analysis is a set of statistical techniques for combining information from different studies to derive an overall estimate of a treatment's effect. The underlying idea is attractive. Just as the response to a treatment will vary among individuals, it will also vary among studies. Some studies will show a greater effect, some will show a lesser effect--perhaps not even statistically significant. There ought to be a way to combine data from different studies, just as we can combine data from different individuals within a single study. That's Meta Analysis. www.tufts.edu/~gdallal/meta.htm

My comments: A recent publication that is sharply critical of meta-analysis. Dr. Dallal points out that meta-analysis is relied on most for situations with high levels of heterogeniety and when there is no single good quality large scale randomized study to rely on. This is the very situation where meta analysis is at its weakest.

BioC2005. Where Software and Biology Connect. Gentleman R, Carey V, Huber W, Irizarry R. Accessed on 2005-06-21.

Excerpt: This conference will highlight current developments within and beyond Bioconductor, a world-wide open source and open development software project for the analysis and comprehension of genomic data. Our goal is to provide a forum in which to discuss the use and design of software for analyzing data arising in biology with a focus on Bioconductor and genomic data. When and Where: August 16-17, 2005 at the Fred Hutchinson Cancer Research Center Seattle, Washington, USA. www.bioconductor.org/meeting05/

Software Accompanying: Correspondence Analysis and Data Coding with R and Java. Murtagh F. Accessed on 2005-06-15.

Excerpt: The software and data presented here accompanies the book Correspondence Analysis and Data Coding with R and Java, by Fionn Murtagh, Chapman & Hall/CRC, 2005. Some of the programs, especially the R and C ones, are in ascii text. Some others are binary (e.g. the clustering DLL program, and the Java class files). The Java code and the data sets are collected together in tar files, to be extracted using WinZIP or tar or some similar utility. www.correspondances.info

My comments: This software might prove useful for microarray analysis.

Calculating Confidence Intervals for Threshold and Post-Test Probabilities. Hozo I, Djulbegovic B. M.D. Computing 1998: 15(2); 110-5. [Medline]

Abstract: We describe a method and a computer program, written in JavaScript, for calculating confidence intervals. The method uses Taylor's series to approximate the standard errors of a post-test probability and threshold probabilities and, from them, to obtain the associated confidence intervals. This method is valid if the variables of interest are stochastically independent.

My comments: I am working on some web pages that talk about diagnostic testing. One important issue is to properly reflect the uncertainty in many of the calculations. A good reference on how to do this is

Design and analysis of pilot studies: recommendations for good practice. Lancaster GA, Dodd S, Williamson PR. J Eval Clin Pract 2004: 10(2); 307-12. [Medline]

Abstract: Pilot studies play an important role in health research, but they can be misused, mistreated and misrepresented. In this paper we focus on pilot studies that are used specifically to plan a randomized controlled trial (RCT). Citing examples from the literature, we provide a methodological framework in which to work, and discuss reasons why a pilot study might be undertaken. A well-conducted pilot study, giving a clear list of aims and objectives within a formal framework will encourage methodological rigour, ensure that the work is scientifically valid and publishable, and will lead to higher quality RCTs. It will also safeguard against pilot studies being conducted simply because of small numbers of available patients.

My comments: I have written about pilot studies, and this paper adds a lot of useful information.