A flip of a coin does not result in an exact 50-50 chance of heads or tails. It depends a lot on how the coin is flipped, of course, but there is a bias. This article explains when, why, and how much bias there is. Continue reading
Category Archives: Recommended
Recommended: The Empirical Evidence of Bias in Trials Measuring Treatment Differences
When I wrote a book about Evidence Based Medicine back in 2006, I talked about empirical evidence to support the use of certain research methodologies like blinding and allocation concealment. Since that time, many more studies have appeared, more than you or I could easily keep track of. Thankfully, the folks at the Agency for Healthcare Research and Quality commissioned a report to look at studies that empirically evaluate the bias reduction of several popular approaches used in randomized trials. These include
selection bias through randomization (sequence generation and allocation concealment); confounding through design or analysis; performance bias through fidelity to the protocol, avoidance of unintended interventions, patient or caregiver blinding and clinician or provider blinding; detection bias through outcome assessor and data analyst blinding and appropriate statistical methods; detection/performance bias through double blinding; attrition bias through intention-to-treat analysis or other approaches to accounting for dropouts; and reporting bias through complete reporting of all prespecified outcomes.
The general finding was that failure to use these bias reduction approaches tended to exaggerate treatment effects, but the magnitude and precision of these exaggerated effects was inconsistent. Continue reading
Recommended: ENCODE: Encyclopedia of DNA Elements
The genetics research community should be lauded for the openness with which they share research data. You can find numerous data sources that are free and without ANY restrictions. One very good example is ENCODE, the Encyclopedia of DNA Elements. This repository, mostly of human data, but some mouse, fruit fly, and round worm data as well. It has data from many different assays including ChIP-seq, RNA-seq, and DNase-seq. It looks like a great teaching resource, though it does require a fairly hefty understanding of genetics to browse through the data. Continue reading
Recommended: Lyndon B. Johnson Space Center job opening for a GS-14 Statistician
I get a lot of emails mentioning job openings and I normally delete them unread. This one caught my eye, not because I wanted to apply for it, but because it illustrates how statisticians get to work on very interesting jobs. This is a Senior Statistician job at the Lyndon B. Johnson Space Center in Houston. If you got this job, you’d be providing assistance on “a wide range of biomedical and technical areas in support of space exploration.” How cool is that!
The other interesting thing is that they say that “accreditation by the American Statistical Association is highly desired.” I’m not accredited by the ASA and don’t plan on it anytime soon, but if you want to be the Buck Rogers of Statistics, maybe you should. Continue reading
Recommended: A Grant Submission New Year’s Resolution
Michael Lauer, the Deputy Director for Extramural Research at the United States National Institutes for Health shows some interesting statistics on when people submit grants and shows that grants submitted earlier than the day of the deadline tend to fare slightly better in the review process. There’s one gross miscalculation on this page, but the message is still interesting. Continue reading
Recommended: Points to consider on switching between superiority and non-inferiority
This page has moved to a new website.
One of the most confusing aspects of medical research is the difference between non-inferiority and superiority trials. This article explains in simple terms what the two type of trials are. Then it covers the desire of many researchers to switch from a non-inferiority trail to a superiority trial or vice versa. In general, if you would like to make the claim of superiority if the data justifies it, or to fall back on a claim of non-inferiority if you must, you are best off designing a high quality non-inferiority trial. The extra methodological rigor and the typically larger sample sizes that come with a non-inferiority trial make the transition from a non-inferiority hypothesis to a superiority hypothesis much smoother than the reverse. A high quality non-inferiority trial includes pre-specifying the margin of non-inferiority, demonstrating adequate power for the non-inferiority hypothesis, and justifying that the control group has demonstrated efficacy in previous trials. You need to show sufficient methodological rigor in your research design to establish that a non-inferiority finding is not just caused by an insensitive research design. Finally, you need to consider a “per protocol” analysis for the non-inferiority hypothesis, but switch to an “intention to treat” analysis for the superiority hypothesis. Continue reading
Recommended: Differences between information in registries and articles did not influence publication acceptance
This page has moved to a new website.
Here’s a research article tackling the same problem of changing outcome measures after the data is collected. Apparently, this occurs in 66 of the 226 papers reviewed here or almost 30% of the time. The interesting thing is that whether this occurred or not was independent of whether paper was accepted. So journal editors are missing an opportunity here to improve the quality of the published literature by demanding that researchers abide by the choices that they made during trial registration. Continue reading
Recommended: The COMPare Project
This page has moved to a new website.
One of the many problems with medical publications is that researchers will choose which outcomes to report based on their statistical significance rather than their clinical importance. This can seriously bias your results. You can easily avoid this potential bias by specifying your primary and secondary outcome measures prior to data collection. Apparently, though, some researchers will change their minds after designating these outcome variables and fail to report on some of the outcomes and/or add new outcomes that were not specified prior to data analysis. How often does this occur? A group of scientists at the Centre for Evidence-Based Medicine at the University of Oxford are trying to find out. Continue reading
Recommended: Clinical trials: discerning hype from substance
I was attending a short course taught by Susanne May on clinical trials (very good, by the way) and she mentioned an interesting publication. It talks about the “random high” bias. Continue reading
Recommended: PS: Power and Sample Size Calculation
Someone stopped by today with a power calculation and I asked what software they used. They showed me something I had not seen before, a program developed by the Department of Biostatistics at Vanderbilt University (more specifically, William Dupont and Walton Plummer). The Vanderbilt Biostatistics Department is run by Frank Harrell, so you can be pretty sure that anything that they develop will be high quality. Continue reading