How likely is it that simple randomization resulted in particular group sizes in a RCT?

I was the editor for a randomized trial submission to our journal which had a total sample size of 132. The authors used simple randomization (i.e. no restricted randomization, such as blocking or minimization), and they ended up with 58 in one group and 74 in the other. This is pretty clearly a moderate imbalance, and not really desirable in a clinical trial.


The question I had was: how probable was it that this result was due to chance alone? Could there have been another explanation for this disparity, such as a faulty randomization generation algorithm? I satisfied myself that the group size disparity would be acceptable if the probability that it could have occurred by chance alone was > 5% (the typical value used for statistical significance).

Continue reading


Apple’s ResearchKit is not (yet) ready for primetime — A medical researcher’s perspective.

I am a clinician and a clinical trialist. Medical research in some form or another (performing it, consuming it, reviewing it, editing it, etc.) occupies much of my time. Therefore, you can imagine my excitement while watching Apple’s product announcement yesterday when they introduced a new open source software platform called ResearchKit. Apple states ResearchKit could:

“revolutionize medical studies, potentially transforming medicine forever” Continue reading

The best treatment for laryngospasm is simple, fast, and free

Ever since I have been on-staff at a tertiary care academic hospital, I have made it a point to teach all the students and residents I work with about the ‘laryngospasm notch’. Specifically, since it is my standard care for every patient I extubate, I make sure trainees are applying firm pressure in the laryngospasm notch after they extubate every patient. Usually, the first residents have ever heard of the ‘notch’ is from me! This is disappointing since this manoeuvre is extremely important in clinical anesthesia, and every anesthesia practitioner should know about it. I therefore thought I would write a blog post about it. Continue reading

Using the -csti- command in Stata to quickly compute relative risks and P values for binary outcomes from medical journals

In medical journals, binary outcomes (such as mortality, length of stay > 30 days, or acute kidney injury [AKI]) are typically published in a Table as the number of events over the number of patients or subjects in the group, i.e. n/N.

Continue reading

My start to blogging


Who would have thought I would start blogging after reading hundreds of blogs for about 15 years? 🙂

However, I find that I have things to say, and I hope this platform will become the place for me to speak my mind.

The target audience of this blog will be physicians and researchers in the domains of anesthesiology and critical care.

I plan to blog about:

  • medicine in general
  • anesthesiology and critical care in particular
  • medical statistics (I have done a MSc in Clinical Trials via the London School of Hygiene & Tropical Medicine and I am passionate about learning, teaching, and (most of all) using statistics in everyday clinical life
  • research methodology (as an Associate Editor for the Canadian Journal of Anesthesia I read a lot of papers, and I am troubled by the lack of rigour applied to many of these manuscripts.) We can (and must) do better.
  • critical appraisal of particularly important articles in any of the areas above, and,
  • all things Apple, including hardware, software, and particularly how academic physicians can incorporate Mac or iOS applications to increase their productivity.

Reading the above, it does appear to be a bit of a hodge-podge, so we’ll have to see how it goes.

I plan to tailor the blog as it evolves to maintain relevance to as broad of an audience as I can.

I will very much be learning how to blog as I go. I have never had a blog before. I hope it will be an interesting ride.

Please leave comments if you find something you want to chat about. I will do my best to respond.