A Finding of Noninferiority Does Not Show Efficacy - It Shows Noninferiority (of short course rifampin for MDR-TB)

An image of two separated curves from Mayo's book SIST

Published in the March 28th, 2019 issue of the NEJM is the STREAM trial of a shorter regimen for Rifampin-resistant TB.  I was interested in this trial because if fits the pattern of a "reduced intensity therapy", a cohort of which we recently analyzed and published last year.  The basic idea is this:  if you want to show efficacy of a therapy, you choose the highest dose of the active drug to compare to placebo, to improve the chances that you will get "separation" of the two populations and statistically significant results.  Sometimes, the choice of the "dose" of something, say tidal volume in ARDS, is so high that you are accused of harming one group rather than helping the other.  The point is if you want positive results, use the highest dose so the response curves will separate further, assuming efficacy.

Conversely, in a noninferiority trial, your null hypothesis is not that there is no difference between the groups as it is in a superiority trial, but rather it is that there is a difference bigger than delta (the pre-specified margin of noninferiority.  Rejection of the null hypothesis a leads you to conclude that there is no difference bigger than delta, and you then conclude noninferiority.  If you are comparing a new antibiotic to vancomycin, and you want to be able to conclude noninferiority, you may intentionally or subconsciously dose vancomycin at the lower end of the therapeutic range, or shorten the course of therapy.  Doing this increases the chances that you will reject the null hypothesis and conclude that there is no difference greater than delta in favor of vancomycin and that your new drug is noninferior.  However, this increases your type 1 error rate - the rate at which you falsely conclude noninferiority.

There is (No) Evidence For That: Epistemic Problems in Evidence Based Medicine

Below is a Power Point Presentation that I have delivered several times recently including one iteration at the SMACC conference in Chicago.  It addresses epistemic problems in our therapeutic knowledge, and calls into question all claims of "there is evidence for ABC" and "there is no evidence for ABC."  Such claims cannot be taken at face value and need deeper consideration and evaluation considering all possible states of reality - gone is the cookbook or algorithmic approach to evidence appraisal as promulgated by the User's Guides.  Considered in the presentation are therapies for which we have no evidence, but they undoubtedly work (Category 1 - Parachutes) and therapies for which we have evidence of efficacy or lack thereof (Category 2) but that evidence is subject to false positives and false negatives, for numerous reasons including: the Ludic Fallacy, study bias (See: Why Most Published Research Findings Are False), type 1 and 2 errors, the "alpha bet" (the arbitrary and lax standard used for alpha, namely 0.05), Bayesian interpretations, stochastic dominance of the null hypothesis, inadequate study power in general and that due to delta inflation and subversion of double significance hypothesis testing.  These are all topics that have been previously addressed to some degree on this blog, but this presentation presents them together as a framework for understanding the epistemic problems that arise within our "evidence base."  It also provides insights into why we have a generation of trials in critical care the results of which converge on the null and why positive studies in this field cannot be replicated.

Underperforming the Market: Why Researchers are Worse than Professional Stock Pickers and A Way Out

I was reading in the NYT yesterday a story about Warren Buffet and how the Oracle of Omaha has trailed the S&P 500 for four of the last five years.  It was based on an analysis done by a statistician who runs a blog called Statistical Ideas, which has a post on p-values that links to this Nature article a couple of months back that describes how we can be misled by P-values.  And all of this got me thinking.

We have a dual problem in medical research:  a.)  of conceiving alternative hypotheses which cannot be confirmed in large trials free of bias;  and b.) not being able to replicate the findings of positive trials.  What are the reasons for this?