Tag Archives: statistics

Why do we need randomized trials?

By | April 28, 2020

Discussion about randomized controlled trials (RCT) has been extensive in social media during this spring due to corona virus epidemic. This discussion was especially heated when “not so good” clinical trial was published stating that hydroxychloroquine is efficient in the treatment of corona virus disease (CoViD-19). I drew this picture and posted it on Twitter.… Read More »

Exploratory or confirming study?

By | February 21, 2020

Methodology is hard. And making valid inferences is very hard. With regard to these topics, orthopaedic research is not very different to other field in medicine. It means that misconceptions, misunderstandings and flawed approaches are prevalent also in our field. American Journal of Sports Medicine published recently two papers which both made a quite common,… Read More »

Propensity scores, orthopaedics and shared decision making

By | January 7, 2020

This is something I posted on Twitter last October. Extended discussion can be found below the tweets Propensity score matching is often used when two cohorts of patient are compared. Aim is to have somewhat comparable groups so effect of treatment or intervention could be estimated reliably. In short, two groups of patient tread by… Read More »

Uncertainty in medical decision making

By | October 21, 2019

“The failure to train doctors about clinical uncertainty has been called “the greatest deficiency of medical education throughout the twentieth century.” Djulbegovic (2004), https://www.bmj.com/content/329/7480/1419 Life is full of uncertainties. In decision making uncertainty means that it is impossible to define future outcomes. Amount of medical information continues to grow exponentially, but uncertainty is still inevitable… Read More »

No evidence of no evidence

By | October 5, 2019

In the null hypothesis significance testing framework, failure to reject the null is never evidence in support of null. However, it is extremely common that failure to reject the null, ie. getting a p-value larger 0.05 is interpreted as “no difference” or “no evidence”. As many experts have said, “absence of evidence is not evidence… Read More »

Industry based evidence synthesis

By | August 28, 2019

In 2017, me and colleagues published both a literature and registry based analysis of use of metal-on-metal hip replacements. This study, titled Lack of evidence—the anti-stepwise introduction of metal-on-metal hip replacements, was a hypothesis-driven study since at that time it seemed that the use of ASR hip replacements was not that evidence based but mainly… Read More »

Post-hoc power – Alone in the universe

By | July 5, 2019

Prologue Firstly, it is important to describe what post-hoc power really means. Post-hoc power is the power of the test using effect size observed and sample size used in the study. For this reason post-hoc power is often labeled as observed power. If for any experiment the effect size, parameter estimates and sample size is… Read More »