statistical significance

News organizations have recently been down on Paxlovid, while it has become the standard of care. Some claim Pfizer's Covid drug "has lost its luster" because of "failures" in two clinical trials. Now, a third trial looks like it could deliver another black mark: the drug doesn't improve symptoms in low-risk patients with Covid. Is this criticism valid? Let's look a little deeper.
The pressure for medical treatment for COVID generated lots and lots of studies. Some good, some awful, few peer-reviewed before being widely and wildly disseminated. A new study looks at how we might separate the good from the bad and ugly.
Sometimes studies are full of bad data. Sometimes they are just based on stupid ideas. Here's one that manages to incorporate both flaws. Should elderly people with broken ribs be given Tylenol in pill form or IV for pain? Perhaps a salami sandwich is a better offering ... since this study is full of baloney.
The study by Didier Raoult et. al., the one partly responsible for the massive, unwarranted use of hydroxychloroquine for COVID, has been picked to bits by a review panel hired by the journal that published it. It's now clear that the Raoult study was a methodological mess. How did it get published at all? Should it be retracted? Let's take a look.
How can physicians, in the care of their patients, translate research findings into useful information? P-values suggest differences, not effects. But could there be a simple solution?