blastula
Contributor
- Joined
- Apr 13, 2006
- Messages
- 10,662
- Gender
- Late for dinner
- Basic Beliefs
- Gnostic atheist
So based on this info; which is better? 482 out of 2104 (with dexamethasone ) dead or 1110 out of 4321 (without dexamethasone) dead? Unless I'm reading this wrong it's all the same to me.
With: 23%, without: 26%
Here is a rough guide to sampling error, the result of using an incomplete sample. For sample size N, its relative value is roughly 1/sqrt(N).
Here, this means a relative error of 1.5% - 2.1%. So that result is not very strong.
To get a better number, one will have to be more careful and use the appropriate statistical distribution.
You missed, "the incidence of death was lower than that in the usual care group among patients receiving invasive mechanical ventilation (29.3% vs. 41.4%; rate ratio, 0.64; 95% CI, 0.51 to 0.81)."
It's indicated for patients on ventilators.

