In medical statistics, studies are given a “statistical significance” rating, which is the level of confidence in the results. It answers the question: How much of the results are based on the chance? A 95% confidence level is often used to show that a certain effect works. That means there is a 5% probability that the result is due to chance alone, in which case, the “positive finding “would actually be false! That means out of 100 studies that should prove false because the intervention doesn’t work, 5 studies will be found incorrectly to prove “true” (based on chance) when they should be false, and give the incorrect impression that the intervention worked.
In the case of 15,000 fish oil studies based on a 95% confidence level, 5% x 15,000 = 750 of these truly failed studies would show positive results by pure chance. When a study or an experiment is conducted, the result is either significant in effectiveness or working very well on the vast majority patients or it isn’t. Then to confirm the experiment, another group performs the same experiment once more. Before any experiment is conducted, one should have a good idea of result, based on established physiology and biochemistry.
Fish oil studies is a prime example, Fish oil doesn’t work because it can’t work. Fish oil can’t work because there are no significant metabolic pathways that could possibly give those supposed “extraordinary” results. As an example of both high effectiveness and high statistical significance in an experiment, see brianpeskin.com for the IOWA Experiment using DPA as a screening tool.
Mike Maunu – Founder
Oxygen4Life.com
