Whats the confidence interval and standard deviation- if either are huge then it very well could be statistically significant. They usually only show 1 or 2 of the mean, standard deviation, and confidence interval in any statistics reporting - that way they don’t get nailed down by those annoying facts.
Lies, damn lies, and statistics.
I think he means "clinically significant."
Obviously a 4% decline alone doesnt sound like much. But I think General Mills has a fair point. If you can get a 4% bang out of just its product, think what you can get if you combine Cheerios with an overall plan to lower your cholesterol.
That could bring you into clinical significance.
"But the current standard for accuracy allows for a five percent testing error. And the current standard for precision allows for roughly a 10 percent error. Together, they mean that in 95 percent of cases, cholesterol test results may be as much as 15 percent higher or 15 percent lower than the actual value."
If the margin-of-error is 15% for the measurement, a 4% drop is not statistically significant.