Are You “Significantly” Informed About the Word “Significantly”?

I was going to write a post today about “natural” products and supplements which may be (or may not be) beneficial to diabetes. I was going to say that even though things like cinnamon, garlic, and fenugreek may show some benefit to blood glucose, they cannot be considered “treatments” for diabetes. Fortunately for you, the Type2diabetes.com editorial team posted a fairly comprehensive summary of this subject entitled Natural Products two years ago – fortunately for me, I actually looked before I started writing. But, in reading that post from 2014 I had another idea that might help you understand this issue (after you read the editorial team’s post) – the use of the word “significantly” in scientific studies.

In common usage, the word “significantly” implies a subjective opinion – “these black shoes are significantly more comfortable than the brown ones.” More importantly, the suggestion is that when something is “significantly” better there is a big difference in the two things – like shoes – being compared. But, when a scientific study says, for instance, that “results from eight clinical trials of cinnamon (taken as an extract or in whole form) used in subjects with type 2 diabetes found significant reductions in fasting plasma glucose” does “significant” actually mean there was a big difference (a big improvement) in fasting blood glucose? The answer is no.

Instead, “significant” in scientific studies is a statistical term meaning that an experimental result – improved fasting blood glucose from consuming cinnamon – is not likely to be related to random chance. So, the statement from the previous paragraph tells us it’s very likely that cinnamon had a favorable impact on reducing fasting blood glucose among this particular study group, but does not tell us (or even hint) how big that the difference was. To see the actual impact we would have to look at the actual study results – the before cinnamon and after cinnamon blood glucose numbers.

Statistical analysis of scientific experiments is an incredibly useful tool. But, the use of the word “significant” has a meaning in statistics that can be misleading unless we look a little deeper.

This article represents the opinions, thoughts, and experiences of the author; none of this content has been paid for by any advertiser. The Type2Diabetes.com team does not recommend or endorse any products or treatments discussed herein. Learn more about how we maintain editorial integrity here.

Comments

Poll