Re: Vitamin D and multiple health outcomes: umbrella review of systematic reviews and meta-analyses of observational studies and randomised trials
My initial reaction while reading this (and before reading the responses) was that some fairly opaque statistics were covering for serious methodological flaws. Meta-analysis has insurmountable shortcomings - such as heterogeneity and reliance on and amplification of flaws in the original studies. To repeat this process by meta-analysing the meta-analyses seems to place excessive hope on the virtues of amalgamation of data for apparent mathematical benefits. I would place more trust in a single, well-designed, adequately powered study.
To borrow a painting analogy, all the colours of the rainbow have been mixed and we have come up with brown. I am glad to see that other, better qualified people have similar misgivings with this paper and have eruditely expressed them above.
Competing interests: No competing interests