<<Disclaimer: Verify this information before applying it to your situation.>>
> Hi Celiacs.
>
> As a statistician, I can't resist addressing this issue of whether
> oatmeal is contaminated because it's a classic case of too little
> information.
>
> As far as I know, the only analysis of the gluten content of oatmeal
> was a letter written to the New England Journal of Medicine in 2004 by
> a registered dietician, Tricia Thompson. Thompson bought 4 containers
> each of McCann's, Country Choice, and Quaker oatmeal in Massachusetts.
> She took a sample from each box and sent the samples to a lab for
> analysis and published the raw data.
>
> Here are the quantities of gluten she found in parts per million (ppm).
>
> McCann's: <3, 12, 23, 725
> Country Choice: <3, 120, 131, 210
> Quaker: 338, 364, 971, 1807
>
> The definition of "gluten free" is controversial, but two common
> definitions are less than 20 ppm (0.002%) or less than 200 ppm
> (0.02%).
>
> Three out of the four samples of McCann's are gluten-free according to
> the stricter defininition --- 23 isn't statistically different from
> 20, given the likely margin of error of the test. One of the four
> samples is not gluten-free. A sample size of 4 is too small to
> conclude whether the bad batch is a fluke or a regular event. Having
> one non-GF batch out of 4 means that we expect somewhere between 0% to
> 67% of the batches to be non-GF, which is only slightly better than
> having no information at all.
>
> The oatmeal was also not a representative sample of McCann's oatmeal,
> so we have no way to know whether other batches of McCann's oatmeal
> are similar to the ones that she analyzed. Other batches may have
> more gluten or less gluten. We have no way to know.
>
> This analysis only requires Stat 101 material, but for the record, I
> have a masters from one of the top 5 stat depts in the country.
>
> J
*Support summarization of posts, reply to the SENDER not the Celiac List*
*******
To unsubscribe, email: mailto:[log in to unmask]
*******
|