[Previous Months][Date Index][Thread Index][Join - Register][Login]
[Message Prev][Message Next][Thread Prev][Thread Next]

RE: [IP] Re: D prevention

Andrew Aronoff [mailto:email @ redacted] wrote:

> WARNING: The following post refers to statistics, which some consider
> to be as repulsive as vulgarity. If you share this view, press your
> delete key NOW!
>      More than 80% of cases of IDDM occur in individuals with no
>      family history of the disease. However, in the remaining 20%,
>      IDDM aggregates in families. The overall risk before age 30 years
>      for North American Caucasian siblings, parents, and offspring of
>      individuals with IDDM ranges from 1% to 15%... compared with
>      rates of < 1% for individuals without IDDM relatives.


Andrew, I've looked this over and one thing jumped out at me immediately:
only one table shows the results of any statistical analysis (Table 8.2,
which is about breast feeding).

All the rest of the numbers are descriptive, but none showing whether or not
the differences from random are greater than could be accounted for by
chance.  IOW, it's as I suggested in my previous response.

That is not to say the numbers are wrong.  It *IS* to say to be very careful
how you (or anyone else) interprets them.  It's one thing to say 20% of type
1 DM occurs within some family association.  It's another thing altogether
to say that this association is a statistically significant departure from
random chance.

There's a nice presentation about genetics, but no tables or analyses to
show these to be either statistically or biologically significant factors,
even if common sense would suggest that they are.

Jim Handsfield
email @ redacted OR
email @ redacted

The opinions expressed are mine and may not represent those of my wife who
runs our house and makes more important decisions than I do.
for HELP or to subscribe/unsubscribe, contact: HELP@insulin-pumpers.org
send a DONATION http://www.Insulin-Pumpers.org/donate.shtml