Re: [Paddlewise] swim or stay with boat

   Mark:

   Using the Table below, a chi-square test for independence of rows
and columns results in: test statistic=0.245, degrees of freedom=3,
p-value=0.970. So the tabled data supports the notion that survivors
and victims carried out very similar patterns of action, or rows and
columns are independent.

   Also, the estimated P(survivor|swim)=28/55 is virtually the same as
the estimated P(victim|swim)=27/55 also. We have sufficient sample size
to do a chi-square test, but we might reach the opposite conclusion  
about independence of rows and columns if we had a much larger sample.

   Fisher's Exact Test should give the same kind of conclusion as the
chi-square test. I wonder if there are any larger scale studies out
there?


           swim  wait  stay  other
survivor    28    26    27     10
victim      27    23    22     10



Quoting Mark Perkins <marker_at_gmail.com>:

> Hi Brad,
>
> The data you posit is available in the "Drownings in Canada" report, at the
> bottom of page 42.
> http://www.redcross.ca/cmslib/general/ws_final_m2_english2006_04_19.pdf
>
> I quote:
> "VICTIM & SURVIVOR RESPONSES TO IMMERSION The behaviour of victims and
> survivors of cold
> water boating immersions due to capsizing and swamping was similar. Similar
> proportions
> swam for shore immediately, after a delay, or stayed with the boat.
> 36% of victims (82/230) had a choice of whether to stay with the boat or
> swim for shore
> (i.e. the boat didn't sink or get swept away by current or wind). Of these,
> 27% (22/82)
> stayed with the boat, 33% (27/82) swam for shore immediately, 28% (23/82)
> swam for
> shore after a delay, and 12% (10/82) did other things.
> 73% of survivors (91/125) had a choice of whether to stay with the boat or
> swim for
> shore. Of these, 30% (27/91) stayed with the boat, 31% (28/91) swam for
> shore
> immediately, 29% (26/91) swam for shore after a delay, and 11% (10/91) did
> other things."
>
>
> Summary Table:
>                      swim    wait      stay
> survivor           28        26         27
> victim             27        23         22
>
> wait = "swim for shore after a delay"
>
> I am curious to see the results of the chi-square or Fisher's Exact test.
***************************************************************************
PaddleWise Paddling Mailing List - Any opinions or suggestions expressed
here are solely those of the writer(s). You must assume the entire
responsibility for reliance upon them. All postings copyright the author.
Submissions:     PaddleWise_at_PaddleWise.net
Subscriptions:   PaddleWise-request_at_PaddleWise.net
Website:         http://www.paddlewise.net/
***************************************************************************