0
$\begingroup$

"In Chile, where they typically dive alone, three of the six attacks since 1963 proved fatal," McCosker said. "Whereas, in California and Oregon, since 1950, only nine of 93 attacks were fatal."

The quote refers to white shark attacks on divers. The claim is that these attacks tend to be fatal more often when divers go out alone (typical of Chile) rather than with companions (typical of California and Oregon). Does this claim have statistical validity?

What statistical approach can I use to answer this question

$\endgroup$
  • $\begingroup$ What comprises an "attack" instance? If a group of 10 divers go out and the group encounters a shark, is that one attack or is it ten? If that's the case, it's like saying Russian Roulette is safer when playing with friends, which is true but conveys the wrong impression. $\endgroup$ – AdamO Mar 16 '18 at 18:16
0
$\begingroup$

You could use Fisher's Exact Test here.

           Fatal      Non-fatal           Total
Chile        3            3                 6
California   9            84            93
Total       12            87            99

Fisher's exact test: The two-tailed P value equals 0.0225. The association between rows (groups) and columns (outcomes) is considered to be statistically significant.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.