A study measured the levels of mercury in livers (microgram of mercury per gram of dried weight) of dolphins that had been stranded in an unusual mortality event along the Texas coast in 1992. Here are the data for the 17 dolphins studied:
?
?
$$\begin{array} { | l | l | l | l | l | l | l | l | l | }
\hline 1.9 & 0.8 & 0.6 & 0.6 & 10.4 & 33.6 & 0.8 & 13.3 & 47.9 \
\hline 1.7 & 17.1 & 2.7 & 932.1 & 172.2 & 34.7 & 27.3 & 27.0 & \
\hline
\end{array}$$ Why shouldn't we use these data to compute a 95% confidence interval for the mean liver mercury concentration in dolphins off the Texas coast in 1992?

Question

A study measured the levels of mercury in livers (microgram of mercury per gram of dried weight) of dolphins that had been stranded in an unusual mortality event along the Texas coast in 1992. Here are the data for the 17 dolphins studied:
?
?
$$\begin{array} { | l | l | l | l | l | l | l | l | l | } 
\hline 1.9 & 0.8 & 0.6 & 0.6 & 10.4 & 33.6 & 0.8 & 13.3 & 47.9 \
\hline 1.7 & 17.1 & 2.7 & 932.1 & 172.2 & 34.7 & 27.3 & 27.0 & \
\hline
\end{array}$$ Why shouldn't we use these data to compute a 95% confidence interval for the mean liver mercury concentration in dolphins off the Texas coast in 1992?

Quizplus · Accepted Answer

The presence of a strongly skewed sample with an extreme outlier (932.1 micrograms/gram) and a small sample size (only 17 dolphins) can significantly affect the reliability of a confidence interval for the mean, making option C the correct reason for not computing a 95% confidence interval in this context.

A Study Measured the Levels of Mercury in Livers (Microgram