Expert: Asmaa Abd Elhameed Ahmed - 9/29/2009

Question
Hi, can you explain the sampling design flaws in the make belief experiment below? I think he is supposed to use alpha 2 tail and sampling may not be random... any other things?


"A researcher wants to determine whether the mean size of fish in the Great Lakes (Lakes Superior, Eerie, Ontario, Michigan, and Huron) is greater than 1m in length. To do so, he samples 10 lake trout in each of three locations in Lake Superior (30 individuals total). He uses a one sample t-test with a critical value - t0.05(2),29."

Answer
hi,
1-first he should do sampling by cluster random sampling i.e.he should consider each of the great lakes as cluster then randomly select from them and then the clusters selected taken as a whole
2- he should do 1 tailed t test as he previously testing that the length is longer(only in one direction)