(a) The following are the OTIS scores (similar to IQ scores ) for a
sample of 15 professional hospital workers:
79, 82, 123, 106, 125, 98, 95, 129, 90, 111, 99, 116, 106, 107,
100.
Find a 99% C.I. for the mean OTIS score of all such people.
( You'll find the Stata command ci name , level(99) helpful).
(b) The data in Table 1 (click here) are taken
from a study on Parkinson's disease, a disease that, among other things,
affects a person's ability to speak. Eight of the people in this study
had a received an operation to treat the disease. Each patient was given
several tests. The result of one of these tests are shown in the table.
The higher score, the more problems with speaking. Construct a 95% C.I.
for the difference in the means and comment briefly.
( You'll find the Stata command ttest name1=name2, unpaired helpful).
(c) A shoe company wanted to compare two materials, A and B, for use on
the soles of boys' shoes. They recruited 10 boys and each boy tested both
materials and they obtained the data in Table 2
(click here). Construct a 95% C.I. for the difference in the means
of wear.
(You'll find the Stata command ttest name1=name2, helpful).
Simulate in Stata twenty random variables, x1, x2 ... x20, each
containing 100 independent observations distributed uniformly on (0,1)
(create, as usual, a log file called ab4.log, where ab are your
initials).
For each of these 20 samples, construct a 95% C.I. for the population
mean and check if it contains the true value of the mean. How many
intervals contain the true value ? In this case, is it an exact or an
approximate C.I ? Comment.