(a)Bookwork. Expect them to say that, provided a r.v.
has a finite mean
then, given a random sample of size
, then the sample mean
is such that
. Of course, they will not know this limiting argument andcan be expected to answer via the asymptotic result that
. A good studentmay comment that the result is exact if sampling from a normal distribution, but then thatit is not the CLT being used. Moreover, any statistic for which an average of independentrandom variables is being used will satisfy the CLT (e.g.
) provided the relevant moments exist.
(b) Assumption – normally distributed population of expenditures (plus randomsampling).90% CI requires 125.40
distribution). This is the interval
(c) If mean expenditure was $116 and inflation is 3% then expenditure in terms of thisyear’s prices is 116.1.03, which is $119.48. Now have a simple hypothesis test to conduct
H H Suppose
Test statistic is
.Therefore, at any reasonable significance level,
cannot be rejected (c.v. = 1.708).
(d) Type I error – reject hypothesis that
erroneously in favour of
. Type IIerror, failure to reject
in favour of
is, in fact, appropriate.
(e) Now expect a description of a test of difference between two means. (The students are NOT given the appropriate sample variance so they cannot attempt the computations.)They would again note that last year’s prices must be indexed to the present (or viceversa), so $116 in last year’s dollars would be $119.48 and the same would then need to