Stat 5102 (Geyer) Midterm 1
The joint density is
Equation (11.36) in the notes gives the mode of the gamma distribution: shape parameter minus one over scale parameter, in this case
By Example 11.2.4 in the notes, the posterior distribution is Normal where
The HPD region for a normal posterior distribution is
The likelihood for is
A 95% C. I. for is
Equation (10.37) in the notes gives the log likelihood for the two-parameter normal. To convert to the log likelihood for this problem we need to plug in for both and giving
The solution given above is perhaps the easiest. Another contender for the easiest expands the binomial in (1) giving
The deriviatives are a bit easier and the expectations are a bit harder than the first solution, but both are fairly easy.
The alternate solution that uses the empirical parallel axis theorm to ``simplify'' (1) giving
The alternate solution that expands the binomial in (2) giving
Example 9.5.4 in the notes gives the math for this problem. The natural estimates of and are and . The natural test statistic is divided by its standard error (estimated standard deviation). As explained in the example, the natural choice for the standard error when we assume uses the pooled estimate of (and ), which is
Not part of the question, but of interest in real life is the interpretation of the -value. According to conventional standards of evidence, this is a ``statistically significant'' result because . Since is not that far below .05, this is not absolutely compelling evidence of effectiveness of the new treatment, but it is fairly compelling.
The pooled estimator of and under is just the number of deaths in both groups divided by the number of subjects in both groups, so is also
An asymptotically equivalent way to do the problem (almost no difference when and are large and is true) uses the standard error estimate
Note that this method is not recommended in real life, not because there is anything wrong with it, but because it's not the method taught in intro statistics books and hence people will argue.