While we expect relatively expensive wines to have more desirable characteristics than relatively inexpensive wines, people are often confused in their assessment of the quality of wine in a blind test (New York Times, December 16, 2010).

In a recent experiment at a local winery, the same wine is served to two groups of people but with different price information. In the first group, 60 people are told that they are tasting a $25 wine, of which 48 like the wine. In the second group, only 20 of 50 people like the wine when they are told that it is a $10 wine.

The experiment is conducted to determine if the proportion of people who like the wine in the first group is more than 20 percentage points higher than those in the second group. Conduct this test at the 5% significance level using the p -value approach. PG-69