A number of considerations suggested that the most appropriate place to start the exposition was with the tonal hierarchy imposed on tones by key contexts in Western music. First, the experimental method is quite simple and illustrates certain issues in experimental design. Second, there are relatively clear intuitions and theoretical predictions for this case; other cases with less clear predictions will be presented later. Third, the techniques of data analysis introduced here, correlation and multidimensional scaling, are used again in numerous other studies. Finally, the results obtained here parallel those found in other areas of human cognition and perception, suggesting that a general psychological principle is operating in the particular musical case considered.