"Linking" is a term given to a general class of procedures by which one represents scores X on one test or measure in terms of scores Y on another test or measure. A recent taxonomy by Holland and Dorans (2006; Holland, 2007) organizes the various types of links into three broad categories: prediction, scale aligning, and equating. In his article "Thinking About Linking," Newton (2010) decries taxonomies such as the one given by Holland and Dorans (2006) because, according to Newton, these frameworks treat equating as the only legitimate form of linking. Newton's discussion may be divided into three major arguments: (a) existing linking frameworks are overly restrictive; (b) these frameworks do not well serve the needs of tests in the English educational system; and (c) the notion of comparability must be redefined to allow the legitimate use of scores from different tests for a particular purpose. This commentary addresses each of Newton's arguments in turn, focusing upon how what educators want to say about the relationship between two tests must drive the data they collect to demonstrate that relationship.