Discussion for ‘indexes of contrast and quantitative significance for comparisons of two groups’

✍ Scribed by Gary G. Koch

• Publisher: John Wiley and Sons
• Year: 1999
• Tongue: English
• Weight: 74 KB
• Volume: 18
• Category: Article
• ISSN: 0277-6715
• DOI: 10.1002/(sici)1097-0258(19991015)18:19<2585::aid-sim363>3.0.co;2-o

✦ Synopsis

The paper by Feinstein provides clear and interesting discussion for interpreting indexes which describe disparity between two groups. The discussion is most helpful in explaining the logical relationships among alternative indexes, and in identifying their strengths and weaknesses. Feinstein quite properly emphasizes the desirability of indexes that clearly represent the importance of a between-group di!erence to the health or well being of a general population. However, no index can be expected to ful"l this role in isolation, without information on its components from the respective groups (for example, the numerators and denominators of a ratio) and their corresponding severities and costs. Moreover, the search for simplicity combined with the author's focus on indexes of contrasts for samples, rather than for the populations they represent, leads to recommendations that harbour ambiguities and severe restrictions not initially apparent.