We extend rank-based dependence measures like Spearman's rho to categorical data so that the same Β±1 limits are always reached under complete dependence. A goodness-of-ΓΏt procedure is derived for dependence models using copulas.
Strategic measure of competitiveness for ranked data
β Scribed by Andrew J. Rohm; Sangit Chatterjee; Mohamed Habibullah
- Publisher
- John Wiley and Sons
- Year
- 2004
- Tongue
- English
- Weight
- 130 KB
- Volume
- 25
- Category
- Article
- ISSN
- 0143-6570
- DOI
- 10.1002/mde.1111
No coin nor oath required. For personal study only.
β¦ Synopsis
Abstract
This study offers a method of evaluating the stability of ranks of a data vector over time. In particular, we study improvement of a process observed over time where the data is ranked. The degree of competition at a major tennis championship (Wimbledon) as well as how trends in the level of competition have changed over time is studied. A metric for shifts in competitiveness and a new statistical methodology is proposed. The findings suggest that competitiveness at Wimbledon has been extremely high. The study offers implications for the sport of tennis as well as an approach to measuring competitive dynamics that can be applied to other contexts. Copyright Β© 2004 John Wiley & Sons, Ltd.
π SIMILAR VOLUMES
## Abstract Economists have long used stateβcollected discharge data to construct HirschmanβHerfindahl (HH) indices measuring hospital competition. Since data are collected to determine the facility providing the service rather than ownership, the difference between the number of reporting faciliti