A contest model is constructed to examine the existence of conference bias in college basketball's Ratings Percentage Index (RPI). Though a general RPI bias has been identified in previous literature, this is the first study to address whether the bias is random or systematic in nature. Within the theoretical model, the RPI is shown to be systematically biased against teams in high ability conferences, even when all teams play to expectation and can be transitively compared. Further, the bias can prevent the RPI from producing an ordinal mapping from revealed team ability level to the real number line. Given the longevity of the controversial RPI as the NCAA''s primary measure of team ability, these results may indicate that the NCAA is serving a demand for team heterogeneity in selecting for the NCAA Men''s Basketball Tournament.
Download Info
To download:
If you experience problems downloading a file, check if you have the
proper application to
view it first. Information about this may be contained
in the File-Format links below. In case of further problems read
the IDEAS help
page. Note that these files are not on the IDEAS
site. Please be patient as the files may be large.