Premium
News or Noise? An Analysis of U.S. News and World Report's Ranking Scores
Author(s) -
Clarke Marguerite
Publication year - 2002
Publication title -
educational measurement: issues and practice
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.158
H-Index - 52
eISSN - 1745-3992
pISSN - 0731-1745
DOI - 10.1111/j.1745-3992.2002.tb00105.x
Subject(s) - ranking (information retrieval) , jackknife resampling , rank (graph theory) , position (finance) , interpretation (philosophy) , noise (video) , psychology , econometrics , political science , statistics , sociology , mathematics , computer science , economics , information retrieval , artificial intelligence , combinatorics , finance , estimator , image (mathematics) , programming language
One of the biggest criticisms of the U.S. News and World Report rankings of colleges and graduate schools is that they are “falsely precise,’ creating a vertical column where a group might more properly exist. In this article, the jackknife method coupled with a linear regression model is used to illustrate uncertainty around the overall scores used to rank schools. Results indicate that the top 50 schools in each ranking can be shown to group in two to three bands. The implications of these findings are discussed in terms of the interpretation of a school's position in a ranking as well a s changes in that position over time. The article concludes with some recommenda‐ tions for both producers and consumers of these rankings.