A New Measure of Congruence: The Earth Mover's Distance

被引:37
|
作者
Lupu, Noam [1 ]
Selios, Lucia [2 ]
Warner, Zach [3 ]
机构
[1] Vanderbilt Univ, Dept Polit Sci, Nashville, TN 37203 USA
[2] Univ Republica, Inst Ciencia Polit, UA-11200 Montevideo, Uruguay
[3] Univ Wisconsin, Dept Polit Sci, Madison, WI 53706 USA
关键词
ELITE-MASS CONGRUENCE; IDEOLOGICAL CONGRUENCE; POLITICAL REPRESENTATION; ELECTION LAWS; VISIONS; PREFERENCES; ALGORITHM; CITIZENS; LINKAGES; PARTIES;
D O I
10.1017/pan.2017.2
中图分类号
D0 [政治学、政治理论];
学科分类号
0302 ; 030201 ;
摘要
Scholars of representation are increasingly interested in mass-elite congruence-the degree to which the preferences of elected elites mirror those of voters. Yet existing measures of congruence can be misleading because they ignore information in the data, require arbitrary decisions about quantization, and limit researchers to comparing masses and elites on a single dimension. We introduce a new measure of congruence-borrowed from computer science-that addresses all of these problems: the Earth Mover's Distance (EMD). We demonstrate its conceptual advantages and apply it to two debates in research on mass-elite congruence: ideological congruence in majoritarian and proportional systems and the determinants of congruence across countries in Latin America. We find that improving measurement using the EMD has important implications for inferences regarding both empirical debates. Even beyond studies of congruence, the EMD is a useful and reliable way for political scientists to compare distributions.
引用
收藏
页码:95 / 113
页数:19
相关论文
共 50 条
  • [21] The Earth Mover's Distance as a Metric for Image Retrieval
    Yossi Rubner
    Carlo Tomasi
    Leonidas J. Guibas
    International Journal of Computer Vision, 2000, 40 : 99 - 121
  • [22] EARTH-MOVER'S DISTANCE AS A TRACKING REGULARIZER
    Charles, Adam S.
    Bertrand, Nicholas P.
    Lee, John
    Rozell, Christopher J.
    2017 IEEE 7TH INTERNATIONAL WORKSHOP ON COMPUTATIONAL ADVANCES IN MULTI-SENSOR ADAPTIVE PROCESSING (CAMSAP), 2017,
  • [23] The Earth Mover's Distance as a metric for image retrieval
    Rubner, Y
    Tomasi, C
    Guibas, LJ
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2000, 40 (02) : 99 - 121
  • [24] EARTH MOVER DISTANCE ON SUPERPIXELS
    Boltz, Sylvain
    Nielsen, Frank
    Soatto, Stefano
    2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 4597 - 4600
  • [25] Using Earth Mover's Distance for audio clip retrieval
    Peng, Yuxin
    Fang, Cuihua
    Chen, Xiaoou
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2006, PROCEEDINGS, 2006, 4261 : 405 - +
  • [26] An Earth Mover's Distance Based Graph Distance Metric For Financial Statements
    Noels, Sander
    Vandermarlieret, Benjamin
    Bastiaensent, Ken
    De Bie, Tijl
    2022 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE FOR FINANCIAL ENGINEERING AND ECONOMICS (CIFER), 2022,
  • [27] Matching point sets with respect to the Earth Mover's Distance
    Cabello, Sergio
    Giannopoulos, Panos
    Knauer, Christian
    Rote, Gunter
    COMPUTATIONAL GEOMETRY-THEORY AND APPLICATIONS, 2008, 39 (02): : 118 - 133
  • [28] Extending Earth Mover's Distance to Occluded Face Verification
    Vidal, Pedro
    Chu, Henry
    Biesseck, Bernardo
    Granada, Roger
    Fuhr, Gustavo
    Menotti, David
    2023 36TH CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, SIBGRAPI 2023, 2023, : 49 - 54
  • [29] The Earth Mover's Distance as a Metric for the Space of Inorganic Compositions
    Hargreaves, Cameron J.
    Dyer, Matthew S.
    Gaultois, Michael W.
    Kurlin, Vitaliy A.
    Rosseinsky, Matthew J.
    CHEMISTRY OF MATERIALS, 2020, 32 (24) : 10610 - 10620
  • [30] Accurate Approximation of the Earth Mover's Distance in Linear Time
    Min-Hee Jang
    Sang-Wook Kim
    Christos Faloutsos
    Sunju Park
    Journal of Computer Science & Technology, 2014, (01) : 142 - 154