Innis Lecture: Inference on income distributions

被引:2
|
作者
Davidson, Russell [1 ,2 ]
机构
[1] McGill Univ, Dept Econ, Montreal, PQ H3A 2T5, Canada
[2] McGill Univ, CIREQ, Montreal, PQ H3A 2T5, Canada
来源
CANADIAN JOURNAL OF ECONOMICS-REVUE CANADIENNE D ECONOMIQUE | 2010年 / 43卷 / 04期
关键词
C12; C13; C81; D31; I32; FREE STATISTICAL-INFERENCE; GENERALIZED GINI INDEXES; STOCHASTIC-DOMINANCE; CONFIDENCE-INTERVALS; LORENZ CURVES; ASYMPTOTIC-DISTRIBUTION; INEQUALITY MEASURES; POVERTY; WELFARE; SHARES;
D O I
10.1111/j.1540-5982.2010.01608.x
中图分类号
F [经济];
学科分类号
02 ;
摘要
P>This paper attempts to provide a synthetic view of varied techniques available for performing inference on income distributions. Two main approaches can be distinguished: one in which the object of interest is some index of income inequality or poverty, the other based on notions of stochastic dominance. From the statistical point of view, many techniques are common to both approaches, although of course some are specific to one of them. I assume throughout that inference about population quantities is to be based on a sample or samples, and, formally, all randomness is due to that of the sampling process. Inference can be either asymptotic or bootstrap based. In principle, the bootstrap is an ideal tool, since in this paper I ignore issues of complex sampling schemes and suppose that observations are IID. However, both bootstrap inference and, to a considerably greater extent, asymptotic inference can fall foul of difficulties associated with the heavy right-hand tails observed with many income distributions. I mention some recent attempts to circumvent these difficulties.Ce memoire tente de fournir une vue synthetique des diverses techniques disponibles pour faire des inferences a partir des repartitions de revenus. On peut distinguer deux approches principales: l'une dans laquelle l'objet vise est un indice d'inegalite de revenus ou de pauvrete; l'autre est construite sur des notions de dominance stochastique. D'un point de vue statistique, plusieurs techniques sont utilisees par les deux approches, mais certaines techniques sont specifiques a l'une ou a l'autre approche. L'auteur postule que l'inference a propos de quantites demographiques est fondee sur un echantillon ou des echantillons, et que formellement tout le caractere aleatoire est attribuable au processus d'echantillonnage. L'inference est soit asymptotique, soit derivee par des technique de bootstrap. En principe, la seconde facon de proceder est un outil ideal, puisque dans ce memoire l'auteur ignore les problemes de procedures d'echantillonnage complexes et presume que les observations sont IDD. Cependant, la seconde facon de proceder, et encore plus la premiere, peuvent rencontrer des difficultes associees au fait que l'on observe des queues de distribution epaisses vers la droite dans plusieurs profils de repartition des revenus. L'auteur mentionne certains efforts recents pour contourner ces difficultes.
引用
收藏
页码:1122 / 1148
页数:27
相关论文
共 50 条
  • [1] Innis Lecture: Equity and equality
    Duclos, Jean-Yves
    CANADIAN JOURNAL OF ECONOMICS-REVUE CANADIENNE D ECONOMIQUE, 2006, 39 (04): : 1073 - 1104
  • [2] Innis lecture: Hedonic equilibrium
    Peters, Michael
    CANADIAN JOURNAL OF ECONOMICS-REVUE CANADIENNE D ECONOMIQUE, 2007, 40 (04): : 1060 - 1077
  • [3] Indirect Inference for Fitting Income Distributions
    Jammalamadaka S.R.
    Tian G.
    Journal of the Indian Society for Probability and Statistics, 2018, 19 (2) : 345 - 358
  • [4] Inference for Income Distributions Using Grouped Data
    Hajargasht, Gholamreza
    Griffiths, William E.
    Brice, Joseph
    Rao, D. S. Prasada
    Chotikapanich, Duangkamon
    JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 2012, 30 (04) : 563 - 575
  • [5] Innis Lecture: Returns on student loans in Canada
    Lochner, Lance
    Liu, Qian
    Gervais, Martin
    CANADIAN JOURNAL OF ECONOMICS-REVUE CANADIENNE D ECONOMIQUE, 2021, 54 (04): : 1495 - 1524
  • [6] Innis Lecture: Environmental crises: past, present, and future
    Taylor, M. Scott
    CANADIAN JOURNAL OF ECONOMICS-REVUE CANADIENNE D ECONOMIQUE, 2009, 42 (04): : 1240 - 1275
  • [7] Innis lecture: Explorations in medium-run macroeconomics
    Beaudry, P
    CANADIAN JOURNAL OF ECONOMICS-REVUE CANADIENNE D ECONOMIQUE, 2005, 38 (04): : 1136 - 1159
  • [8] Classical and Bayesian Inference for Income Distributions using Grouped Data
    Eckernkemper, Tobias
    Gribisch, Bastian
    OXFORD BULLETIN OF ECONOMICS AND STATISTICS, 2021, 83 (01) : 32 - 65
  • [9] Innis Lecture: The time of your life: The mortality and longevity of Canadians
    Milligan, Kevin
    CANADIAN JOURNAL OF ECONOMICS-REVUE CANADIENNE D ECONOMIQUE, 2024, 57 (04): : 1088 - 1108
  • [10] Innis lecture: Canadian policies for broad-based prosperity
    Trefler, Daniel
    CANADIAN JOURNAL OF ECONOMICS-REVUE CANADIENNE D ECONOMIQUE, 2008, 41 (04): : 1156 - 1184