Bayesian and Likelihood Inference for 2 x 2 Ecological Tables: An Incomplete-Data Approach

Ying Lu Department of Sociology, University of Colorado at Boulder, Boulder, CO 80309 e-mail: ying.lu{at}colorado.edu Aaron Strauss Department of Politics, Princeton University, Princeton, NJ 08544 e-mail: abstraus{at}princeton.edu e-mail: kimai{at}princeton.edu (corresponding author) Ecological inference is a statistical problem where aggregate-leveldata are used to make inferences about individual-level behavior.In this article, we conduct a theoretical and empirical studyof Bayesian and likelihood inference for 2 x 2 ecological tablesby applying the general statistical framework of incompletedata. We first show that the ecological inference problem canbe decomposed into three factors: distributional effects, whichaddress the possible misspecification of parametric modelingassumptions about the unknown distribution of missing data;contextual effects, which represent the possible correlationbetween missing data and observed variables; and aggregationeffects, which are directly related to the loss of informationcaused by data aggregation. We then examine how these threefactors affect inference and offer new statistical methods toaddress each of them. To deal with distributional effects, wepropose a nonparametric Bayesian model based on a Dirichletprocess prior, which relaxes common parametric assumptions.We also identify the statistical adjustments necessary to accountfor contextual effects. Finally, although little can be doneto cope with aggregation effects, we offer a method to quantifythe magnitude of such effects in order to formally assess itsseverity. We use simulated and real data sets to empiricallyinvestigate the consequences of these three factors and to evaluatethe performance of our proposed methods. C code, along withan easy-to-use R interface, is publicly available for implementingour proposed methods (Imai, Lu, and Strauss, forthcoming). Authors' note: This article is in the part based on two workingpapers by Imai and Lu, "Parametric and Nonparamateric BayesianModels for Ecological Inference in 2 x 2 Tables" and "QuantifyingMissing Information in Ecological Inference." Various versionsof these papers were presented at the 2004 Joint StatisticalMeetings, the Second Cape Cod Monte Carlo Workshop, the 2004Annual Political Methodology Summer Meeting, and the 2005 AnnualMeeting of the American Political Science Association. We thankanonymous referees, Larry Bartels, Wendy Tam Cho, Jianqing Fan,Gary King, Xiao-Li Meng, Kevin Quinn, Phil Shively, David vanDyk, Jon Wakefield, and seminar participants at New York University(the Northeast Political Methodology conference), at PrincetonUniversity (Economics Department and Office of Population Research),and at the University of Virginia (Statistics Department) forhelpful comments.     

Ecological Inference and Entropy-Maximizing: An Alternative Estimation Procedure for Split-Ticket Voting

Publication of King's A Solution to the Ecological InferenceProblem has rekindled interest in the estimation of unknowncell values in two- and three-dimensional matrices from knowledgeof the marginal sums. This paper outlines an entropy-maximizing(EM) procedure which employs more constraints than King's EImethod and produces mathematical rather than statistical procedures:the estimates are maximum-likelihood values. The mathematicsare outlined, and the procedure's use illustrated with a studyof ticket-splitting at New Zealand's first (1996) general electionusing the mixed-member proportional representation system, forwhich official figures provide a check against the EM estimateof the number voting a straight party ticket in each constituency.     

Trade‐Offs,Limitations, and Promises of Big Data in Social Science Research

The promise of “big data” is a grand one. The collection and aggregation of massive datasets and the development of analytical tools by which to study these data is part of cutting‐edge efforts across scientific disciplines, with social, behavioral, and economic sciences leading the way in many of these efforts. There has been a recent rise in National Science Foundation funding for “big data” research across directorates that coincides with scholarly, public, and governmental attention to the topic. Nonetheless, there are limitations and trade‐offs to “big data” research, particularly as it corresponds to scientific modes of inquiry and the limited range of topics that fall under its umbrella, that must be recognized and incorporated into the general understanding of its long‐term promise.     

Time Series Intervals and Statistical Inference: The Effects of Temporal Aggregation on Event Data Analysis

While many areas of research in political science draw inferencesfrom temporally aggregated data, rarely have researchers exploredhow temporal aggregation biases parameter estimates. With somenotable exceptions (Freeman 1989, Political Analysis 1:61–98;Alt et al. 2001, Political Analysis 9:21–44; Thomas 2002,"Event Data Analysis and Threats from Temporal Aggregation")political science studies largely ignore how temporal aggregationaffects our inferences. This article expands upon others' workon this issue by assessing the effect of temporal aggregationdecisions on vector autoregressive (VAR) parameter estimates,significance levels, Granger causality tests, and impulse responsefunctions. While the study is relevant to all fields in politicalscience, the results directly apply to event data studies ofconflict and cooperation. The findings imply that politicalscientists should be wary of the impact that temporal aggregationhas on statistical inference.     

残疾人社会保障:问题与对策

目前我国在残疾人社会保障方面还存在一些问题,主要表现在残疾人社会保障的供需矛盾突出、残疾人群体中贫困问题较为严重和残疾人社会保障城乡差距较大.为此,要采取以下对策:调动国家和社会力量,缓解供需矛盾;促进社会救济和社会保险相结合,改善残疾人的生活现状:统筹城乡残疾人社会保障制度,缩小城乡差距.     

Museums and the Active Citizen: Tackling the Problems of Social Exclusion

The aim of this paper is to attempt to determine the role of museums in combating social exclusion through facilitating active citizenship. It does this by presenting the results of an analysis that used a modified form of a model of citizenship created by Makela as a framework to explore the data generated by an empirical study. By focusing upon respondents in an holistic way, so understanding their experiences of museum based exhibitions and community development projects within the contexts of their lives, the study concludes that museums were able to overcome many of the barriers to active citizenship that were identified. However, it was also evident that they themselves were creating barriers as some were physically or intellectually inaccessible to a number of study participants. The most significant contribution of museums in developing active citizens was to provide a context for constructing a sense of identity and so develop greater self-confidence. The paper concludes that if the potential that museums have fostered is to be released government agencies need to work together.     

新疆籍流浪儿童社会融入障碍与对策初探——基于一项质性调查的研究

新疆籍流浪儿童在回归后,很难融入家乡的社会生活。通过文献、观察和访谈的质性方法,从经济、文化心理、社会公共关系三个方面,掌握其社会融入的状况和障碍。结合新疆籍流浪儿童的特殊性和新疆的区情,综合各种现有模式,试图提出合适的社会融入对策。     

Iterative Approaches to R x C Ecological Inference Problems: Where They Can Go Wrong and One Quick Fix

This article argues that a key step in King's iterative approachto R x C ecological inference problems—the aggregationof groups into broad conglomerate categories—can introduceproblems of aggregation bias and multimodality into data, inducingmodel violations. As a result, iterative EI estimates can beconsiderably biased, even when the original data conform tothe assumptions of the model. I demonstrate this problem intuitivelyand through simulations, show the conditions under which itis likely to arise, and illustrate it with the example of Colouredvoting during the 1994 elections in South Africa. I then proposean easy fix to the problem, demonstrating the usefulness ofthe fix both through simulations and in the specific South Africancontext.     

The Science of Public Administration: Problems,Presumptions, Progress,and Possibilities

Nearly 70 years ago, Dahl noted the difficulty of constructing a science of public administration that was plagued by three interrelated problems: values, behavior, and culture. Underlying all three problems was the presumption that public administration could establish a set of universal principles independent of moral or political ends, individual human differences, or social influences. In discussing these three broad and easily accessible themes, Dahl did more than identify and critique the field's problems and presumptions. He also provided a road map to move the field forward and establish a science of public administration. Drawing on the framework provided by Dahl, this article argues that the field has made considerable progress in recognizing, if not addressing, each problem raised by Dahl. Even so, several current presumptions or omissions are also identified that, if challenged, can provide additional possibilities to advance the science of public administration.     

中国社会科学研究的本土化与国际化探讨——兼论中国政治学的建设和发展

中国社会科学在向西方"取经"到本土化创新的发展过程中,既面临着本土化研究成果的供需矛盾,也经历了本土化与国际化的世纪争辩。本文在系统归纳、阐述并回答社会科学研究中"何为本土化""为何本土化""如何本土化"等基本问题的基础上,联系中国政治学学科发展,辨析研究对象或议题本土化、研究方法本土化、研究目的本土化、研究价值本土化之间的联系和差异,认为本土化是加快构建中国特色哲学社会科学体系的重要路径,但并非唯一路径。加快构建中国特色社会科学体系,促进学科知识体系的完善和进步,应摒弃西方中心取向,建构中国特色学科、学术和话语体系,并实现中国政治学本土化与国际化的有机结合。