政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/56392
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文笔数/总笔数 : 113656/144643 (79%)
造访人次 : 51722166      在线人数 : 586
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧：
  • 您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果
  • 若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据
    •  进阶搜寻


    请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/56392


    题名: 解析台灣民眾的統獨偏好---從抽樣分配的假設出發
    其它题名: A New Approach to Analyze Taiwanese Public Opinion toward Future Cross-Strait Relations
    作者: 俞振華
    贡献者: 行政院國家科學委員會
    國立政治大學選舉研究中心
    关键词: 統獨偏好測量;潛在抽樣分配;變異數不等選項模型;貝氏統計分析
    unification-independence measurement;latent sampling distribution;heterogenous choice model;Bayesian statistical approach
    日期: 2010
    上传时间: 2012-12-05 11:07:34 (UTC+8)
    摘要: 長期以來，台灣民眾的統獨偏好一直是國內外研究台灣政治發展的學者所關注的焦點。學者探究台灣民眾統獨偏好一向不遺餘力。過去數年來，學界也發展了許多不同的方法來測量民眾的統獨偏好。大體而言，主要的測量方式包括早期由政治大學選舉研究中心所發展的「統獨偏好六分類測量」、吳乃德（1992；1993）所提出的「條件問句測量」及其變型 (Chu 2004)，及至近來結合兩者的各式「交叉量表」(耿曙、劉嘉薇、陳陸輝 2009；Hsieh and Niou 2005)等。這些測量方法所著重的層面不一而足，有的為了建立統獨偏好的理論基礎，有的為了增強測量工具的效度。但所有方法都是為了釐清統獨議題的本質，探求台灣民眾究竟如何看待統獨問題。過去與民眾統獨偏好相關的研究，不論是偏重理論面的探討，或是強調方法上的精進，都是利用調查資料進行實証分析，透過比較樣本中個人態度的差異，來呈現台灣民眾統獨偏好的分佈。然而，至今所有相關的實証分析皆奠基於兩點相當重要，但從未明示的假設：第一、每位受訪者的統獨相關態度分別來各個無法觀察得到的潛在抽樣分配 (Latent sampling distribution)。各個抽樣分配有一個平均數 (Mean)及變異數 (Variance)。第二、各個潛在抽樣分配之間只可能會有平均數的差別，而沒有變異數的差別。換句話說，過去的研究者或許只在乎解釋為何各個潛在抽樣分配之間會有平均數的差別（譬如解釋為何受訪者A的偏好位置和受訪者B的偏好位置會不同），而對於變異數是否有差異完全沒興趣。本研究的主要目的是藉由與過去不同的潛在抽樣分配假設，來重新審視並測量台灣民眾的統獨偏好。研究申請人假定，台灣民眾不同的統獨偏好，其潛在抽樣分配存有顯著的差異—不但平均數不同，變異數也不相同。如果該假定成立，本研究將進一步透過貝氏統計分析途徑，利用變異數不等選項模型（Heterogenous Choice Model）來探討哪些變數決定平均數的不同（即受訪者統獨偏好的位置）？又哪些因素影響變異數的差異（即受訪者統獨偏好的分佈）？藉由在方法上創新的實証分析，本研究將重新釐清既有統獨偏好的理論架構，探究民眾在表達統獨偏好時，「理念」與「務實」兩個考量層面究竟是如何交纏在一起？
    Over the past few decades, future cross-strait relations have been one of the major research agendas for scholars and policy makers who are interested in Taiwan’s political development. Scholars have strived hard to not only explore every dimension of the subject but also develop numerous methods to measure Taiwanese unification-independence preferences. Three major types of measurements can be identified—namely, a six-point scale developed by the Election Study Center at National Chengchi University, Nei-Teh Wu’s conditional preference approach and its modifications, and a number of cross-tab mixed scales that combine the first two types of measurements. It is believed that these measurements have been designed to fulfill different goals: while some were built to theorizing Taiwanese public opinion toward the unification-independence issues, others were proposed for the increase of measurement validity. With different goals, however, all measurements intend to uncover the real essence of the unification-independence issue by investigating how the general public views it. Previous empirical studies on Taiwanese unification-independence preferences have been conducted by using survey data and quantitative methods to explore the extent to which responses differ across samples. The underlying assumption of this approach, which has never been explicitly mentioned, is twofold: first, each response we observe is a random draw from an unobserved latent sampling distribution that has a mean and variance; second, while the means may differ across the sampling distributions, the variances are all the same. The assumption of equal variance also suggests that the mean seems to be the only parameter of substantive interest. The major purpose of this research is to revisit the measurement of Taiwanese public opinion toward future cross-strait relations as we relieve the previous assumption of an equal variance for latent sampling distributions. Specifically, we hypothesize that the latent sampling distributions of Taiwanese unification-independence preferences may comprise different means and unequal variances. If that is the case, we will then apply Bayesian statistical approach to form a set of heterogenous choice models to investigate what factors may contribute to explain the differences among means (i.e., differences among locations of responses) and what factors may result in variation of variances (i.e., differences among distributions of responses). On the basis of methodological innovation, this empirical analysis will explain how an individual’s “idealistic” and “pragmatic” considerations entwined with each other to determine his/her opinion toward future cross-strait relations.
    關聯: 基礎研究
    學術補助
    研究期間:9908~ 10007
    研究經費:767仟元
    数据类型: report
    显示于类别:[選舉研究中心] 國科會研究計畫

    文件中的档案:

    档案 大小格式浏览次数
    992410H004072.pdf2426KbAdobe PDF21824检视/开启


    在政大典藏中所有的数据项都受到原著作权保护.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈