English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 91913/122132 (75%)
Visitors : 25757658      Online Users : 346
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://nccur.lib.nccu.edu.tw/handle/140.119/58469

    Title: 因果推論與觀察研究:「反事實模型」之思考
    Other Titles: Causal Inference and Observational Study: On the Counterfactual Model of Causality
    Authors: 黃紀
    Huang, Chi
    Contributors: 政大政治系
    Keywords: 因果推論;觀察研究;反事實之因果模型;評估研究;非隨機分派之效應模型
    Causal inference;Observational study;Counterfactual model of causality;Evaluation research;Treatment effects model with nonrandom assignment;Endogenous treatment
    Date: 2008-04
    Issue Date: 2013-06-21 10:34:13 (UTC+8)
    Abstract: 「反事實之因果模型」的出發點很簡單:要確認D是Y的因,也必須反過來思考「那若沒有D的話Y會如何?」故因果效應的推論,應不只是建立在D和Y聯袂發生的規律上,還要進一步比較「實際結果」(事實)和「可能但未發生的結果」(反事實)兩者之差異。這固然不是因果推論唯一的定義與思維方式,但這個模型一方面能刺激「反事實」的逆向思考,另一方面卻又能將觀察不到的假想「反事實」操作化為控制(比較)組,逐漸發展成一套共通的因果推論架構,貫穿隨機分派實驗、準實驗、自然實驗、以及非實驗之觀察研究,不但邏輯一貫,而且更能落實到具體可行的分析方法,對社會科學中無法或不易進行實驗、但仍希望推論因果的觀察研究,有相當大的啟發,並澄清了傳統實證分析方法中,過於偏重觀察得到的因果規律等若干不夠精確的觀念,刺激了另一波方法論的反思。
    The core of the counterfactual model of causality (CMC) is simple. To argue that D is the cause of Y, we must ask “What would Y have been if D were not the case?” In other words, we should not rely solely on the observed regularities to infer causality. Instead, researchers need to compare the realized outcome (i.e., factual) with its potential outcome (i.e., counterfactual). This potential outcome model forces us to explicitly state and make operational the counterfactual with a clear implication of what should be controlled or compared. It has been developed into a unified framework for causal inference based on randomized experiments, quasi-experiments, natural experiments, as well as non-experimental observational studies. This recent trend is indeed exciting for social science research targeted to address cause-and-effect questions and yet impossible or difficult to conduct lab experiments. CMC stimulates a new wave of reexamination of more traditional concepts and methods of causal inference in social science research.
    Relation: 社會科學論叢, 2(1), 1-22
    Data Type: article
    Appears in Collections:[政治學系] 期刊論文

    Files in This Item:

    File Description SizeFormat
    21122.pdf1724KbAdobe PDF877View/Open

    All items in 政大典藏 are protected by copyright, with all rights reserved.

    社群 sharing

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback