課程資訊
課程名稱
因果模型
Causal Models 
開課學期
109-2 
授課對象
文學院  哲學研究所  
授課教師
鄧敦民 
課號
Phl7570 
課程識別碼
124 M8110 
班次
 
學分
3.0 
全/半年
半年 
必/選修
選修 
上課時間
星期四8,9,10(15:30~18:20) 
上課地點
哲研討室三 
備註
本課程中文授課,使用英文教科書。研究所:C領域。 大學部:(C)哲學專題群組。
總人數上限:15人 
Ceiba 課程網頁
http://ceiba.ntu.edu.tw/1092causalmodels 
課程簡介影片
 
核心能力關聯
核心能力與課程規劃關聯圖
課程大綱
為確保您我的權利,請尊重智慧財產權及不得非法影印
課程概述

「因果模型」(又稱作「結構方程模型」)是分析因果關聯與進行因果推理時,十分重要的工具。這套工具已經發展得相當完整,並且被廣泛地應用在社會科學的許多領域中,也被應用在許多的哲學理論上。例如,Woodward (2003)的因果解釋理論、Briggs (2012)的干預型反事實條件句理論、Schaffer (2016)的形上立基之結構方程進路等等,都訴諸了因果模型這樣的工具,來幫助我們將重要的哲學概念加以理論化。

在本課程中,我們會很仔細地研究因果模型這套工具,詳細研讀Pearl (2009)的經典著作:Causality: Models, Reasoning, and Inference (CUP)。因果模型的技術細節,以及因果模型的哲學意涵,也會在課程中詳加討論。

Causal models, also known as ‘structural equation models’, are very important tools for analyzing causal connections and making causal inference. These tools have already been well developed and widely applied in many areas in social sciences, and also in many philosophical theories. For instance, Woodward’s (2003) theory of causal explanation, Briggs’s (2012) theory of interventionist counterfactuals, Schaffer’s (2016) structural equation approach to metaphysical grounding, etc., all invoke causal models to help theorize important philosophical concepts.

In this course, we shall carefully study causal models by going through Pearl’s (2009) Causality: Models, Reasoning, and Inference (CUP). The technical details and the philosophical significance of causal models will also be discussed in class.
 

課程目標
本課程目標在於使學生
(1) 完整掌握因果模型這套工具;
(2) 對於因果模型的技術細節與哲學意涵有大致的掌握;
(3) 有能力應用因果模型來處理哲學議題。

In the end of the course, students are expected to
(1) have a comprehensive understanding of causal models;
(2) have some understanding of the technical details and the philosophical significance of causal models; and
(3) have the ability to apply causal modeling to deal with relevant philosophical issues
 
課程要求
每週修課同學須閱讀指定閱讀材料,並輪流進行課堂報告。上課時修課同學亦須參與課堂討論。 
預期每週課後學習時數
 
Office Hours
 
指定閱讀
Pearl, Judea. 2009. Causality: Models, Reasoning, and Inference. 2nd edition. Cambridge: Cambridge University Press. 
參考書目
Spirtes, Peter, Clark Glymour, and Richard Scheines. 2000. Causation, Prediction, and Search. 2nd edition. Cambridge, Mass.: MIT Press.

Pearl, Judea, Madelyn Glymour, and Nicholas P. Jewell. 2016. Causal Inference in Statistics: A Primer. John Wiley & Sons Ltd.

Pearl, Judea, and Dana Mackenzie. 2018. The Book of Why: The New Science of Cause and Effect. New York: Basic Books. 
評量方式
(僅供參考)
 
No.
項目
百分比
說明
1. 
課堂參與 
40% 
 
2. 
期末考試 
60% 
 
 
課程進度
週次
日期
單元主題
第1週
2/25  Introduction 
第2週
3/04  Introduction to probabilities, graphs, and causal models I (ch.1 pp.1-20) 
第3週
3/11  Introduction to probabilities, graphs, and causal models II (ch.1 pp.21-40) 
第4週
3/18  A theory of inferred causation (ch.2 pp.41-56) 
第5週
3/25  Causal diagrams and the identification of causal effects I (ch.2 57-64, ch.3 pp.65-74) 
第6週
4/01  溫書假(調整放假) 
第7週
4/08  Causal diagrams and the identification of causal effects II (ch.3 pp.75-94) 
第8週
4/15  Actions, plans, and direct effects I (ch.3 pp.95-104, ch.4 pp.107-115) 
第9週
4/22  Midterm break 
第10週
4/29  Actions, plans, and direct effects II (ch.4 pp.116-132) 
第11週
5/06  Simpson’s paradox, confounding, and collapsibility (ch.6 pp.173-191) 
第12週
5/13  The logic of structure-based counterfactuals I (ch.6 pp.192-200, ch.7 pp.201-210) 
第13週
5/20  The logic of structure-based counterfactuals II (ch.7 pp.211-229) 
第14週
5/27  The logic of structure-based counterfactuals III (ch.7 pp.230-248) 
第15週
6/03  Probability of causation: interpretation and identification (ch.7 pp.249-257; ch.9 pp.283-291) 
第16週
6/10  Probability of causation: interpretation and identification (ch.9 pp.292-308) 
第17週
6/17  The actual cause (ch.10)