Presentation: “Causal Conclusions”. Homework Analogies – pp. 81-90 Review: – Exercises (models for exam) Analogical Reasoning, e.g., ex. 8.4 Causal Argumentation,

Slides:



Advertisements
Similar presentations
Reason and Argument Induction (Part of Ch. 9 and part of Ch. 10)
Advertisements

Andrea M. Landis, PhD, RN UW LEAH
© LOUIS COHEN, LAWRENCE MANION & KEITH MORRISON
Chapter 3: The Experimental Research Approach Introduction Introduction –Goal is to discover the effects of presumed causes This multimedia product and.
Causal Reasoning Observation Large text on my Internet screen Question Why the large text? Hypothesis Accessibility features are activated Evidence Normal.
Part I: Mill’s Methods redux
Fallacies Related to Cause & Effect
Welcome to Dave Penner’s Presentation on Inductive Reasoning!
Explanations. D1. The explanandum is that which is to be explained in an explanation. D2. The explanans is that which does the explaining in an explanation.
Critical Thinking: Chapter 10
EPIDEMIOLOGY AND BIOSTATISTICS DEPT Esimating Population Value with Hypothesis Testing.
Developing Ideas for Research and Evaluating Theories of Behavior
How Psychologists Ask and Answer Questions
DESIGNING, CONDUCTING, ANALYZING & INTERPRETING DESCRIPTIVE RESEARCH CHAPTERS 7 & 11 Kristina Feldner.
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc Chapter 11 Introduction to Hypothesis Testing.
The Research Design.
RESEARCH IN EDUCATION Chapter I. Explanations about the Universe Power of the gods Religious authority Challenge to religious dogma Metacognition: Thinking.
Magister of Electrical Engineering Udayana University September 2011
Fundamentals of Data Analysis Lecture 4 Testing of statistical hypotheses.
Understanding Statistics
Chapter 4 Introduction to Hypothesis Testing Introduction to Hypothesis Testing.
Chapter 2 Psychology’s Scientific Method
1 Research Design The Basics of Social Research Babbie.
Association between 2 variables
Inductive Generalizations Induction is the basis for our commonsense beliefs about the world. In the most general sense, inductive reasoning, is that in.
By: Ellyn Polley.  One causes the other  Useful to establish claims of policy  Event A is necessary for event B to occur  Ex.- The Dog hit the table.
BINOMIALDISTRIBUTION AND ITS APPLICATION. Binomial Distribution  The binomial probability density function –f(x) = n C x p x q n-x for x=0,1,2,3…,n for.
Chapter 12 CAUSAL REASONING.
Basic Concepts of Correlation. Definition A correlation exists between two variables when the values of one are somehow associated with the values of.
Chapter 5 Parameter estimation. What is sample inference? Distinguish between managerial & financial accounting. Understand how managers can use accounting.
Invitation to Critical Thinking Chapter 9 Lecture Notes Chapter 9.
22 February From Theory to Evidence. Hypothesis vs. Research Question When no expected direction to relationship. Exploratory research, not deductive.
Economics 173 Business Statistics Lecture 4 Fall, 2001 Professor J. Petry
Review of Research Methods. Overview of the Research Process I. Develop a research question II. Develop a hypothesis III. Choose a research design IV.
Chapter Two: Explaining Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.
INDUCTIVE LOGIC DEDUCTION= DRAWING OUT IMPLICIT “KNOWLEDGE” OR CLAIMS FROM PREMISES. INDUCTION= EXPANDING “KNOWLEDGE” BY TESTING TRUTH OF THE PREMISES.
Digression - Hypotheses Many research designs involve statistical tests – involve accepting or rejecting a hypothesis Null (statistical) hypotheses assume.
Chapter 10 Lecture Notes Causal Inductive Arguments.
URBDP 591 I Lecture 4: Research Question Objectives How do we define a research question? What is a testable hypothesis? How do we test an hypothesis?
SAMPLING DISTRIBUTION OF MEANS & PROPORTIONS. PPSS The situation in a statistical problem is that there is a population of interest, and a quantity or.
Graduate School for Social Research Autumn 2015 Research Methodology and Methods of Social Inquiry socialinquiry.wordpress.com Causality.
Matching. Objectives Discuss methods of matching Discuss advantages and disadvantages of matching Discuss applications of matching Confounding residual.
INDUCTIVE ARGUMENTS The aim of this tutorial is to help you learn to recognize, analyze and evaluate inductive arguments.
Chapter Two Methods in the Study of Personality. Gathering Information About Personality Informal Sources of Information: Observations of Self—Introspection,
Philosophical Question of the Day! Let’s suppose that you and your family members (Mom, Dad, and Sister) went to eat a buffet dinner at the Golden Corral.
Regression Analysis: A statistical procedure used to find relations among a set of variables B. Klinkenberg G
Fundamentals of Data Analysis Lecture 4 Testing of statistical hypotheses pt.1.
1 Causation in epidemiology, confounding and bias Imre Janszky Faculty of Medicine NTNU.
Causal Arguments MILL’S METHODS AND SCIENTIFIC REASONING.
BHS Methods in Behavioral Sciences I April 7, 2003 Chapter 2 – Introduction to the Methods of Science.
RESEARCH METHODS B 1. SESSION 2: SCIENCE AND RESEARCH (cont.) V.Scientific explanations VI. Theorizing and logical process 2.
Scientific Method Vocabulary Observation Hypothesis Prediction Experiment Variable Experimental group Control group Data Correlation Statistics Mean Distribution.
Introduction to Area Studies Causal Analysis Presenter – Sue Nah RHIE.
Fundamentals of Data Analysis Lecture 10 Correlation and regression.
Induction, Analogy, Causation. There are two kinds of arguments: inductive and deductive Inductive arguments are much more common, but it is also much.
GS/PPAL Research Methods and Information Systems
What is Inductive Reasoning?
Inductive Logic and Analogy
Research Issues.
Chapter 4: Inductive Arguments
IS Psychology A Science?
IS Psychology A Science?
Comparative Method I Comparative methods deal primarily with finding and/or eliminating necessary and/or sufficient conditions that produce a given outcome.
Research Design Shamindra Nath Sanyal 12/4/2018 SNS.
Inductive and Deductive Logic
Chapter 8 Inductive Reasoning.
Chapter 3 The Idea Of Causation on Social Research
Lecture # 2 MATHEMATICAL STATISTICS
Concise Guide to Critical Thinking
Presentation transcript:

Presentation: “Causal Conclusions”

Homework Analogies – pp Review: – Exercises (models for exam) Analogical Reasoning, e.g., ex. 8.4 Causal Argumentation, e.g., 8.3b Inductive Generalization, e.g., 8.2b No need to write out argument in argument form.

Identify the (i) sample, (ii) population, and (iii) target characteristic in this generalization. At a recent Star Wars convention, where more than 3,000 people participated, 50 people under 50 years of age were polled on which they liked better, Star Wars, or Lord of the Rings. 60% said they preferred Star Wars, 20% said they enjoyed both equally, and 20% said they preferred Lord of the Rings. From this survey, we can conclude that more than 50% of all science fiction fans prefer Star Wars to Lord of the Rings.

At a recent Star Wars convention, where more than 3,000 people participated, 50 people under 50 years of age were polled on which they liked better, Star Wars, or Lord of the Rings. 60% said they preferred Star Wars, 20% said they enjoyed both equally, and 20% said they preferred Lord of the Rings. From this survey, we can conclude that more than 50% of science fiction fans prefer Star Wars to Lord of the Rings. Strong or Weak? (1a) Sample size? (1b) Statistical representation of different strata? (2) Interviewer Bias? (1) Biased Sample?

CAUSAL STATEMENTS Concept of Causation

Causal Statements How Blackwater Sniper Fire Felled 3 Iraqi Guards Last Feb. 7, a sniper employed by Blackwater USA, the private security company, opened fire from the roof of the Iraqi Justice Ministry…. (Three guards were killed.) An Iraqi police report described the shootings as "an act of terrorism" and said Blackwater "caused the incident." The media network concluded that the guards were killed "without any provocation." Washington Post, 11/8/2007

Causal Statements How Blackwater Sniper Fire Felled 3 Iraqi Guards Last Feb. 7, a sniper employed by Blackwater USA, the private security company, opened fire from the roof of the Iraqi Justice Ministry…. (Three guards were killed.) An Iraqi police report described the shootings as "an act of terrorism" and said Blackwater "caused the incident." The media network concluded that the guards were killed "without any provocation." Washington Post, 11/8/2007 (1)Blackwater (A) caused the incident (2)The guards were killed (B) without provocation The guards suffered some effect, i.e., not the cause. Active Voice Passive Voice

THE MEANING OF “TO CAUSE SOMETHING” Causation

Meaning of Causation A.Causal Conditions – A Sufficient Condition – A Necessary Condition – Necessary and Sufficient Conditions B.Partial Causation – Contributing factors

A. Causal Conditions

The Sufficient Condition – The presence of this condition alone is capable of bringing about the effect – Sufficient but not necessary condition – Examples: The intense heat caused a third degree burn. If you run over a nail, your tire will burst.

A. Causal Conditions The Necessary Condition – The presence of this condition must exist for effect to occur at all – Necessary but not sufficient The presence of a necessary condition does not entail the causal event will take place – Examples: Without oxygen, the fuel cannot be ignited. If you want to do well on the exam, then you must study consistently.

Necessary AND Sufficient Conditions P Q The biconditional – “if and only if” (iff) – A certain condition, itself, is capable of bringing about the effect and – Another condition must exist for first condition to occur at all A. Causal Conditions

Examples from the text – (Boyle’s Law) The volume and pressure of a gas are inversely proportional If the volume of the gas decreases, then the pressure increases AND If the pressure of the gas increases, then the volume decreases. The volume of gas decreases if and only if gas pressure increases, and vice versa. Sufficient & Necessary

Causal Arguments 1.What are causal statements? 2.Causation: what does this mean? 3.Types of Causal Arguments 4.Critique of Causal Conclusions (Mill’s Methods) – strong causal conclusions – weak causal conclusions

Causal Arguments 4 Types – Causal statements expressed in premises 1.Causal Predictions 2.Causal Explanations 3.Causal Prescriptions – Otherwise 4.Causal Conclusions Each contains a causal generalization as premise Each contains a causal generalization as premise 8.3C, p

Causal Arguments Causal Conclusions – Premises Data expresses relation between events – Conclusion Establishes that relation is causal

MILL’S METHODS Causal Conclusions

Mill’s Methods 1.Method of: 1.Agreement 2.Difference Agreement & Difference 3.Concomitant Variation 4.Residue

Mill’s Method: Agreement Agreement (p. 71) – If more than one instance of some phenomenon has only one common antecedent, it is probable that this one antecedent is the cause or partial cause. Structural Features – the effect occurs in a number of cases – a variety of possible causal factors are present Only one antecedent present in each case “modified method of agreement” (p. 73) 1.A plurality of antecedent causal factors is present in each case (Partial causal factors)

Mill’s Method: Agreement Agreement (p. 71) – If two or more instances of a phenomena E have only one antecedent circumstance in common, then probably that antecedent is the cause or partial cause of E. E = effect “argument form” (p. 72) Structural Features – the effect occurs in a number of cases – In each case there are a variety of possible causal factors Only one antecedent causal factor is present in each case – “modified method of agreement” (p. 73) A plurality of antecedent causal factors is present in each case – Partial causal factors More instances of agreement the greater the likelihood that this factor is the cause of E. More instances of agreement the greater the likelihood that this factor is the cause of E.

Mill’s Method: Difference Difference (p. 73) – If phenomenon E occurs and then does not occur when the latter circumstance differs only in the absence of one antecedent, then that absent antecedent circumstance is probably the cause or partial cause of E. Structural Features – A minimum of two happenings E occurs E does not occur – In each case there are a variety of possible causal factors When E does not occur, one antecedent factor is removed

Mill’s Method: Difference Difference (p. 73) – If an instance of a phenomena E and an instance in which E does not occur differ only in the absence of one antecedent circumstance with the instance of E, then that antecedent circumstance is probably the cause or partial cause of E. See “argument form” on p. 73 Structural Features – A minimum of two happenings E occurs E does not occur – In each case there are a variety of possible causal factors When E does not occur, one antecedent factor is removed More instances difference the greater the likelihood that this factor is the cause of E. More instances difference the greater the likelihood that this factor is the cause of E.

2 of Mill’s Methods Agreement – Event (E) occurs whenever antecedent occurs Difference – Absence of event (E) coincides with absence of causal factor A causal conclusion is strong to the degree that it is supported by premises with evidence of one or more of Mill’s methods (p. 79)

Mill’s Methods: Example Six people eat dinner in a restaurant. Liz has soup, a hamburger, ice cream, french fries, and mixed vegetables. Tom has salad, soup, fish, mixed vegetables, and ice cream. Andy has salad, a hamburger, french fries, and ice cream. Sue has french fries, a hamburger, and salad. Meg has fish and mixed vegetables. Bill has french fries, a hamburger, and soup. Later, Liz, Tom, and Andy get sick from something they ate, but Sue, Meg, and Bill don’t. What food made the first three diners sick? – Method of Agreement and Difference

Mill’s Methods: Example Six people eat dinner in a restaurant. Liz has soup, a hamburger, ice cream, french fries, and mixed vegetables. Tom has salad, soup, fish, mixed vegetables, and ice cream. Andy has salad, a hamburger, french fries, and ice cream. Sue has french fries, a hamburger, and salad. Meg has fish and mixed vegetables. Bill has french fries, a hamburger, and soup. Later, Liz, Tom, and Andy get sick from something they ate, but Sue, Meg, and Bill don’t. What food made the first three diners sick? – Method of Agreement and Difference

Mill’s Methods: Example Six people eat dinner in a restaurant. Liz has soup, a hamburger, ice cream, french fries, and mixed vegetables. Tom has salad, soup, fish, mixed vegetables, and ice cream. Andy has salad, a hamburger, french fries, and ice cream. Sue has french fries, a hamburger, and salad. Meg has fish and mixed vegetables. Bill has french fries, a hamburger, and soup. Later, Liz, Tom, and Andy get sick from something they ate, but Sue, Meg, and Bill don’t. What food made the first three diners sick? – Method of Agreement and Difference

Agreement LizTomAndySueMegBill Fish* French Fries ** Hamburger** Ice Cream*** Mixed Vegetables ** Salad** Soup**

Agreement LizTomAndySueMegBill Fish* French Fries ** Hamburger** Ice Cream*** Mixed Vegetables ** Salad** Soup**

Difference LizTomAndySueMegBill Fish** French Fries **** Hamburger**** Ice Cream*** Mixed Vegetables *** Salad*** Soup***

Agreement and Difference LizTomAndySueMegBill Fish** French Fries **** Hamburger**** Ice Cream*** Mixed Vegetables *** Salad*** Soup***

Mill's Method: Concomitant Variation Concomitant Variation – A first discovery: the volume knob – If variations in phenomenon E coincide with variations in phenomenon P, then it is probable that E and P are causally related. (p. 75)

Mill's Method: Concomitant Variation Types of Variance Simultaneous (Where antecedent and consequent remains unclear) versus Sequential (Where definite gap exists between antecedent and consequent)

Mill's Method: Concomitant Variation In attempting to diagnose Mrs. Thompson’s high blood pressure, a cardiologist noticed a correlation between fluctuations in blood pressure and certain brain waves. As the blood pressure increased, so did the intensity of the brain waves, and as the blood pressure decreased, the intensity of the brain waves decreased. The cardiologist concluded that the two conditions were causally related.

Mill's Method: Concomitant Variation In attempting to diagnose Mrs. Thompson’s high blood pressure, a cardiologist noticed a correlation between fluctuations in blood pressure and certain brain waves. As the blood pressure increased, so did the intensity of the brain waves, and as the blood pressure decreased, the intensity of the brain waves decreased. The cardiologist concluded that the two conditions were causally related.

Mill’s Methods: Residue Characteristic features 1.Deals with complex phenomena 2.Established knowledge of some causal factors a)in measured quantities Subtract from any phenomenon such part as is known by previous inductions to be the effect of certain antecedents, and the residue (i.e., remaining parts) of the phenomenon is the effect of the remaining antecedents

Mill’s Method: Residue After realizing a loss of $100,000 a department store’s chief accountant could suggest only three causes: an excessive number of clerks, increases in utility rates, and damage to merchandise caused by a flood. These expenses were estimated at $25,000, $30,000 and $10,000 respectively. Since no other ordinary sources could be found, the accountant attributed the remaining $35,000 to shoplifting.

Mill's Method: Residue After realizing a loss of $100,000 a department store’s chief accountant could suggest only three causes: an excessive number of clerks, increases in utility rates, and damage to merchandise caused by a flood. These expenses were estimated at $25,000, $30,000 and $10,000 respectively. Since no other ordinary sources could be found, the accountant attributed the remaining $35,000 to shoplifting.

Mill’s Methods 1.Agreement 2.Difference – (Agreement & Difference) 3.Concomitant Variation 4.Residue

Mill’s Methods 1.Agreement 2.Difference – (Agreement & Difference) 3.Concomitant Variation 4.Residue Typically establishes sufficient conditions Establishes variable relations Establishes partial causation A causal conclusion is strong to the degree that it is supported by premises with evidence of one or more of Mill’s methods (p. 79)

Homework Analogies – pp Review: – Exercises (models for exam) Analogical Reasoning, e.g., ex. 8.4 Causal Argumentation, e.g., 8.3b Inductive Generalization, e.g., 8.2b