GS/PPAL 6200 3.00 Section N Research Methods and Information

GS/PPAL 6200 3.00
Research Methods and Information
Systems
March 14-15, 2017
Professor Brenda Spotton Visano
Office: 130 McLaughlin
Voice Mail: (416) 736-2100 ext. 20470
E-mail: [email protected]
Agenda
• Methods of Knowing
• Mill’s methods of knowing
• Articles for review: What can small samples
reveal?
–
Lieberson, Stanley (1991) Small N’s and big conclusions: An examination of the reasoning in
comparative studies based on a small number of cases. Social Forces 70(Dec.): 307-320.
http://www.heinonline.org.ezproxy.library.yorku.ca/HOL/Page?handle=hein.journals/josf70&div=23
&collection=journals&set_as_cursor=0&men_tab=srchresults&terms=Leiberson,%20Stanley&type=
matchall
–
Savolainen, Jukka (1994) The rationality of drawing big conclusions based on small samples: In
defense of Mill’s methods. Social Forces 72(June): 1217-1224
http://www.heinonline.org.ezproxy.library.yorku.ca/HOL/Page?handle=hein.journals/josf72&id=123
3&collection=journals&index=
• Sampling and Measurement – precursor to causal
inference
Sample Questions to which we might
seek an Answer
Physical Phenomenon
• How do we know ice is cold?
• How could we test a hypothesis that states “all
things frozen are cold”?
Social Phenomenon
• How could we test a hypothesis that states
“drunk driving causes automobile accidents”?
Causality
• David Hume (1711-1776) A Treatise of Human
Nature, 1738; Hume’s Causality:
• Precedence (X precedes Y in time)
• Contiguity (X and Y are contiguous in time and space)
• Constant Conjunction (X and Y always co-occur)
• John Stuart Mill (1806-1873), A System of Logic, 1843
– Methods of (1) Agreement, (2) Difference, (3) Joint
Agreement and Difference, (4) Residue, and (5)
Concomitant Variations
Method of Direct Agreement
–
–
–
–
Y occurs together with X1, X2
Y occurs together with X1, X3, X4
Therefore Y is the cause, or the effect, of X1
If Y is the effect of X1, then Y is the dependent
variable, X1 is the independent variable, and by Mill’s
method of agreement X1 “causes” Y
Method of Difference
– Y occurs together with X1, X2, X3, X4
– Y does not occur together with X2, X3, X4
– Therefore Y is the cause, or the effect, or a part of
the cause of X1.
• Example of test for “drunk driving causes
automobile accidents”?
Method of Agreement
Accident (Y)
Drunk
driving (X1)
Other car
(X2)
Driver
speeding
(X3)
Driver runs a
red light (X4)
Yes
Yes
Yes
No
No
Yes
Yes
No
Yes
Yes
Method of Difference
Assumptions and Limitations
• Assumes:
– a unique cause
– the causal variable is included in the set of
possibilities investigated
– invariance in the patterns investigated
– correlation implies causation
• Limitations: see Lieberson (1991) for argument
opposing the use of Mill’s methods in social
research and Savolainen (1994) for a defense of it