● To distinguish between rival plausible
hypotheses. [Campbell 1994]
● To attack proposed scientific theories. [Popper
● Controlled experiments on population samples.
● Archival Analysis
● Case Study
Applicability of Tools
[after Yin 1994]
Tool Question Control? Past
Experiment How, Why Yes Present
Survey Where, How No Present
Archival (same) No Both
History How, Why No Past
Case Study How, Why No Present
vs. Rival Theories
● Controlled experiments: requires theory to know
what to control.
● Randomized experiment: Renders unstated rival
theories implausible by statistics.
● Case study: Requires explicit theories in order to
What is a Case Study?
● 'Case Study' is ambiguous.
– Teaching case study: B-school.
– Record keeping case study: medicine, law.
– Research case study: many social sciences.
Research Case Study
● Purpose: distinguish between rival plausible
– Direct observation
– Participant observation
● “1. A case study is an empirical inquiry that
● “investigates a contemporary phenomenon within
its real-life context, especially when
● “the boundaries between phenomenon and
context are not clearly evident.”
● “2. The case study inquiry
● “copes with the technically distinctive situation in
which there will be many more variables of
interest than data points, and as one results
● “relies on multiple sources of evidence, with data
needing to converge in a triangulating fashion,
and as another results
● “benefits from the prior development of
theoretical propositions to guide data collection
Parts of good case study – Yin
● Question: Why did X happen?
● Propositions: X happened because of A, B, and C.
● Unit of analysis: person, team, company, etc.
● Logic linking data to propositions: What effects
do data points D, E, and F have on X?
● Criteria for interpreting findings: How do you
Parts of a good case study – McGee
● [Copy Yin fig 2.3]
● A case study is not a data point. Saying “you can't
generalize from a single case” misses the point.
● A single case study is analogous to a single
experiment. Each either supports or refutes a
Types of case studies
(holistic) Type 1 Type 3
(embedded) Type 2 Type 4