In Ada W. Finifter, ed. (1993) Political Science: ‘The State of the Discipline Il.
5 Washington, D.C.: American Political Science Association,
a ES ES
The Comparative Method
David Collier
Comparison is «Fundamental tool of analysis. Tt
sharpens our power of description, and plays « ceatral
role ia concept formation by bringing ialo focus
suggestive similarities and contrasts among cases.
Coniparison is routinely used in testing hypotheses, and it
can contribute to the inductive discovery of new
hypotheses and to theory-bulding.
‘The forms of comparison employed in the
discipline of political science vary widely and include
those contained in statistical analysis, experimental
research, aad historical stdies, At the sxme time, the
label “comparative method” has «standard meaning
within the discipline and in the socal ecioaces more
broadly: it efers to the methodological issues that arise
in the systematic analysis of small number of cases, or
‘small N."! This chaptr examizes altemative
perspectives on the comparative method that have
emerged over roughly te past two decades. Although
the primary foeus is on discussions located in the fields of
conparative politics aad intematoaal studies, the
application of the comparative method is by no means
restricted to those fields.
‘The decision to analyze only «few casos is
strongly influenced by the types of political phenomena
uncer study and how they are conceptualized. Topics for
which it is productive to examine relatively Few cases
include revolutions, particular types of national political
regimes (eg, post-communist regimes), or particular
forme of urtan political systems. This focus on a small
number of cases is adopted because thete exis relatively
fo instances of the phenomenon under consideration that
exhibit the attributes of interes o the analyst.
‘Altematively, some analysis believe that politcal
Phenomena in goneral are best understood through the
‘careful examination ofa small number of cases. In the
field of comparative and intersationl sudies, the practice
of focusing on few cases has achieved greater legitimacy
{n event years in conjunction with the rise ofthe echo!
of "comparative historial analysis," in which small
numbers of countries are studied over long petiods. This
close scrutiny of eech couatry limits the number of
national cases a scholar can consider
‘Choosing to study few cases routinely poses
problem of having more rival explanations to assess than
‘casce to observe, or the quandary of ‘many variables,
‘small N* (Lijphart 1971, 686). Elementary statistics
teaches us that as the number of explanatory factors
approaches the number of cases, the eapacity to
adjudicate amoug the explanations through statistical
‘comparizon repidly diminishes. This problem has stime-
lated much discussion of how most productively to
saalyze a small N.
‘The late 1960s and early 1970s saw a boom in
waiting on comparative method (c.g., Merritt and Rokkan
1966; Kalleberg 1966; Verba 1967; Smelser 1968;
Lasswell 1968; Praeworski and Teune 1970; Sartori
1970; Merritt 1970; Etzioni and Dubow 1970; Lijphart
1971; Vallier 1971: Zelditch 1971; Ammer and Grimshaw
1973). ‘This literature established a set of norms and
practices for emall-N research, proposed alternative
strategies for conducting such analyses, and crested a
base ling of understanding that has played an important
role in the ongoing practice of small-N studies. This
chapter assesses the issues of comparative method that
have been debated in the intervening years and considers:
their implications for ongoing research. The point of
departure ig Arced Lijphart's (1971) article *Comparative
Polities and Comparative Method.” Among the studies
published in tht period, Lijphart's piece stands out for its
imaginative synthesis of basic issues of comparison and
of the relation between comparative method and other
‘branches of methodology? It therefore provides a
helpful framework for examining, and building upon,
new developments in the field.
‘Avcentral theme that emerges in the discussion
below is that refinements in methods of small-N analysis
hheve evbetantially broadened the range of techniques:
available to comparative researchers. The most fruitful
approach is eclectic, one in which scholars are willing,
and able to draw upon these diverse techniques.105 ‘The Comparative Method
Synopsis of Lijphart
LLijpbart defines the comparative method as the
analysis of a small number of cases, entailing at least two
‘bservations, yet too few to permit the application of
conventional statistical analysis. A central goal of bis
article is to assess the comparative method in relation to
three other methods~experimental, statistical, and case~
study-aad to evaluate thaco different approaches by two
criteria: 1) how well they achieve the goal of testing
thoory through adjudicating among rival explanations, and
2) how difficult itis to acquice the data needed to employ
each method (see Figure 1).
‘Tho experimental method has the marit of
providing strong criteria for eliminating rival explanations
through experimental coatrel, but unfortunately itis
impossible to generate appropriate experimental data for
most topics relevant to political analysis. The statistical
method bas the merit of ascassing rival explanations
through the weaker but still valuable procedure of
statistical control, but itis often not feasible to collect a
sufficiently lerge st of relisble data to do this form of
anal
‘The cace-ttudy method bas the merit of
providing a framework in which a scholar with modest
time and resources can generato what may potentially be
useful data on a particular case. Unfortunately,
opportunities for systematically testing hypotheses are far
sore limited than with the other mathods. Yet Lijphart
(pp. 691-93) insists that case studies do make &
‘contribution to tasting hypothaces and building theory,
and he offers a suggestive typology of case studies based
‘on the nature of this contribution. He distinguishes
among asheoretical case studies; interpretative case
studies (that self-consciously use a theory to illuminate a
particular case); hypothesis-generating case studies;
theory-confirming case studies; theory-infirming case
studies (that, although they canaot by themselves
disconfirma theory, can raise doubts about it); and
deviant case analyses (that seek to elaborste and refine
ivory through 2 clove examination of a case that departs
from the predictions of an established theory). Lijphart
emphasizes that "certain types of case studies can even be
considered implicit parte of the comparative method” (9.
(691), and to the extent thatthe assessment of hypotheses
does occur in seme ease studies, it is often because the
case studies are placed in an implicit or explicit
comparative framework. Yet even within this
framework, he emphasizes that findings from a single
case should not be given much weight in the evaluation of
hypotheses and theory (p. 691).
‘The comperstive method, as defined by Lijphat,
thas an intermediate satus in terms of both bis criteria. It
provides a weaker basis than the experimental or
statistical method for evaluating hypotheses, due tothe
eck of experimental control and the prcblem of many
variables, small N. Yet it does offer x stionger bass for
evaluating hypotheses than do case studies. Despite the
‘constraint of addressing more Variables than cases, the
comparative method allows systematic comparison thet, if
appropriately utilized, can contribute to adjudicating
among rival explanations.
Although the data requirements of the
comparative method may be much greater thaa for case
studies, Lijphart argues that they are less demanding than
for experimental or statistical research. He thorofore
‘views the comparative method as most appropriae in
research bused on modest resources, and he suggests that
studies using the comparative method might often serve
‘as a first step toward Statiscical analysis.
fa all possible one should generally use the
statstial (or perhaps even the ex
method instzal of te wesker comparative
‘method. But of, given the ineviuble
scarey of ine, energy, and Gnascial
resources, the intensive comparative analysis
fof s few cases may be mere promising then
‘a more supertiia satistical analysis of
‘many cases, In uch sition, the most
fruiful approach would be w regard the
‘compartive analysis es the fist sage o
research, i whieh hypetbeses are carfully
formulated, and the statistical analysis asthe
second stage, in which diese hypotheses are
tested in a5 large a sample as possible
971, 685)
Lijpbart also proposes solutions to both sides of
the problem of many variables, small N (1971, 686 1).
‘With regard to the small number of cases, even if
rescershers stop short of a statistical study, they can
‘nonetheless try to increase the number of cases used in
assessing hypotheses. With regard to the large number of
variables, he suggests two approaches. First, analysts
can focus on “comparable cases,” that is, on cases that
') are matched oa miny variables that are not central t0
the study, thus in effect “controlling” for these variables;
and b) differ in terms of the key variables that are the
focus of analysis, therchy allowing a more adequate
assessment of their influence. Hence, the selection of
‘cases acts as a partcl substitute for statistical or
experimental control. Second, analysts can reduce the
number of variables either by combining variables in 2
single scale or through theoretical parsimony, that is,
through developing @ theory that focuses on a smaller
‘number of explanatory factors.
‘Thus, Lijpbart provides a compact formulation
of the relationship between the comparative method and‘Figure 1. Situating the Comparstive Method as of 1971: Lijphart’s Scheme
Case Study Method
Comparative Method
Exparimantal Mathod
| Mont ]
| ert: Parmtsines |
Bewannwons |
|
|
ed reseureas.
Inherent Protiem:
Contributes loss te
building theory tnan
studios wth mare
| cases
| Types of case stu
| dies
1. Athearetic!
| 2.tmerpretve
3. Hypotnesis-
generating
Theaey-contrming
Thearyinteming
(8, case states
that weaken
teory marginaty)
Deviant casa studios
[Detined as: Syste
[patie anes of smal
‘eumber of e080
| CsmalbN" analysis)
Mert: “Given inevi
fla scarcity of tie,
| energy. and financial
rasoutees, th itor
‘sve anaiyasof afew
‘casos may De more
| promeing han tho
‘supericialstalsical
analysis of many
ceases" (Uhr.
588)
| Innerent ProDtem:
Weak capacity 0 sort
| cut rival explanations,
specifica the proo-
fom el "any vari
‘ables, few cases
Potential Solutions
4, Reduce number of
vansbies
Combine var-
bi
». Employ more par-
simorious theory
Merit: Eiminaies rival
‘xplanauons trough
experimental conta!
Inherent Problem:
Experimental eonvolis
impossible for many or
‘most topics of
retevance ta fold of
‘comparative polities
‘Statistical Metnod
Marit: Assasses rival
explaraions throvah
statistical conto!
Inherent Protiem:
Diticut i-cllect acs.
quale iniormaton in a
eufficient numberof
eases, que to amitec
lime and roeources
Collioe
107