lecture 3 goals tools and trade offs

• KKV canonical book with qual tradition w quan methods.

  • bcs is the same

    • how the anlaysis of one or a few cases contributed to overarchiving goals of positivist researcg (shared w quan research)

    • specifically descriptive and casual infrence and concept formation (reconstruction)

  • we cannot achieve everuthign with quan tools. Qual tools achive specific goals that quan tools do not. Thus a key part of research design is understanding trade off

• key terms:

  • overarching goals, intermediate goals , tools

  • set relational causation

overaching goals

• embedded in specific “methodologies”, per schaffer

• shared by positivist researchers: descriptive and casual inferences

• important for positivist qualitative researchers: “refining theory”, which can also contribute to the overarching goals of descriptive and casual inference

intermediate goals

• “immediate goals” per schaffer

• diff traditions choose diff paths to pursue these overarching goals

• intermediate goals present trade offs “ the pursuit o one particular objective may make it hard to achieve another”. in other words, i cannot achieve everything at the same time

tools

• “methods per schaffer

• practices and procedures for achieving intermediate goals

• there are also trade offs at the level of tools. no tool can achieve everything

• moreover, while a given tools may achieve a particular intermeidate goal, it may make it difficult to achieve another one

what is research design?

research design is about making choices among potentially incompatable goals or to evaluate these trade offs in light of alternative goals.

advice from KKV and critics 1) avoid “no variance” designs

• 1) avoid “no variance” designs: Do not do on single case study. You must focus on something that varies

  • problem 1 : this advice often gets in the way of doing relevant research. Why? You are limiting yourself to questions that can be addressed with stat data

  • problem 2 : some research practices can improve inference but not necessarily innovation

    • it’s not that by using quan methods you cannot innovate. its abt practices, sometimes research questions come from methods, when it should be the other way around

    • the horse behind the car: making questions that can be answered with cross national regression to with experimental design ,and skewing relevant questions that do not fit these methods

• qualitative practices tend to be conducted to innovative questions and areas and research and areas of research

  • practice: how do you approach a research (analysis of effect of causes)

  • method: tools (LRA, comparative case studies)

    • for instance, identifying and studying deviant cases

    • KKV assumed that creativity and theoretical innovation are only the product of personal “genius” or “brilliance’” they are not

      • there is something dishonest abt this perspective because a lot of innovation in quan political science and in econ come from qual research

    • my suggestion, let your question guide your method choice. and loook for questions that are puzzling

KKV advice and critics 2) conceptualization and measurement

2) conceptualization and measurement: focus research on concepts that maximize measurement validity and reliability, and to avoid organizing data with typologies

concept: political legitimacy

operational: what indicators can we use to tap into our def

measurement: what data sources do we have

validity: how a measurement reflects a concept.. how good is my indicator . if we do it several time do we get the same results

• problem 1: may turn into invitation to ignore questions involving important concepts

  • again the methods determing the research agendas, and not the other way around

  • there are concepts that are very important normatively and theoretically and yet are quite difficult to measure. For example civil society political culture, legitimacy, hegemony

• prob 2: typologies and more generally research on concept formation, can make important contributions to casual inference, for instance by identifying casual heterogeneity

  • good ex in session 7

advice KKV and critics 3) selection bias

• 3) selection bias: KKV advice is to avoid selecting a set of cases that does not represent the population (which is achieved by a large enough sample chosen at random)

  • w large sample and random selection

  • problem 1: yes , a small number of cases selected in a purposive way (not random) will not be representative of a population. but we learned last week there are other benefits that cannot be achieved w a large sample of cases. representatives is not the only possible (immediate) research goal

    • an important benefit achieved through qual methods is rigorous within case analysis. selection bias is not a concern since we have chosen a case that matters for a purpose other than representativeness

    • other benefits

      • hypothesis formation of theory refinement (w sold empirical resarch)

      • concept formation through a few cases

      • analyzing cases athat are actually comparable, without stretching their comparability through a large sample (eg countries within a historical region or subnational cases

      • comparing cases that are not obviously cases (changing the unit of analysis, like historical regions across countries

  • problem 2: a representative sample depends on how one defines the universe of population of cases (good for testing causal relation but not theorizing)

    • for example you make assumptions that are debatable

      • countries are perfectly comparable to each other

      • diff periods are comparable

advice KKV and critics 4)models of casualtion

• KKV advise against using “deterministic” (set relational) notions of causation on the grounds that the world is probabilistic

  • problem 1: what abt hypothesis and theories formulated in terms of set relations- how are we to evaluate them?

    • these theories are often formulated, for ex in the contect of comparing historical processes

set relational causation

the correct terminology is

• correlational vs set relational causation (probabilistic

• finish slide

set relational causation example

democratic peace hypothesis (one version of it): democracies do not got to war with other democracies.

what is a Dyad?: pair of countries

• X is sufficient condition of Y

  • if x then for sure y

  • x—>y

  • y = big circle x is little circle in y

  • asymmetric causation

• x is a necessary condition for y

  • x ← y

  • x = is big circle y is little circle in x

• x id a necessary and sufficient causation of y

  • x ← → y

  • equifinality: more than one path to the same outcome

    • either x1 or x2 is individually sufficient for y

    • x1 or x2 —> y

  • conjunctural causation: two conditions produce the outcome but only if they are together

    • x1 and x2 are togeather sufficeint for y

    • x1 and x2 —> y

set relational equifinality

more than one path to the same outcome

• either x1 or x2 is individually sufficient for y

• x1 or x2 —> y

set relational conjunctural causation:

• two conditions produce the outcome but only if they are together

  • x1 and x2 are together sufficient for y

  • x1 and x2 —> y

set relational INUS conditions

when there is >1 casual paths to the same outcome.

• each path is a conjunctural cause

• the conditions in each conjunctural case are insufficient but necessary for the conjuncture (IN)

  • individually its insufficient but together its necessary

• these conjunctures are unnecessary but sufficient to the outcome (us)

• similar to equifinality but had conjunctions

• INUS conditions are common in comparative historical analysis (comparison of historical processes and sequences).

what us a case study?

• distinguish from historical studies

  • historians embrace the richness of reality

  • social scientists focus on aspects of reality that relate to a theoretically discussion (or policy discussion, as there is scholarly research on policy)

• a case is often an instance fo something else - “what is this a case of”

  • instance of a class of events, inside which we analyze in detain certain aspects to develop to test historical explanations that may be gernalizable to other vents

  • not necessarily

• case vs observation

  • one or dew cases… but many observations: pieces of data within the case( like in the case study of floidas panhandle)

  • case studies are not “narrative” studies : we can use many types of sata within the case including stats.. member that qual method are not abt “wrods” (vs. numbers)

typology by objectives of research

• ideographic: describe, explain, interpret, and or understand a sinfle case as an end in itself rather than as a vehicle for developing broader theooretical generalization. like a historican case study

• inductive: not structured by theoretical framwork

• theory guided : explicitly

unlike ideographic case studies others want to generalize beyond the data

• hypothesis generating: purposing or refining a theory, for instance , through the specification of casual mechanisms

• ex liphart the politics of accommodation

  • contradicts the conventional wisdom that liberal democracy does not work in context of deep societal divisions, at decolonialization in africa and asia (while many democratic experiments failed)

hypothesis testing

sone hypotheiss can cve tested through on eor few cases using process tracing, strictured comparisons crucial cases etc

plausibility probe

exploratory case study highlighting elements that will be useful for … finish slide

research design : case selection criteria

• dv= phenomenon i want to explain

• iv= explanatory factor

• causes of effects kind of questions

purposeful sample: studies with small number of cases are always nonrandom. we select with a purpose in mind, they are not random (statistical).

for example, strategies for exploration

• extreme: case shows clearly the values of interests in the iv or dv

• variation: cases tha illustrate/show relevant variation in iv or dv

why do we need a selection criteria or strategy

• selection bias risk

  • without a proper sense of scope (what kind of case is this), it might over- or under estimate theoretical claims or casual relationships

  • always useful to have a comparative design or even add “shadow cases”

• when is it not a problem

  • the broader conversarion is clear

  • falsify necessary causes (outcome present without iv)

  • falsify sufficient cases (iv present but outcome absent)

• within case analysis: mechanisms

crucial case deisgn (single case)

• hardest and easiest cases for a hypothesis or theory

  • most likely: if theory does not work here, not likely to be relevant

    • a case most likely to support the theory

  • least likely case: if theory works here, it is likely relevant

    • a case least likely to support a theory

      • A researcher wants to test the following hypothesis: Democratic institutions take root in developing countries when they receive robust diplomatic backing and material aid from Western countries and organizations. For this purpose, the researcher conducts a case study of a particularly difficult place characterized by political violence, high poverty rates, and ethnic divisions, such as Iraq, which is strongly supported by the West.

  • example: development —> democracy

    • brazil most likely case

    • mexico least likley

deviant case design (single case)

• a case that deviates from the model

• case study asks: what is it an anomaly (is it really)

  • example: india: relatively poor country that democratized at independence, despite economic underdevelopment

• refine the thoery

• case study asks: under what scope conditions does the theory work

  • singapore: rich country that has never (truly) democratized

comparative designs

• MSSD (mills method of diff) (same iv and diff dv)

• MDSD (miss method of agreement ) (diff iv and same dv)

  • A researcher is interested in studying why social revolutions happen (DV). She studies three countries (France, Russia, and China) that differ in their political institutions, histories, geographies, and cultures, and yet experienced similar revolutions.

• sources of leverage: how does that help me w causality

example MSSD

Peru and Chile and similar initial conditions

• colonial heritage

• economic dev

• position in International division of labour (minerals)

• exposed to regional geopolitical tensions (wars and invasions)

but diff outcomes

• ineffective peru// effective taxation system (chile)

explanation (necessary condition)

• hierarchical (Peru)// non hierarchical (Chile) labour relations (inherited from colonial times

MDSD example

• compares France, China and Russia , who are diff in initial conditions

  • these are alternative explanations

• but similar outcomes: radical transformations of state and society in relatively short period

• explanation (INUS condition)

  • INUS conditions is when equifinality (diff explanatory paths )based on combination of diff variables

  • INUS conditions is a subcase of equifinality: theres conjuctural conditions(combinations of variable)

    • inter state rivalry—> liberal reforms —> peasant rebellion —> collapse of coercive apparatus —> etc

potential issues w MSSD and MDSD

• Comparability

  • Cases do not need to be exactly similar (as if in an experimental comparison), but they must be ‘reasonably’ comparable. The author has the burden of showing that the cases are indeed comparable (Most Similar) or convergent(Most Different)in theoretically relevant ways.

• Complex causation

  • When used for complex phenomena(e.g., macro-political processes), allow for“conjunctural causation”and “equifinality”....Here is where models of set-relational causation come in handy.

    • we talked abt INUS and not only equifiniality

• Researchers are using more and more within-case analysis (process tracing) in combination with case comparisons.