Lecture 2: Research Logic and Research Design Flashcards
Normative research
- Questions that inquire what ought to be
- deals with ethics, values, and value judgements
Aim= prescriptive - Require the application of philosophy rather than of data
Positive research
- Questions that inquire what is
- Deals with empirical phenomena + theoretical concepts plus the link between them
- Capable of being researched through data collection
Theoretical research
- Theory elaboration, conceptualization
- Analytical (truth = based on logical deductive reasoning)
Empirical research
- Theory generation
Testing + application,
Conceptualization - Synthetic
truth result from a confrontation between theory + empirical content
Descriptive research
kind of empirical research type
What is going on?
- Collection of relevant facts that can be used as evidence in subsequent theory building or conceptualization
- good descriptive research can lead to a ‘‘light bulb’ moment
Research objective: thick description, or conceptualization
Explanatory research
Why or How is it going on?
- Can focus on causes of events (Y), causal effects (X) or causal mechanism (X-Y)
- Why-questions: causal effects
- How-questions: causal mechanism
Research objective: Theory building or theory testing
What is research design?
’’ a research design is** a logical plan for getting from here to there**, where here may be definited as the initial set of questions to be answered, and there is some set of conclusions (answers) about these questions)- Yin
- Logic plan ‘’ a research design deals with a logical problem, not logistical’
Not just about how you do the research, but also why and what the purpose of doing this is.
- Logic plan ‘’ a research design deals with a logical problem, not logistical’
- How are you going to conduct the research?
- Methods need to be consistent and logical, not logistical
Units of variation
= units of analysis (count of N/ number of cases)
X- centered
Focuses on a cause
* has it a specific effect on a specific outcome
* gauging the contribution of X in explaining part of variation in Y
Case study
Empirical analysis of small sample of cases
Y- centered
Focuses on outcome.
* discern the relevant causes
* Explaining te variation in Y as best as you can (backward looking)
Mechanism-centered
Focuses on tracing a causal mechanism/ causal process
* Uncovering the sequence of intervening factors that link an X to an Y
What is a case?
Bounded empirical phenomenon that is an instance of population of similar empirical phenomena
* boundaries: spatial/ temporal/ substantive
* Causal homogeneity
Causal effects and mechanisms are expected to hold true for other cases in population
Why select cases purposefully
- avoid selection bias + faulty generalizations
- increases external validity
- Random sampling is not usually an option due to the few cases or theoretical concerns.
- Selecting cases carefully avoids false conclusions
Characteristics Case study
- Generalizability: causal effects + mechanisms are expected to hold true for other cases in population
- both qualitative as quantitative techniques can be used
Population
Universe of cases, class of events, studied +unstudied cases
Sample
Studied cases
Analytical level
- Macro level
- meso level
- micro level
Macro-level
Societies, economies, states
Meso level
Groups, territorial subunits
Micro level
Individuals
Level of analysis
- Cross-case level
- Within-case level
Cross-case level
Causal effects
Within-case level
Causal mechanisms
Types of observations
- Data set observations
- Causal process observations
Causation
A type of co-variation where one phenomenon contributes to or produces another
Criteria for causal inference
- Temporal sequence ( X–> Y)
- Proximity ( in time and space)
- Constant coexistence (of X and Y)
- Necessary connection (between X and Y)
views towards causation
- Probabilisitc view
- Deterministic view
Probalistic view on causation
- When values of an independent variable increase or decrease –> this usually results in values of dependent variable increasing or decreasing
- Cause as a pobability raiser
= X sometimes effects Y
Deterministic view on causation
when the values of an independent variable increase or decrease, this always results in the values of the dependent variable increasing or decreasing
explanatory factors are (potentially) necessary and/or sufficient conditions for an outcome
= X always effects Y
What is a theory?
A theory consists of..
- A prime hypothesis
- One or more explanatory hypotheses
= argument - one or more antecedent conditions
Theories provide an explanation as to how A causes B and they can be written in the form of an arrow diagram (theoretical model)
A theory consists of
- a prime hypothesis A–> B
- One or more explanatory hypotheses A–> q, Q–>r, r–> B = your argument
- one or more antecedent conditions
Predictive research
Predictions about future through identifying future patterns. Oriented towards elections. Not focused on in on the course
Choosing a Research design
- make decisions based on theory out there.
- In explanatory research: you have to think about the variation you want to explain.
- Level of analysis
*The type of data you have to collect to answer your research question
- Probabilistic or deterministic causational perspective
- choice of methods
Theory testing
- Start with describing/ analysing theory.
- Hypotheses
- Measurement/ sampling etc
- Data collection
- Data analysis
- Either data analysis makes it so there are implications for hypothesis; so either confirm/ reject theory. When you reject; a new theory is needed.
Deductive –> when theory-testing
- Describing/analyzing theory.
- Formulating hypotheses, measurement, and data collection.
- Data analysis leading to hypothesis confirmation or rejection.
Theory building
When there is not much or no theory to build on.
1. Start with data collection
2. Data analysis
3. Implications for new hypothesis/ theory
4. When implications for hypothesis, it results in a theory
5. When new theory is needed, a new hypothesis is needed and then you go through the process of measurement, data collection, data analysis, implications hypothesis again, and making hypothesis in the end
Types of Research designs
- Single case –> short time + space ( one case in time)
- Comparative case study–> different case studies at a specific time point
- Periodisation study –> one case across different points in time
Brainstorm qualitative research questions?
- List political science or international relations terms
- HIghlight complex processes, beliefs, opinions or motivations
- Create research questions by associating themes, often starting with ‘‘how’’ why?’
