Research Methods Political Science is about the scientific study of phenomena Political scientists develop and test theories Study of politics based on theory observation A theory is a tentative conjecture about the causes of some phenomena of interest Once stated it can be restated into a testable hypothesis A hypothesis is a theory based statement but it is about what we would expect to observe if our theory was incorrect It s an expectation about what was observed Must be falsifiable More specifically it s a statement derived from the theory that describes the expected co variation between x and y Correlation or For every hypothesis there is a null hypothesis Statistical testing relies on the rejection of the null In other words if we reject the null our hypothesis is not yet wrong BUT our theory can still never be truly proven To test hypotheses we must measure our concepts which allows us to examine data and co variation First we need an abstract definition of our concept Second we produce and operational definition o A set of instructions that describe how to measure the value of that concept Operationalization Validity Does it match the concept well Reliability do we get the same value when we repeat the measurement Error in operationalization can be broken into two parts Random Systematic tendency to assign values that are too high low equal likelihood of assigning too high low values A Causal theory explains our phenomenon of interest Answers the questions What causes something why Provides a story about how and why change in the value of one concept influence the values of another concept To construct a theory there are two ways to go about it Deduction Induction was observed o Deduction theory first then empirical testing o Induction observation first then theory construction to explain what Theory must specify type of causal relationship Direct X Y Indirect X Z Y Spurious Z X and Z Y Endogeneity simply put is reverse causation Causal Theory Hypothesis Empirical Test Evaluation of hypothesis Evaluation of Causal Theory Scientific Knowledge Empirical simply means based on our observations of the real world Once a theory has become established as part of scientific knowledge in a field of study researchers build upon the foundation that this theory provides Through these cycles of accumulating knowledge and shared assumptions we refer to this theory that been so built upon as a paradigm Usually when a paradigm is widely accepted by researchers they pose increasingly technical questions due to the work beforehand This is known as normal science A key element in the production of theories in political science is variables and the causal relationships between them Variable Label description of what variable is Variable Value denominations in which it occurs Example Individual s age Label Age Value Years Days etc The causal explanation behind a theory is the question Why do you think that this independent variable is causally related to this dependent variable Make your theories causal Don t let data alone drive your theories Avoid normative statements Consider only empirical evidence Pursue both generality Analyze the real world not counterfactuals Think in terms of concepts not proper nouns Propose testable causal relationships Scientific Method 1 2 Identify a question or puzzle Identify the dependent variable Propose a causal explanation theory 3 Identify the independent variable State the hypothesis Identify the null hypothesis 4 5 Operationalize the concepts collect data 6 Test the hypothesis 7 Re evaluate the theory given the results How do we know Epistemology Daily experience i e toddler learning to walk Tradition i e farming techniques from our ancestors Authority i e your professor Mutual Agreement communication Observation o Verifiable and repeatable o Falsification o Probability Deterministic vs Probabilistic Causation Deterministic Causation the associated cause is always present no other variables influence the relationship between cause and effect the link between an independent variable that brings about the occurrence of the dependent variable every time Cause X is always present when outcome Y occurs o Contains words like always o Ex Law of Gravity o All republicans have higher incomes deterministic Probabilistic Causation designates a group of philosophical theories that aim to characterize the relationship between cause and effect using the tools of probability theory The central idea behind these theories is that causes raise the probabilities of their effects all else being equal Occurs with some likelihood when cause is present o Contains word like probably and likely o People with higher incomes are more likely to be registered republicans probabilistic Inference Best guess about something unknown given known information Causal Inference unknown causal relation between two or more variables o Cannot be observed Why Inaccurate observations Tendency to overgeneralize Illogical reasoning o To draw a valid causal inference we require both logical and empirical support o Valid CI requires o All are uncertain Theory that expects X to effect Y and Evidence of correlation between X and Y Descriptive Inference unknown fact about a single variable o Good description offers us a profile of interest including Unit of interest individuals states countries Variation Both quantitative and qualitative judgment
View Full Document
Unlocking...