Midterm 1 Flashcards
What are the five steps of the scientific method?
- Observe some aspect of the universe (in this case, something
related to politics) - Generate a hypothesis about some causal relationship: a
tentative one that explains what you observed - Use the hypothesis to make predictions
- Test those predictions by experiments or further observation
or data collection - Repeat: replicate, question, and redesign
Inductive Reasoning
reasoning from the data
Deductive Reasoning
reasoning from general principles
Systematic:
methodical, organized, orderly; follows a clear
and justifiable series of steps
Empirical
how the world works (causal questions)
Factual/procedural
– Describes the facts of the world
Hypothetical
– what might be in the future
Normative
– How the world should be
What are the four key components of a theory?
- expectation (or prediction or hypothesis)
- causal mechanism
- assumptions
- scope conditions
Hypthesis/ expectation
What is the basic prediction of your theory?
– What is the relationship between the key variables you are
interested in?
Dependent Variable (Y)
Relies on the independent variable (Y)
Independent Variable (X)
Variable that affects/causes the DV
Causal Mechanism
The chain of events leading from the IV to the DV
Assumptions
Factors that are assumed to be true/false in your theory
Scope Conditions
When/ Where your theory is applicable
Observable Implication
Things that you would expect to be
true (or to see) if your theory is correct
Unit of Analysis
The cases or entities you study, the unit of
observation
Ecological fallacy (also known as aggregation bias)
failure in reasoning that arises when you draw an inference
about an individual based on aggregate data for a group
bivariate
2 variables (X causes Y)
multivariate
More than 2 variables (X and Z cause Y)
Correlation
an association between two variables
4 hurdles to establishing a causal relationship
- Is there a correlation between X and y?
- Can we rule out reverse causation?
- Is there a credible causal mechanism?
- Have we controlled for all confounding variables?
Reverse causation:
the possibility that Y could cause X
Confounding variable
a variable (Z) that is correlated with both the IV (X) and the DV (Y) and that somehow alters the
relationship between the two
What are the four hurdles for causal relationships.
- Is there a correlation between X and Y
- Reverse causation
- Is there a credible causation relationship
- Control for Confounding variables
test-retest
can the experiment be repeated by another person and get simular results
internal consistancy
Is there agreement among the questions asked?
intercode reliability
Will different observers get the same results?
convergent validation
Comparison of your measure compared to others that study the same thing
Construct validation
Does the measure correspond
theoretically to what you are trying to measure?
Conceptualization
How would you know it if you saw it/ What do the IV and DV mean
Operationalizing
How would you recognize it (observable features)
Substantive Intepretation
for every change in X, what changes in Y
r^2
How well the model fits the data- higher is a better fit
N
How many were measured of the Unit of analysis
sampling statistic
single measure of some attribute of a sample
sampling error
Difference between what is true and what is estimated (cannot know)
standard error
Average sampling error for sampling size
Beta Coefficient
the slope of the lineX/Y