POLS 209 - MIDTERM – KELLSTEDT STUDY GUIDE
Correlation - Answer -Similiarities.
Covariation - Answer -Differences.
Data - Answer -Collection of variable values for 2 or more observations.
Empirical - Answer -Based on real world observation.
Hypothesis testing - Answer -The hypothesis must have more support than the null
hypothesis.
Negative relationship - Answer -Greater values of the independent variable means
there are lower values of the dependent variable.
Normative statements - Answer -statements that describe how the world should/ought
to be
Operationalize - Answer -to turn a concept of interest into a measured or manipulated
variable. It is a form of measurement.
Paradigm - Answer -a shared set of assumptions and accepted theories in a particular
scientific field.
Parsimonious - Answer -simple & narrow.
Positive relationship - Answer -Greater values of independent variables means there
are also greater values of the dependent variables.
Theoretical model - Answer -the combination of independent variables, the dependent
variable, and the causal relationships that are theorized to exist between them.
Theory - Answer -A tentative conjecture (unconfirmed speculation) about the causes of
some phenomenon of interest.
- evidence/research happens before theory.
Rules of the road? - Answer -1. Make theories causal
2. Don't let data alone drive your theories
3. Consider only empirical evidence
4. Avoid normative statements
5. Pursue both generality & parsimony
Bivariate - Answer -involving just two variables
, Causal Hurdles scorecard - Answer -a shorthand for summarizing evidence about
whether an independent variable causes a dependent variable
Confounding variable - Answer -in an experiment, a factor other than the factor being
studied that might influence a study's results.
Correlated with the independent & dependent variables, and alters the relationship
between the two.
Deterministic relationship - Answer -if some cause occurs, then the effect will occur
with certainty.
Multivariate - Answer -involving more than two variables
Probabilistic relationship - Answer -increases in X are associated with increases (or
decreases) in the probability of Y occurring, but those probabilities are not certainties.
Spurious - Answer -not genuine, false, not what it appears to be.
Causality - Answer -- the relationship between cause and effect.
- studied in philosophy as "deterministic"
- Social reality is more complex, so it is understood as "probabilistic" in our world.
- examples: "tend to," "usually don't," "less likely to," "more likely to," etc.
4 Causal hurdles - Answer -1. Is there a credible causal mechanism that connects X to
Y? (how/why is the claim believable).
2. Can we rule out the possibility that Y could cause X?
3. Is there covariation between X and Y?
4. Have we controlled for all confounding variables Z that might make the association
between X and Y spurious?
(Hurdle 4 is the toughest to cross)
How does one control for Z? - Answer -- precise strategies (research designs)
- remember: if we don't control for Z, the other possible causes for Y, then our
conclusions about whether X -> Y might be mistaken.
- If reality is multivariate, and our theory is bivariate, we must control for other potential
causes for y.
Research design - Answer -Strategies that a researcher employs to make comparisons
with the goal of evaluating causal claims.
- helps us figure out if X -> Y.
- can be an experimental design or an observational study.
Experiment - Answer -A research design in which the researcher both controls &
randomly assigns values of the independent variable to the subjects.
2 main factors: control & random assignment.
Correlation - Answer -Similiarities.
Covariation - Answer -Differences.
Data - Answer -Collection of variable values for 2 or more observations.
Empirical - Answer -Based on real world observation.
Hypothesis testing - Answer -The hypothesis must have more support than the null
hypothesis.
Negative relationship - Answer -Greater values of the independent variable means
there are lower values of the dependent variable.
Normative statements - Answer -statements that describe how the world should/ought
to be
Operationalize - Answer -to turn a concept of interest into a measured or manipulated
variable. It is a form of measurement.
Paradigm - Answer -a shared set of assumptions and accepted theories in a particular
scientific field.
Parsimonious - Answer -simple & narrow.
Positive relationship - Answer -Greater values of independent variables means there
are also greater values of the dependent variables.
Theoretical model - Answer -the combination of independent variables, the dependent
variable, and the causal relationships that are theorized to exist between them.
Theory - Answer -A tentative conjecture (unconfirmed speculation) about the causes of
some phenomenon of interest.
- evidence/research happens before theory.
Rules of the road? - Answer -1. Make theories causal
2. Don't let data alone drive your theories
3. Consider only empirical evidence
4. Avoid normative statements
5. Pursue both generality & parsimony
Bivariate - Answer -involving just two variables
, Causal Hurdles scorecard - Answer -a shorthand for summarizing evidence about
whether an independent variable causes a dependent variable
Confounding variable - Answer -in an experiment, a factor other than the factor being
studied that might influence a study's results.
Correlated with the independent & dependent variables, and alters the relationship
between the two.
Deterministic relationship - Answer -if some cause occurs, then the effect will occur
with certainty.
Multivariate - Answer -involving more than two variables
Probabilistic relationship - Answer -increases in X are associated with increases (or
decreases) in the probability of Y occurring, but those probabilities are not certainties.
Spurious - Answer -not genuine, false, not what it appears to be.
Causality - Answer -- the relationship between cause and effect.
- studied in philosophy as "deterministic"
- Social reality is more complex, so it is understood as "probabilistic" in our world.
- examples: "tend to," "usually don't," "less likely to," "more likely to," etc.
4 Causal hurdles - Answer -1. Is there a credible causal mechanism that connects X to
Y? (how/why is the claim believable).
2. Can we rule out the possibility that Y could cause X?
3. Is there covariation between X and Y?
4. Have we controlled for all confounding variables Z that might make the association
between X and Y spurious?
(Hurdle 4 is the toughest to cross)
How does one control for Z? - Answer -- precise strategies (research designs)
- remember: if we don't control for Z, the other possible causes for Y, then our
conclusions about whether X -> Y might be mistaken.
- If reality is multivariate, and our theory is bivariate, we must control for other potential
causes for y.
Research design - Answer -Strategies that a researcher employs to make comparisons
with the goal of evaluating causal claims.
- helps us figure out if X -> Y.
- can be an experimental design or an observational study.
Experiment - Answer -A research design in which the researcher both controls &
randomly assigns values of the independent variable to the subjects.
2 main factors: control & random assignment.