Research Design Foundations (Schwab, 2005) Flashcards
Explore the 4 research designs and important terms related to understanding research design
Misspecification
Occurs if variables that operate in the causal model are not included in
the model studied.
Nuisance variable
A variable in the causal model that is not controlled in a research study,
Biased relationship
An observed relationship between an independent and a dependent variable that under- or overstates the causal relationship.
Spurious relationship
An observed relationship between an independent and a dependent variable but no causal relationship. Occurs when a nuisance variable accounts for all the
observed relationship between a dependent and an independent variable(s).
Suppressor variable
A nuisance variable that biases an observed relationship between an independent and a dependent variable downward; usually occurs when a nuisance variable has a positive relationship with the independent variable and a small negative relationship
with the dependent variable.
Noisy relationship
Occurs when a nuisance variable is related to the dependent variable but not to the independent variable(s).
Mediator variable (intervening variable)
comes between an independent and a dependent
variable in a causal chain.
Full mediation
The relationship between an independent and dependent variable operates
only through a mediator variable. The independent variable has no direct effect on
the dependent variable.
Partial mediation
The relationship between an independent and dependent variable operates partially through a mediator variable. The independent variable has a direct effect on the dependent variable and an indirect effect through the mediator.
Moderator variable
A variable whose values are associated with different relationships between an independent and a dependent variable. It may or may not be an independent
variable.
Interaction variable
Synonym for moderator variable. A relationship between an independent and a dependent variable depends on the value of another variable.
Boundary condition
Synonym for moderator variable. A relationship between an independent and a dependent variable depends on the value (boundary) of another variable.
Probability sampling
The selection of a subset of cases obtained from a larger population of cases by using rules of probability.
Convenience sampling (also judgment sampling)
The selection of cases (usually an intact
group) to study by using nonprobability methods.
Restriction of range
A reduction in the variance of a variable through selection of cases.
Comparison groups
Groups of research cases thought to be comparable on levels of potential nuisance variables.
Matching
Cases are selected for research so those who experience different levels of an independent variable(s) are equated on levels of nuisance variables.
Random assignment
Allocation of cases to levels of an independent variable(s) without order; a procedure designed to equate cases on nuisance variables at each level of an independent variable(s).
Experiments
A research design in which cases are randomly assigned to levels of an independent variable(s).
Quasi-experiments
A research design in which cases do not control the levels of the independent variable(s) they experience; cases are not randomly assigned to levels of the independent variable(s).
Field study
A research design in which values of the independent variable(s) are characteristics of the cases studied and in which cases are not randomly selected from some larger population.
Survey study
A research design in which values of the independent variable(s) are characteristics of the cases studied and in which cases are randomly selected from some larger
population.
