experimental research Flashcards
treatment group
he group that gets the “treatment,” or the altered independent
variable.
control group
The group that does not receive the “treatment.” We can see this
group as the baseline
treatment vs control
Experiments involve manipulating one or more independent variables across
treatment and control groups.
Then, both groups are assessed to see if there are any differences between them
lab experiments
conducted in an artificial setting, with controlled manipulations
field experiments
Field experiments are conducted in a real-world setting with controlled
manipulations
conjoint experiments
Conjoint experiments are survey-based techniques that help determine the attributes
people value in an object or action
vignette experiments
Vignette experiments provide participants with different examples of situations and
ask for participants’ reactions and responses to these situations
quasi-experiments
research studies that investigate the effect of an intervention or treatment
Quasi-experimental designs approximate a true experimental design but lack random assignment to experimental and control groups
natural experiments
Natural experiments are where the treatment and control groups are naturally
occurring.
when does a natural experiment occur
This happens where the treatment and control group differ substantially without any
intervention or manipulation by the researcher
example of a natural experiment
For example, in examining the effect
of access to public transportation (IV) on class attendance (DV), a researcher may
look at a set of students from a rural community, versus a set of students from a more
urban community. They may observe that access to public transport (our independent
variable) varies across the two groups. Individuals from an urban community may
have better access to public transportation naturally, just based on where they live—
without any need for the researcher to manipulate the independent variable
themselves
internal validity
Refers to how well a study shows whether changes in the
independent variable causes changes in the dependent variable
external validity
Refers to a study’s ability to generalize results from its site or
sample to its target population or beyond.
confounder
A confounding variable is a variable other than the independent
variable that is causing a change in the dependent variable.
spurious relationships
A situation in which a relationship between two variables
seems to exist but, in reality, they are correlated because of a third variable, a
confounder
how do confounding variables influence a study’s internal validity
threaten a study’s internal validity by creating alternative explanations for results, making it difficult to determine if observed relationships are truly causal
what is the point of having treatment and control groups
to see if a difference is the result of this specific change in variable, or just by chance
critiques of experimental research
potential for artificiality, ethical concerns, and limitations in generalizability, especially when dealing with complex real-world phenomena
purpose of random assignment in experimental research
to ensure that groups being compared are equivalent at the start of the study, minimizing bias and allowing researchers to confidently attribute any observed differences in outcomes to the manipulated variable
deductive approach
starts with a general theory or hypothesis and then tests it through specific observations or experiments, moving from the general to the specific
experiments are deductive
inductive approach
starts with specific observations or data and moves towards broader generalizations or theories
