Ch9- Experimental Research Flashcards
random assigment
division of subjects into groups at the beginning of experimental research using a random process so the experimenter can treat the groups as equal
science of the sophmore
first year psych grad students - generalizability limited
limited external validity of studies based on undergraduate samples usually using the experimental method.
Matching
alternative to random assignment - infrequently used
relevant characteristics to match on - locate exact matches - hard to match on all characteristics - hard to known which are meaningful
Parts of the experiment
- independent var
- dependent variable
- pretest
- post-test
- experimental group
- control group
- random assignment
pretest
measurement of the dependent variable prior to the introduction of treatment
post test
is the measurement of the dependent variable after the treatment has been introduced into the experimental situation
classical experimental design
has
- random assignment
- control group
- experimental group
- pretests and post-tests for each group
pre-experimental designs
used when difficult to use classical
weaknesses that makes inferring a causal relationship more difficult
- lack random assignment
- weaker internal valdity
one-shot case study design
only has experimental group, post-test and no pre-test
new staff training asking question after delivering food, record tips for all after a month
one group pretest post-test design
One group, pretest, treatment, post test
no control or random assignment
hire, dont train take pretest, train take post test
static group comparison
an experimental design with two groups, no random assignment and only a post test
train go to one of two resturants, retrain people at resturant one at 1m - experimental, control group retrained to not check in - tips recorded after
quasi-experimental
experimental designs that are stronger than pre-experimental designs.
variations on the classical experimental design that an experimenter uses in special situations or when an experimenter has limited control over the independent variable
two-group post test only design
identical to static except groups are randomly assignment
all parts of the classical design except a pretest
random assignment reduces the chance that the groups differed before the treatment but without a pretest researcher can not be certain that the groups began with respect to the independent variable
participation higher with reward example
interrupted time series design
researcher uses one group and makes multiple pretest measures before and after the treatment.
- cigarette taxes jumped - taxes remained constant
dependent variable measured across many time points,treatment occurs in the midst often only once
equivalent time series
an experimental design in which there are several repeated pretests, posttests, and treatments for one group, often over a period of time.
one-group design that extends over a time period,
latin square designs
used to examine whether the order or sequence in which subjects receive multiple versions of the treatment has an effect
Solomon four-group design
an experimental design in which subjects are randomly assigned to two control groups and two experimental groups. only one experimental group and one control group receive a pretest.
all four groups receive a post-test.
pretest can sometimes sensitize subjects to the treatment or improve their performance on the post-test - developed this to overcome that
factorial design
two or more independent variables in combination
main effects and interaction effects - two or more variables that operate simultaneously
Threats to internal validity
selection bias
history effects
maturation
testing effect
instrumentation
morality
statistical regression
diffusion of treatment
experimenter expectancy
selection bias
threat to internal validity when groups in an experiment are not equivalent at the beginning of the experiment
subjects in experimental have a characteristic that affects the dependent variable
maturation
long time periods
threat to internal validity - due to natural processes of growth, boredom, and so on that occur to subjects during the experiment and affect the dependent variable
history effects
threats to internal validity that result from an occurrence that affects the dependent variable during an experiment but that is unplanned and outside the control of the experimenter
terrorist attack happens during racism study
testing effect
a pretest measure that itself affects an experiment- threatens internal validity because more than the treatment alone affects the dependent variable
remembering items on a test
instrumentation
a threat to reliability occuring when the dependent variable measure changes during an expeirment
scales for weight loss weaken
morality
threat to internal validity due to subjects failing to participant through the entire experiment
attrition
statistical regression
a problem of extreme values or a tendency for random errors to move group results toward the average - threat to internal validity
happens in two ways
1. subjects are unsusual with regard to dependent - started violent less violent later - begin at extremem move to average by chance
- problem with measurement instrument - floor or ceiling scores - random chance will produce change btw pretest and post test
diffusion of treatment
threat that research participants in different groups will communication with each other and learn about the others treatment - threat to internal validity
experimenter expectancy
threat to internal validity not by a researcher’s purposefully unethical behaviour but by their indirectly communicating desired findings to the subjects
reactivity
a threat to external validity that arises because subjects are aware they are in an experiment being studied
hawthorne effect
a effect of reactivity named after a famous case in which subjects reacted to the fact that they were in an expeirment more than they reacted to the treatment.
participants responded not to the treatment but to the additional attention they received from being a part of the experiment - knowing they were being watched
field experiment
experimental research that takes place in a natural setting
natural experiment
quasi-experiment by which a researcher can examine the impact of a policy change or similar change in a social system by comparing an outcome of interest before and after such change is implemented.