1/53
Looks like no tags are added yet.
characteristics of survey research
the variables of interest measured are self-reporting
a lot of attention on who we sample from and overall sampling
most are non-experimental and used to describe single variables
context effects
unintended influence on respondents’ answers
item-order effect
the order in which items are presented affects people’s responses
BRUSO
the order in which items are presented affects people’s responses
brief
relevant
unambiguous
specific
objective
probability sampling
the researcher can specify the probability that each member of the population will be selected
non-probability sampling
when the researcher can’t specify these probabilities
convenience sampling
selecting whoever’s nearby and willing to participate
snowball sampling
participants help recruit additional participants
quota sampling
subgroups are reported to be proportional to subgroups in the actual population
self-selection
individuals choose to participate without being approached directly by the researchers
sampling frame
list of all the members of the population to select respondents. needed for probability sampling
simple random sampling
every individual in a population has an equal chance of being chosen
stratified random sampling
the population is divided into different subgroups or strata, and a random sample is taken from each one
proportionate stratified random sampling
selecting a proportion of respondents in each subgroup that’s proportionate to the population
disproportionate stratified random sampling
sampling extra respondents in extra small subgroups
cluster sampling
large clusters of individuals are randomly sampled, and individuals in these clusters are randomly sampled, too
sampling bias
occurs when a sample is selected in a way that’s not representative of the whole population
non-response bias
when non-responders differ from survey responders in systematic ways
the process of answering one item
interpret the problem
retrieve information
form a judgment
format the response
edit the response
the process/components of making a questionnaire
an introduction that recruits
informed full consent
clear instructions
most important items first
group by topic and scale
demographics last, then thanks
what is the most common range of respondents for surveys?
100-1000
quasi-experimental research
resembles experimental research, but is either missing a control group or participants are not randomly assigned to conditions
one-group posttest only design
the dependent variable is measured after a treatment is implemented
weakest type of quasi-experimental design
pretest-posttest design
measured once before the treatment is implemented, and again afterwards
alternative explanations to a post-test score being higher than the pre-test score
history: something happening before the time
maturation: participants might’ve changed during the time
testing: measuring the dependent variable during the pre-test
instrumentation: the basic characteristics of the measuring instrument changes over time
threat to internal validity
a regression to the mean
an individual who scores extremely high or low on one occasion tends to score closer to the mean, often due to chance
spontaneous remission
the tendency for medical and psychological problems to improve overtime without treatment
interrupted time-series design
a set of measurements taken at intervals over a period of time
non-equivalent groups design
participants aren’t randomly assigned to conditions
post-test only (NEGD)
one group is exposed to the treatment, the other isn’t. they’re compared after
pretest-posttest (NEGD)
both treatment and control groups get a pretest and posttest in between whether or not they’re treated
interrupted time-series (NEGD)
taking a set of measurements at intervals over a period of time before and after an intervention in two or more nonequivalent groups
pretest-postest with switching replication (NEGD)
nonequivalent groups are given a pretest of the dependent variable. the DV is assessed again after given the treatment
switching replication with treatment removal design (NEGD)
the treatment is removed from the first group when it’s added to the second group
factorial designs
experiments that include more than one IV
one IV is combined with each level of the others to produce all possible combinations. each combination becomes a condition in an experiment
between-subjects factorial design
choosing between within and between-subjects must be made separately for each IV. all IVs are manipulated between subjects
mixed factorial design
manipulating one IV between subjects and another one within subjects
non-manipulated IVs are in many factorial designs
main effect
the effect of one IV on the DV- averaging across the levels of the other IV
interaction
when the effect of one IV depends on the level of another
spreading interactions
one IV has a strong effect at one level of a variable, but little to no effect at another level
cross-over interaction
one IV has an effect at both levels of another IV, but the effects are in opposite directions
social validity
treatments that have substantial effects on important behaviors that can be implemented reliably in the real world
reversal/ABA design
phase A: a baseline is established for the DV
phase B: the researcher introduces the treatment
phase A: the researcher removes the treatment and waits for it to reach a steady level
repeats as many times as needed
alternating treatments design
multiple treatments are alternated quickly on a regular schedule
across participants (mulitple-baseline)
a baseline is established for each participant, and the treatment is introduced for each one at a different time
across behaviors (mulitple-baseline)
multiple baselines are established for the same participant, but for different behaviors. the treatment is introduced at a different time for each DV
across settings (mulitple-baseline)
multiple baselines are established for the same participant in different settings
factors researchers take into account from single-subject visual inspection
level of DV across conditions
trend of gradual increases or decreases across observations
latency, the time it takes for the DV to begin changing after a change in conditions
experimental analysis of behavior
using single-subject research to describe how rewards, punishments, and other external variables affect behavior over time
Skinner
steady state strategy
the researcher waits until the participant’s behavior is in one condition
multiple-treatment reversal design
a baseline is followed by separate phases where different treatments are introduced
multiple-baselines design
measures a trait before and after applying a treatment to one or more participants
across behaviors or
across settings or
across participants
percentage of non-overlapping data (PND)
percentage of responses in the treatment condition that are more extreme than the most extreme response in a relevant
converging evidence
we should examine the pattern of flaws running through the literature because its nature can support or undermine the conclusions we wish to draw