exam 2 Flashcards
survey research
a quantitative and qualitative method with two important characteristics: measuring using self-reports and sampling
respondents
participants
large random samples are preferred because…
they provide the most accurate estimates of what is true in the population
most survey research…
is non-experimental, used to describe single variables and assess statistical relationships between variables BUT can be experimental
Model of the cognitive processes involved in responding to a survey item
question interpretation -> information retrieval -> judgment formation -> response formatting -> response editing
context effects
unintended influences on respondents’ answers - are not related to the content of the item but to the context in which the item appears: i.e. response options, item-order effect, type of questions, etc
item-order effect
when the order in which the items are presented affects people’s responses
open-ended items
ask questions and allow participants to answer in whatever way they choose
close-ended items
ask a question and provide a set of response options for participants to choose from
rating scale
an ordered set of response options on a typical rating scale ranges from 3 - 11, although five and seven are probably most common
likert scale
strongly agree, agree, neither agree nor disagree, disagree, strongly disagree
BRUSO
brief, relevant, unambiguous, specific, and objective
introduction serves two basic functions
encourage participants to participate in the survey, and establish informed consent
probability samples
occurs when a research can specify the probability that each member of the population will be selected for the sample
non-probability sampling
occurs when the research cannot specify these probabilities
convenience samples
studying individuals who happen to be nearby and willing to participate
snowball sampling
in which existing research participants help recruit additional participants for the study
quota samples
subgroups in the sample are recruited to be proportional to those subgroups in the population
self-selection samples
in which individuals choose to take part in the research on their own accord, without being approached by the researcher directly
sampling frame
essentially a list of all the members of the population form which to select the respondents
simple random sampling
each individual in the population ahs an equal probability of being selected for the sample
stratified random sampling
the population is divided into different subgroups or “strata” and then random sample is taken from each sub
proportionate stratified random sampling
select a sample in which the proportion of respondents in each of various subgroups matches the proportion in the population
disproportionate stratified random sampling
can be used to sample extra respondents from particularly small subgroups
cluster sampling
larger clusters of individuals are randomly sampled and then individuals within each cluster are randomly sampled
how large does a survey need to be?
depends on level of confidence wanted and the practical constraint
sampling bias
when a sample is selected in such a way that it is not representative of the entire population and therefore produces inaccurate results
non-response bias
if survey non-responders differ from survey responders in systematic ways
use verbal labels instead of
numerical labels
non-experimental research
research that lacks the manipulation of an independent variable - simply measuring variable as they naturally occur
used for description or prediction/correlation
correlational research
measuring two variables with little or no attempt to control extraneous variables and then assess the relationship between them
observational research
focuses on making observations of behavior in a natural or laboratory setting without manipulating anything
cross-sectional studies
comparing two or more pre-existing groups of people
longitudinal studies
one group of people is followed over time as they age
cross-sequential studies
combines elements of both cross-sectional and longitudinal studies
smaller period of time during which they follow people in different age groups\
correlation is used when…
when the relationship is thought to not be causal, when it can not be studied as causal, to establish reliability and validity of measurement and if higher external validity is more important.
scatterplots can have
a positive or negative relationship
Pearson’s r
correlation coefficient; -1.00 - 1.00
.1 = small, .3 = medium, .5 = large
only good for linear relationships
restriction of range
Pearson’s r can be misleading when one or both of the variables have a limited range in the sample relative to the population
directionality problem
two variables can be statistically related because X causes Y or because Y causes X
third-variable problem
two variables might be related because a third variable causes both X and Y
spurious correlation
correlations that are a result of a third-variable are referred to as this
correlation matrix
showing the correlation between every possible pair of variables in the study
factor analysis
organizes the variables into a smaller number of clusters, such that they are strongly correlated within each cluster but weakly correlated between clusters - each cluster is then interpreted as multiple measures of the same underlying construct
statistical control of potential third variables
instead of controlling these variables through random assignment or by holding them constant as in an experiment the researcher measures them and includes them in the statistical analysis caused partial correlation
regression
a statistical technique that allows researchers to predict one variable given another
can also be used to describe more complex relationship between more than two variables
predictor vairable
variable that is used to make the prediction
outcome or criterion variable
variable being predicted
interviews
can be unstructured or structuredf