Research Design & Analysis Exam 2 Flashcards
self-report measure
operationalizes a variable by recording people’s answers to questions about themselves in a questionnaire
observational measure
operationalizes a variable by recording observable behaviors or physical traces of behaviors
physiological measure
operationalizes a variable by recording biological data such as brain activity, hormone levels, etc.
quantitative data
data that is collected numerically or intended to be coded numerically
categorical variable
scale is assessed in categories (sex, race, gender, etc.)
ordinal variables
variables measured in ranks
test-retest reliability
a participant will get pretty much the same score each time they are measured with it
continuous scales
equal distance between each scale position
interrater reliability
consistent scores are obtained no matter who measures the variable
internal reliability
a participant gives a consistent pattern of answers, no matter how the researcher phrases the question
correlation coefficient
direction (position/negative sign) associated with the number
-strength (the number)
face validity
it looks like what you want to measure
content validity
the measure contains all the parts that your theory says it should contain
criterion validity
evaluate whether the measure under consideration correlates with behavioral outcomes we expect
convergent validity
the measure correlates with the other, and establishes measures designed to the same or similar constructs
why conduct surveys?
-to study relationships between/among variables
-provides a methodology for asking people to tell about themselves
discrimination validity
the measure does not correlate with the other, establishes measures designed to the same or similar constructs
questionnaires
-personal admin to groups or students
-mail surveys
-internet surveys
interviews
-face to face interviews
-telephone interviews
-focus group interviews
response set
a type of shortcut people can take when answering survey questions
acquiescence
when people say yes to every item instead of carefully thinking about each one
fence sitting
playing it safe by answering in the middle of the scale, especially for controversial studies
naturalistic observation
-observation in natural setting
-no attempt to intervene or change situation
observer effects
when participants confirm observer expectations
how to prevent observer bias?
-train observers well
-provide clear rating instructions
-multiple observers
reactivity
change in participants behavior when they know they are being watched
population
entire set of people or products in which you are interested
sample
a smaller set taken from the population
census
a set of observations that contains all members of the population of interest
biased sample
when some members of the population of interest are left out, resulting in the results not being generalized to the population
unbiased sample
when all members of the population are equally included
convenience sampling
sampling only those who are easy to contact
self-selection
sampling only those who volunteer
simple random sampling
when the sample is chosen randomly from the population
systematic sampling
when the researcher uses a randomly chosen number, N, and counts off every Nth member of a population
cluster sampling
when clusters of participants within the population of interest are selected at random
multistage sampling
involves a random sample of clusters followed by a random sample of people within the selected clusters
stratified random sampling
when the researcher identifies particular categories, and then randomly selects individuals within each category
oversampling
when the researcher overrepresents one or more group
random assignment
used only in experimental designs to assign participants to groups at random
what does random sampling increase?
external validity
what does random assignment increase?
internal validity
purposive sampling
a biased sampling technique in which only certain kinds of people are included in a sample
snowball sampling
when participants are asked to recommend acquaintances for the study
quota sampling
when the researcher identifies subsets of the population, sets a target number, and non randomly selects individuals within each category until the quotas are filled
time sampling
choose time intervals for making observations
situation sampling
choose different settings or conditions for observations
bivariate correlations
associations that involve exactly two variables
t test
a statistic to test the difference between two group averages
what makes a study correlational?
having two measure variables
effect size
describes the strength of an association
outlier
-extreme scores in a few cases
-can make a correlation seem stronger or weaker than it really is
restriction of range
-lack of full range of scores on one of the variables
-makes correlations appear smaller than they really are
curvilinear association
association between two variables is not a straight line
directionality problem
unable to determine which variable comes first
third variable problem
a potential third variable might explain the relationship between the first two
spurious association
a bivariate association that is attributable only to systematic mean differences on subgroups within the sample, not the original association
moderator
a variable the changes the relationship between two other variables
multivariate design
involve more than two measured variables
what are the three criteria to establish causation?
-covariance
-temporal precedence
-internal validity
longitudinal research
compares the same group to itself over time
cross sectional research
compares two variables or groups of people to one variable, at one time-point
parsimony
the degree to which a scientific theory provides the simplest explanation of some phenomenon