Exam 3 Research Methods Flashcards
What is a Forced Choice question?
Respondents pick the best of two or more choices
(Ex: yes or no)
What is an Open-Ended question?
Respondents may answer any way they like
What is a Likert Scale question?
Survey format using a rating scale containing multiple response options
with anchors (1-5 strongly disagree, neither agree nor disagree, strongly
agree)
What is Semantic Differential question?
Survey format using a rating scale containing contrasting adjectives (1-5 Bad to Good)
What is a Double-barreled question?
Problematic question that asks two questions in one
(Ex: How much do you enjoy collecting and analyzing data?)
What is a Double Negative question?
Negatively phrased statements that make wording complicated or confusing
(Ex: I don’t want nothing to do with her)
What is a Leading question?
Wording encourages one response more than others
(Ex: Our company’s pizza rolls are the best aren’t they?)
Define: Order Effects
The order questions are asked in can affect responses
Define: Observer Effects
A change in behavior of study participants in the direction of
observer expectations
Define: Observer bias
Bias that occurs when observer expectations influence the
interpretation of behaviors or outcome of the study
Define: Reactivity
A change in behavior of participants due to being aware they are being watched
Define: Acquiescence: (AKA: yea: saying)
Saying yes to every item or strongly agree
Define: Naysaying
saying no to every item or strongly disagree
Define: Fence sitting:
playing it safe by answering in the middle of the scale for
every item
Define: Social Desirability Bias
Giving answers that making one look better
Define: Population
Larger group from which a sample is drawn
Define: Sample
Group of people, animals, or cases used in a study
Define: Census
Set of observations that contains all members of population of interest
Define: Oversampling
Researcher intentionally overrepresent one or more groups
What is probability sampling?
Ensures that the sample is representative of the population
What is nonprobability sampling?
Involves
selecting individuals based on convenience or judgment
Define: Convenience sampling
Choosing a sample based on those who are easiest to access and readily available
(Ex: Undergrads in college)
Define: Purposive sampling
Participants are chosen on purpose
Define: Snowball sampling
Participants asked to recommend acquaintances for the study
Define: Quota sampling
Researcher identifies subsets of populations of interest sets a target for number for each category in the sample and non randomly selects individuals within each category until quotas are filled
Define: Simple random sampling
Random sample chosen from the population of interest
(Ex: Choosing names out of a hat)
Define: Systematic sampling
Researchers use a randomly chosen number (N) and counts off every Nth member of the population to achieve a sample
Define: Cluster sampling
Cluster of participants within the population selected at random
Define: Multistage sampling
Random sample of people within the selected clusters (Involves at least 2 stages)
Define: Random sampling
a way of selecting members of a population for your study’s sample (everyone has an equal chance of being chosen)
Define: Stratified random sampling
Researcher identifies particular demographic categories and then randomly selects individuals within each category
Define: Random assignment
a way of sorting the sample into control and experimental groups
Define: Bivariate Correlation
An association that involves two variables
How can you interpret a correlation coefficient?
-1 to 1; closer to 1 stronger relationship, closer to 0 is weaker
Positively correlated: variables change in the same direction
Negatively correlated: variables change in opposite directions
How can you interpret effect sizes?
The magnitude, or strength, of a relationship between two or more variables
Weak (r=.1), moderate (r=.3), strong (r=.5)
Larger effect sizes are more important than smaller ones
Small effect sizes combined over many people or situations can have an important impact
When are confidence intervals statistically significant?
Confidence intervals are expressed like this
* [.04, .06] ! does not cross 0
* [-.04, .06] ! does cross 0
Confidence intervals that do not cross 0 are statistically significant
Define: Outlier
a score that stands out as either much higher or lower than most of the other scores in a sample
How does a moderator inform external validity?
When an association is moderated by residential mobility, type of relationship, day of the week, or some other variable, we know it does not generalize from one of these situations to the others
Define: moderator
A variable that (depending on the level) changes the relationship between two other variables
Define: Cross sectional
In a longitudinal design, a correlation between two variables that are
measured at the same time
Define: Autocorrelation
In a longitudinal design, the correlation of one variable with itself,
measured at two different times
Define: Cross-Lag
In a longitudinal design, a correlation between an earlier measure of one variable & a later measure of another variable
In a multiple regression design, ____ variable is to dependent variable as _____ is to independent variable.
Criterion; Predictor
Define: Mediator
Variable that helps explain the relationship between two other variables
Define: Independent Variable
The variable that is manipulated
Define: Dependent Variable
The variable that is measured
Define: Control Variable
Variable that a researcher holds constant on purpose
What is a control group?
Level of the IV that is intended to represent “no treatment” or a
neutral condition
What is a treatment group?
participants exposed to a level of IV that involves a medication,
therapy or intervention
Define: Design Confound
The experimenter’s mistake in designing IV
What is Independent-Groups design?
Different groups of participants are exposed to different levels of the IV
Each participant experiences only one level of the IV
AKA: between-subjects design or between-groups design
What is a within-group design?
Experimental design in which each participant is presented with all levels of the IV
AKA: within-subjects design
Everyone gets everything
What is a posttest-only design?
Experiment using an independent-groups design in which participants are tested on the DV only once
What is a pretest/post-test design?
Experiment using an independent-group design in which participants are tested on the key DV twice: once before & once after exposure to the IV
What is a repeated measures design?
Experiment using a within-group design in which participants respond to a DV more than once after exposure to each level of the IV
Define: Practice effects
type of order effect in which performance improves over
time due to becoming practiced at DV measure
Define: Carryover effects
type of order effect in which some form of
contamination carries over from one condition to the next
Define: counterbalancing
In a repeated measures experiment, presenting the levels of the IV to participants in different sequences to control for order effects
