research design 2 exam 1

research design: case study

qualitative strategy focused on the in-depth investigation of a single entity or a small group of entities, such as a specific person, organization, community, or event

research design: correlation

non-experimental strategy used to investigate the statistical relationship between two or more variables without the researcher manipulating or controlling any of them

research design: experimental

framework used to establish a cause-and-effect relationship by deliberately manipulating one variable to isolate and measure its exact impact on another variable

research design: non-experiment

framework where the researcher labels, measures, and observes variables as they naturally occur without manipulating an IV or randomly assigning participants to conditions

research design: quasi-experiment

participants are not randomly assigned to groups, often because it is unethical or impossible (ex. comparing smokers vs non-smokers)

observational techniques: naturalistic

non-experimental, qualitative or quantitative research method where scientists observe and record behaviors in their natural environments without any intervention, manipulation, or interaction

observational techniques: archival

non-experimental method where researchers analyze pre-existing data

observational techniques: contrived

research method where scientists deliberately create an artificial environment or manipulate a specific situation to observe how participants behave under those exact conditions

observational techniques:

theory

ideas that explain why or how specific phenomena occur

hypothesis

specific, testable, and falsifiable prediction about the relationship between two or more variables

prediction

specific, measurable statement detailing what outcome will occur in a study if a given hypothesis is true

construct

a complex concept that cannot be directly observed or measured

operational

the precise, concrete, and measurable description of how a researcher will define, create, or measure an abstract construct in a specific study

categorical variables

a type of variable that divides data into distinct groups, classes, or categories based on a specific characteristic

numerical variables

a data type that expresses a measurable quantity with numbers

concurrent validity

a type of measurement validity where a new test score matches up with an established, trusted test score measured at the exact same time

construct validity

the degree to which a test, survey, or measurement tool actually measures the abstract psychological concept it claims to be measuring, rather than an entirely different trait by mistake

predictive validity

type of validity where a test score successfully forecasts a person’s future performance, behavior, or outcomes on an outside benchmark

face validity

the extent to which a test or measurement tool appears to measure what it claims to measure to a casual observer or participant at face value

test-retest reliability

a method for evaluating measurement consistency by administering the exact same test to the same group of individuals across two separate time points and calculating the correlation between the two sets of scores

interrater reliability

the degree of agreement and consistency between two or more independent observers when they score, code, or evaluate the same data

independent variable

what we manipulate (change), and has at least two levels (conditions)

dependent variable

what we measure

control group

group that receives no treatment (IV)

extraneous variable

any variable in a study other than the two variables studied

confounding variable

an extraneous variable that changes systematically with the two variables being studied and influences the DV

internal validity

extent to which the IVs and only the IVs, caused changes in the DVs

external validity

extent to which the results can generalize to other people, settings, times, measures, and characteristics

simulation

create an artificial environment that’s similar to the natural environment of interest

field study

experiment conducted in the real world

subject variables

the existing characteristics, traits, or demographics that participants naturally bring with them into a study

higher order designs

have more than 2 factors —> leads to 2 × 2 factorial designs

within design

all subjects receive all levels of independent variables

between design

one group of subjects gets 1 level of IV while the other group of subjects gets other level of IV

practice, fatigue, and contrast effects

practice effects: participants get better at a task over time because they gain familiarity and learn the routine

fatigue effects: participants perform worse over time because they grow tired, bored, or lose interest

contrast effects: experiencing one condition alters how a participant perceives or reacts to stimuli in the next condition

disadvantages to within design (participant attrition, time-related problems, and order effect)

participant attrition: car result in only one measurement for a subject

time-related problems: participants may be influenced by outside factors between measurements

order effect: first measurement may influence subsequent measurements

counterbalancing

systematically varying the order of presentation of the conditions to distribute order effects evenly across all conditions

within-subjects design (repeated measure)

an experimental framework in which every single participant is exposed to all conditions, treatments, or time points of a study

within (concurrent)

variation of within-subjects framework where participants are exposed to all levels of the independent variable at the exact same time and then select a single preference or behavioral response

purpose of random sampling

to select a subset of individuals from a larger population in a way that ensures every member has an equal and independent chance of being chosen
eliminates selection bias and achieving external validity (representativeness)