1/64
Vocabulary practice flashcards for PSY 141 Final Exam covering research methods, design types, validities, ethical considerations, measurement, and statistical tests.
Empiricism
The practice of using verifiable, systematic observation and evidence collected through the senses or measurement instruments as the basis for drawing scientific conclusions.
Falsifiability
A feature of a good scientific theory stating that a hypothesis or theory must be formulated in a way that allows it to potentially fail or be proven wrong with empirical data.
Preregistration
The practice of publicly registering a study's hypotheses, design, and data analysis plan prior to collecting data to prevent questionable research practices.
Basic vs. Applied Research
Basic research seeks to enhance general theoretical knowledge, whereas applied research is conducted with a specific, real-world practical problem in mind.
Confederate
An actor who participates in a psychological study while pretending to be another participant or bystander, following scripted instructions by the researcher.
Availability Heuristic
A cognitive bias where people estimate the likelihood of events based on how easily recent or salient examples come to mind.
Confirmation Bias
The tendency to seek out, interpret, and favor information that supports one's preexisting beliefs while ignoring or discounting contradictory evidence.
Bias Blind-Spot
The cognitive tendency to recognize biases in others' judgments while failing to recognize the presence of biases in one's own thinking.
Meta-analysis
A statistical procedure for mathematically combining and synthesizing the results of multiple independent empirical studies to determine the overall effect size.
Systematic Review vs. Narrative Review
A systematic review uses explicit, structured, and repeatable scientific methods to identify and summarize all relevant literature, whereas a narrative review provides a broader, qualitative summary without formal search and synthesis protocols.
Conceptual Definition vs. Operational Definition
A conceptual definition defines a variable at the theoretical level, whereas an operational definition specifies the exact method, procedure, or instrument used to measure or manipulate that variable in a study.
Frequency Claim
A claim that describes a particular rate, proportion, or level of a single measured variable within a population.
Association Claim
A claim that argues that two or more measured variables covary or are related, such that knowing the level of one allows the prediction of the level of the other.
Causal Claim
A claim arguing that a specific change in one variable is directly responsible for producing a change in another variable.
Three Rules for Causation
The criteria required to demonstrate causality: covariance (the variables are correlated), temporal precedence (the cause occurs before the effect), and internal validity (no alternative explanations or confounds exist).
Construct Validity
The extent to which an operational measure accurately captures the theoretical construct it is intended to measure.
External Validity
The degree to which the findings of a study can generalize beyond the sample to other populations, contexts, times, or places.
Internal Validity
The degree of certainty that the independent variable, and not an unmeasured confound or alternative explanation, caused changes in the dependent variable.
Statistical Validity
The extent to which the study's statistical conclusions, effect sizes, statistical significance tests, and sample considerations are sound and accurate.
Beneficence
A Belmont Report ethical principle requiring researchers to protect participants from harm, ensure their well-being, and maximize potential benefits while minimizing potential risks.
Respect for Persons
A Belmont Report ethical principle asserting that individuals should be treated as autonomous agents who voluntarily grant informed consent, with extra protection provided to populations with diminished autonomy.
Justice
A Belmont Report ethical principle demanding a fair balance between the kinds of people who bear the burdens of research participation and the people who benefit from its outcomes.
Institutional Review Board (IRB)
A formal committee mandated at research institutions to review the ethics of research proposals involving human participants before any data can be gathered.
Anonymity vs. Confidentiality
Anonymity means researchers collect no identifying participant information, whereas confidentiality means identifying information is collected but kept strictly secure and inaccessible to anyone outside the research team.
Data Fabrication vs. Data Falsification
Data fabrication involves completely inventing research data out of thin air, whereas data falsification involves improperly altering or cherry-picking existing data or manipulating research procedures to distort the results.
Test-Retest Reliability
The consistency in results obtained when researchers administer the same measurement scale to the same participants at two different points in time.
Interrater Reliability
The level of agreement or consistency between two or more independent raters or observers who record the same behavior or phenomena.
Internal Reliability
The degree to which different items on a multi-item self-report scale correlate with one another to assess the same single theoretical construct.
Cronbach's Alpha
A correlation-based statistical metric computed to evaluate the internal reliability of a multi-item measurement scale.
Criterion Validity
An empirical assessment of construct validity evaluating whether a measure correlates meaningfully with relevant behavioral outcomes or objective standards.
Convergent Validity vs. Discriminant Validity
Convergent validity is the extent to which a measure correlates strongly with measures of theoretically similar constructs, whereas discriminant validity is the extent to which it does not correlate with measures of theoretically dissimilar constructs.
Double-Barreled Question
A poorly constructed survey question that combines two separate issues or questions into one, making it ambiguous which part the respondent is addressing.
Acquiescence
A response set in survey taking where a respondent systematically chooses 'agree' or 'yes' to every statement without carefully reading the prompt.
Fence-Sitting
A response set in which respondents systematically choose the neutral middle option on a scale to avoid taking a stand, particularly on controversial topics.
Socially Desirable Responding
A response bias (also known as faking good) where participants answer questions dishonestly to portray themselves in a favorable or socially acceptable light.
Observer Bias
A bias that occurs when an observer's expectations or preconceived hypotheses influence how they record and interpret participants' behaviors.
Observer Effect (Expectancy Effect)
A phenomenon that occurs when an observer's behavior inadvertently causes the participants to change their behavior to match the observer's expectations.
Reactivity
A change in participant behavior caused simply by the awareness that they are being observed or studied.
Stratified Random Sampling
A probability sampling technique where the researcher identifies specific demographic categories (strata) and then randomly selects participants proportionally from each stratum.
Random Sampling vs. Random Assignment
Random sampling is a method of selecting participants from a population to maximize external validity, whereas random assignment is a procedure used in experiments to assign participants to conditions to maximize internal validity.
Design Confound
A threat to internal validity in an experiment where a second variable systematically varies along with the intended independent variable, providing an alternative explanation for the outcome.
Selection Effect
A threat to internal validity that occurs when the kinds of participants in one treatment level are systematically different from those in another level, often due to non-random assignment.
Independent-Groups Design vs. Within-Groups Design
In an independent-groups (between-subjects) design, different participants are exposed to each level of the independent variable; in a within-groups design, each participant is exposed to all levels of the independent variable.
Counterbalancing
A technique used in within-groups designs where participants are assigned to different orders of experimental conditions to prevent order, carryover, or practice effects from confounding results.
Latin Square
A formal partial-counterbalancing system used in within-groups designs ensuring that each condition appears at each ordinal position once, and each condition precedes and follows each other condition once.
Demand Characteristics
Cues or characteristics within an experiment that lead participants to guess the experimental hypothesis and alter their behavior accordingly.
Regression to the Mean
A statistical phenomenon and threat to internal validity where an extreme score at pretest naturally drifts closer to the average score upon retesting.
Attrition Threat
A threat to internal validity that occurs when a specific, systematic type of participant drops out of a multi-part study before completion.
Ceiling Effect and Floor Effect
Measurement problems where scores cluster at the high end (ceiling) or low end (floor) of a scale due to an insensitive dependent variable or an overly strong or weak manipulation.
Factorial Design
An experimental setup involving two or more independent variables (factors), in which every level of every variable is crossed with every level of every other variable.
Main Effect
The overall effect of one independent variable on the dependent variable in a factorial design, averaging across all levels of the other independent variables.
Interaction Effect
An outcome in a factorial design where the effect of one independent variable on the dependent variable differs depending on the level of another independent variable.
Quasi-Experiment
An empirical study resembling an experiment but lacking full experimental control, typically because researchers cannot randomly assign participants to conditions.
Interrupted Time-Series Design
A quasi-experimental design in which participants or groups are repeatedly measured on a dependent variable before, during, and after an interruption or event occurs.
Wait-List Design
A quasi-experimental study design in which all participants are assigned to receive an intervention, but some receive it immediately while others wait, serving as a control group during the delay.
Direct Replication vs. Conceptual Replication
A direct replication reproduces the original study's operational methods as closely as possible, whereas a conceptual replication uses different operationalizations to test the same underlying theoretical hypothesis.
File Drawer Problem
A publication bias phenomenon where studies finding null effects or non-significant outcomes are not published, remaining tucked away in researchers' files.
p-Hacking
Questionable data analysis practices—such as removing outliers post-hoc, testing multiple subsets, or adding subjects until p<0.05—aimed at achieving statistical significance.
HARKing
An unethical research practice that stands for 'Hypothesizing After the Results are Known,' presenting a post-hoc finding as if it had been predicted from the start.
Descriptive vs. Inferential Statistics
Descriptive statistics organize, summarize, and describe the characteristics of a data sample, whereas inferential statistics use sample data to make generalized inferences about a broader population.
Alpha Level
The established probability threshold (commonly α=0.05) used by researchers to determine statistical significance and reject the null hypothesis.
Pearson Correlation Coefficient
A standardized inferential statistic (r) ranging from −1.00 to +1.00 that indicates the direction and strength of the linear relationship between two continuous variables.
t-Test
An inferential statistical test used to evaluate whether there is a statistically significant difference between the means of two groups (independent) or two conditions within the same group (paired).
Analysis of Variance (ANOVA)
An inferential statistical test (F-test) used to compare the means of three or more groups or factor levels to determine whether at least one mean differs significantly.
Chi-Square Test
A non-parametric inferential statistical test used to evaluate whether observed categorical frequencies significantly differ from expected frequencies.