1/82
Comprehensive vocabulary flashcards covering measurement reliability, validity, measurement scales, research designs, experimental control, artifact prevention, and statistical concepts from the Psy/Soc 10 Midterm 2 review.
Reliability
The consistency of a measurement.
Test-retest reliability
Giving the same test to the same people at two different times, where scores should be similar.
Alternative form reliability
Giving two equivalent versions of a test, where scores should be similar across versions.
Inter-rater reliability
The extent to which two different observers or coders agree on what they observe.
Internal consistency
An assessment of whether items within one test measure the same general concept.
Split-half reliability
A measure of internal consistency obtained by comparing scores from two halves of the same test.
Cronbach's alpha
A number estimating how consistently a test's items work together, where higher values generally indicate greater consistency.
Item-total correlation
A check to see whether one item's scores match the overall test-score pattern, ideally excluding that item from the total.
Validity
Whether a measure measures what it is supposed to measure.
Construct validity
The extent to which an instrument measures the intended theoretical concept (e.g., an anxiety test measuring anxiety rather than reading ability).
Content validity
The degree to which a measure covers all important parts of the concept (e.g., a final exam covering all major course topics).
Face validity
The extent to which a measure looks like it measures the intended concept at surface level.
Predictive validity
The ability of a measure to predict an outcome that is measured at a later time (e.g., an entrance exam predicting future grades).
Concurrent validity
The extent to which a measure agrees with a relevant criterion measure taken around the same time.
Convergent validity
The extent to which a measure relates strongly to other measures of the same or similar concepts.
Divergent/discriminant validity
The extent to which a measure does not relate strongly to measures of theoretically unrelated concepts.
Reactivity
A phenomenon that occurs when people change their behavior because they know they are being studied.
Unobtrusive measurement
Measuring behavior without noticeably interfering with participants, such as by using existing records.
Nominal scale
A measurement scale using categories with no inherent order (e.g., blood type or college major).
Ordinal scale
A measurement scale consisting of ordered categories where gaps between values may not be equal or are unknown (e.g., first, second, and third place; class rank).
Interval scale
A measurement scale characterized by equal intervals between values but no true zero point (e.g., temperature in Celsius).
Ratio scale
A measurement scale featuring equal intervals between values and an absolute, true zero meaning 'none' (e.g., weight, distance, response time, or time spent studying).
Quantitative approach
A research approach that uses numbers, scores, and counts to focus on amounts and statistical patterns.
Qualitative approach
A research approach that uses words, descriptions, and personal experiences to focus on meaning and context.
Experiment
A research method in which the investigator manipulates a variable and measures its effect; the strongest method for testing cause and effect.
Correlational design
A research design that measures whether variables are related without manipulating them; cannot establish causation.
Systematic observation
Recording clearly defined, actual behaviors using consistent, predetermined rules.
Survey
A method that asks people questions about their attitudes, experiences, or behavior to collect large amounts of data quickly.
Archival research
Analyzing information that already exists, such as statistical records, survey datasets, or media records.
Ethnography
Studying a group's culture through extended direct observation and immersion in their context.
Naturalistic observation
Observing behavior in its real-world, normal setting without manipulating or interfering with it.
Case study
An in-depth study of a single individual, group, or situation; useful for investigating rare phenomena and generating ideas.
Focus group
A small-group discussion led by a moderator to collect diverse viewpoints and foster interaction.
Content analysis
Systematically coding written or media material into categories (e.g., counting stereotypes in advertisements).
Structured interview
An interview method presenting identical questions in the exact same order to every participant, facilitating standardized comparison.
Semistructured interview
An interview format combining planned, predetermined questions with flexible follow-up inquiries.
Unstructured interview
A flexible, conversational questioning technique that can reveal unexpected information but is difficult to standardize.
Independent variable (IV)
The variable that the researcher manipulates in an experiment.
Dependent variable (DV)
The outcome variable that the researcher measures to assess the effect of the manipulation.
Confounding variable
An extraneous variable that varies systematically along with the independent variable, providing an alternative explanation for the findings.
Independent groups / between-subjects design
An experimental design where entirely different groups of participants are assigned to each experimental condition, eliminating carryover effects.
Repeated measures / within-subjects design
An experimental design where the exact same participants complete every experimental condition, reducing required sample size and controlling individual differences.
Matched groups design
A design where participants are matched on a key characteristic and then individual members of each pair/set are assigned to different conditions.
Carryover effect
An effect occurring in repeated measures designs when participation in an earlier condition influences performance in a subsequent condition.
Practice effects
Performance improvements that occur simply because participants have completed a task or measure previously.
Fatigue effects
Deteriorations in participant performance over time resulting from tiredness, boredom, or cognitive strain.
Counterbalancing
Varying the order in which experimental conditions are administered across participants to control for order and carryover effects.
Complete counterbalancing
An experimental procedure where every possible ordering of conditions is tested across participants.
Latin square
A counterbalancing technique using selected orders such that each condition appears at least once in each ordinal position.
Posttest-only design
An experimental design in which the treatment is administered first and the dependent outcome is measured only afterward.
Pretest-posttest design
A design in which the dependent variable is measured both before and after the administration of the experimental treatment.
Informed consent
Explaining the study procedures, risks, and participant rights prior to participation so individuals can voluntarily decide whether to enroll.
Debriefing
An educational session after study participation that explains the research purpose, clarifies any deception, and answers participant questions.
Operational definition
A clear, specific description explaining exactly how a variable is manipulated or measured in a study.
Straightforward manipulation
Directly altering instructions, materials, or physical conditions presented to participants.
Staged manipulation
Creating a complex, realistic situation or event specifically designed to induce a particular psychological experience.
Confederate
A member of the research team who poses as an ordinary participant or bystander during an experiment.
Ceiling effect
A situation where participants' scores cluster near the maximum possible value, often because a task is too easy, obscuring differences between conditions.
Floor effect
A situation where participants' scores cluster near the minimum possible value, often because a task is too difficult, making decreases impossible to detect.
Demand characteristics
Cues in an experiment that lead participants to guess the study's purpose and alter their behavior accordingly.
Experimenter bias
When researcher expectations unintentionally influence participant responses, task performance, or data recording.
Placebo group
A control group that receives an inactive or simulated treatment resembling the actual treatment to separate chemical/active effects from expectation effects.
Double-blind study
A research procedure in which neither the participants nor the experimenters interacting with or evaluating them know which treatment condition participants received.
Manipulation check
A measure used to verify whether the experimental manipulation successfully produced the intended psychological state or experience in participants.
Pilot study
A small-scale practice run of an entire study conducted prior to the main investigation to detect and fix procedural issues.
Descriptive statistics
Numerical and graphical procedures used to organize, summarize, and describe the characteristics of a collected sample dataset.
Inferential statistics
Statistical techniques that use sample data to draw conclusions and test hypotheses about a larger population while accounting for random sampling variation.
Normal distribution
A symmetrical bell-shaped frequency distribution where the mean, median, and mode are exactly equal.
Positively skewed distribution
An asymmetric distribution with a long tail extending toward high scores (to the right), typically resulting in a mean that is higher than the median.
Negatively skewed distribution
An asymmetric distribution with a long tail extending toward low scores (to the left), typically resulting in a mean that is lower than the median.
Central tendency
A statistical summary representing the center or typical value of a distribution, assessed via mean, median, or mode.
Mean
The arithmetic average obtained by adding all individual scores together and dividing by the total number of scores; highly sensitive to extreme outliers.
Median
The middle score in an ordered distribution dividing the upper half from the lower half; resistant to the influence of extreme scores.
Mode
The most frequently occurring score or response category in a distribution.
Variance
The average squared deviation around the mean; calculated for samples using n−1 as the divisor.
Standard deviation
The square root of the variance, representing the spread of scores around the mean in the original measurement units.
Pearson's r
A correlation coefficient measuring the strength and direction of a linear relationship between two continuous variables, ranging from −1 to +1.
Spearman correlation
It measures how strongly two variables tend to increase or decrease together, using their ranks rather than their actual values.
Effect size
A standardized statistical index describing the strength or magnitude of a relationship or experimental difference (e.g., Pearson's r).
Regression
A statistical procedure that uses one or more predictor variables to estimate or predict an outcome criterion score.
Multiple correlation
A statistical metric assessing how strongly several predictor variables simultaneously relate to a single continuous outcome.
Partial correlation
A technique measuring the linear relationship between two variables while statistically holding constant and controlling for the influence of other variables.
Path analysis
A statistical modeling method used to test proposed direct and indirect causal pathways among a set of measured variables.