1/59
Comprehensive practice flashcards covering core concepts of bivariate correlations, multivariate longitudinal and regression designs, simple experimental designs, internal validity threats, and null effects.
Bivariate Correlation
An association that involves exactly two measured variables.
Correlation Coefficient (r)
A numeric index ranging from −1.0 to +1.0 that describes the direction and magnitude of a linear relationship between two quantitative variables.
Directionality Problem
A problem in correlational research where two variables are measured around the same time, making it unclear which variable came first and hindering causal inference.
Third-Variable Problem
The existence of a plausible alternative explanation (a lurking or confounding variable) that accounts for the association between two variables in a correlational study.
Spurious Correlation
An apparent association between two variables that seems to exist but is not real, often resulting from a shared relationship with a third variable or coincidence.
Moderating Variable (Moderator)
A variable that, depending on its level, changes the strength or direction of the relationship between two other variables.
Outlier
A score that stands out as either much higher or much lower than most of the other scores in a distribution, which can exert a disproportionate influence on statistical estimates.
Curvilinear Association
A non-linear relationship in which the association between two variables changes direction across different values (e.g., positive up to a point, then becoming negative).
Effect Size
The magnitude, or strength, of a relationship between two or more variables.
Replication
The process of repeating a study to test whether the original findings can be consistently reproduced.
Multivariate Design
A research design configured to test associations involving more than two measured variables.
Longitudinal Design
A study in which the same variables are measured in the same sample of individuals at different points in time to help establish temporal precedence.
Cross-Sectional Correlation
In a longitudinal study, a correlation computed between two distinct variables that were measured at the exact same point in time.
Autocorrelation
In a longitudinal study, the correlation of a single variable with itself across two different time points to determine its consistency over time.
Cross-Lag Correlation
In a longitudinal design, a correlation between an earlier measurement of one variable and a later measurement of another variable, helping to evaluate temporal precedence.
Multiple Regression
A statistical technique used to compute the relationship between a predictor and a criterion variable while statistically controlling for one or more additional variables.
Criterion Variable
The primary outcome variable that researchers are most interested in understanding or predicting in a multiple-regression analysis (analogous to a dependent variable).
Predictor Variable
A variable included in a multiple-regression analysis to explain variance in the criterion variable (analogous to an independent variable).
Beta (β)
A standardized regression coefficient indicating the direction and strength of the relationship between a predictor and criterion variable while holding all other predictors in the model constant.
Mediator
An intermediate variable that serves as the underlying mechanism explaining why or how two variables are related.
Independent Variable
In an experiment, the variable that is intentionally manipulated by the researcher, comprising two or more levels or conditions.
Dependent Variable
In an experiment, the outcome variable that is measured to assess the effect of manipulating the independent variable.
Control Variable
A potential third variable that a researcher intentionally holds constant across all experimental conditions to preserve internal validity.
Comparison Group
A group in an experiment whose level on the independent variable differs meaningfully from that of the treatment group, allowing for the evaluation of covariance.
Systematic Variability
An experimental problem in which the levels of a confounding variable fluctuate predictably in step with the levels of the independent variable.
Unsystematic Variability
Random or haphazard variability within a study whose levels fluctuate independently of experimental group membership.
Design Confound
An experimenter's error in which an unintended variable varies systematically along with the independent variable, serving as an alternative explanation for the outcome.
Selection Effect
A threat to internal validity in independent-groups designs occurring when participants assigned to one condition systematically differ from those assigned to another condition.
Random Assignment
The use of a random process to allocate participants into experimental conditions, ensuring every participant has an equal chance of being assigned to any group.
Matched Groups
An assignment procedure in which participants are matched on a key measured characteristic and then randomly distributed across experimental conditions.
Independent-Groups Design
An experimental setup in which different groups of participants are placed into different levels of the independent variable, with each person experiencing only one condition.
Within-Groups Design
An experimental setup in which each participant is exposed to all levels of the independent variable.
Posttest-Only Design
An independent-groups experimental design where participants are tested on the dependent variable only once, following exposure to the independent variable.
Pretest/Posttest Design
An independent-groups design where participants are tested on the dependent variable twice: once prior to and once following exposure to the independent variable.
Repeated-Measures Design
A within-groups experimental design in which participants are measured on the dependent variable multiple times, each measurement following exposure to a different level of the independent variable.
Concurrent-Measures Design
A within-groups experimental design in which participants are exposed to all levels of an independent variable roughly at the same time, followed by a single measurement.
Order Effects
A threat to internal validity in within-groups designs where the sequence in which conditions are presented alters participant behavior or responses.
Counterbalancing
The practice of presenting experimental conditions in varied sequences across participants to prevent order effects from confounding results.
Demand Characteristics
Subtle cues in an experimental context that allow participants to guess the study hypothesis and adjust their behavior accordingly.
Manipulation Check
An extra dependent variable incorporated into an experiment to confirm that the experimental manipulation actually influenced the intended construct.
Pilot Study
A small-scale study executed before the primary investigation to assess and confirm the effectiveness of an experimental manipulation or protocol.
Cohen's d
A standardized metric of effect size that reflects how far apart two group means are relative to their pooled standard deviation.
One-Group Pretest/Posttest Design
A flawed research design where a single group of participants is measured on a pretest, given a treatment, and then measured on a posttest without a comparison group.
History Threat
A threat to internal validity occurring when an external event unrelated to the study happens between pretest and posttest, systematically influencing the results.
Maturation Threat
A threat to internal validity where changes in the dependent variable occur naturally or spontaneously over time rather than because of the experimental treatment.
Regression to the Mean
A statistical phenomenon whereby an unusually extreme measurement obtained at Time 1 tends to naturally score closer to the group mean upon retesting at Time 2.
Attrition Threat
A threat to internal validity occurring when participant dropouts between pretest and posttest are non-random or systematic (such as extreme scorers quitting).
Testing Threat
A threat to internal validity in which repeated exposure to a test leads to performance changes due to practice effects or fatigue.
Instrumentation Threat
A threat to internal validity occurring when the instrument or researcher measuring the dependent variable changes calibration, behavior, or standards from pretest to posttest.
Observer Bias
A threat to internal validity in which researchers' expectations or hypotheses unconsciously influence how they record, code, or interpret participant responses.
Placebo Effect
A phenomenon in which participants experience genuine improvement simply because they believe they are receiving an active, effective treatment.
Double-Blind Study
An experimental protocol in which neither the participants nor the research staff interacting with them know who is receiving the treatment versus the control.
Masked Design
An experimental procedure where participants are aware of their assigned group, but the observers measuring the dependent variable remain unaware.
Double-Blind Placebo Control Study
An experiment comparing a true treatment group to an inert placebo group where neither the researchers nor the participants know who belongs to which group.
Null Effect
A research outcome showing no statistically significant difference or association between the levels of the independent variable and the dependent variable.
Ceiling Effect
A situation where a dependent measure is so easy that nearly all participants score at or near the top possible value, obscuring true between-group differences.
Floor Effect
A situation where a dependent measure is so difficult that nearly all participants score at or near the bottom possible value, obscuring true between-group differences.
Measurement Error
Any extraneous factor that inflates or deflates an individual's observed score relative to their true score on a dependent variable.
Situation Noise
Environmental distractions (such as sights, smells, or ambient sounds) that inflate within-groups variability and obscure genuine differences between experimental conditions.
Statistical Power
The probability that a study will obtain a statistically significant result when an independent variable genuinely exerts an effect in the population.