Research Methods: Non-Experimental & Quasi-Experimental

Research where variables cannot be directly manipulated, often used to study relationships between factors.

Studies involving a treatment or intervention, but participants are not randomly assigned to groups, leading to potential biases.

A study where a variable is measured before and after a treatment, but only in one group, making it difficult to rule out alternative explanations.

A research design using multiple measurements over time, interrupted by a treatment. It helps to establish trends, but alternative explanations still exist.

A quasi-experiment that compares two groups (one treated, one not) without random assignment. It's susceptible to group differences.

The average of a dataset, susceptible to distortion by outliers.

The middle value in a sorted dataset, resistant to outliers.

The value that appears most frequently in a dataset.

A visual representation of the relationship between two or more variables, often used to identify trends and patterns.

A data point that is significantly different from other data points in a dataset. They can influence the mean and skew results.

A variable that is manipulated or changed by the researcher in an experiment.

The variable that is measured in an experiment.

The process of assigning participants to different experimental groups in a way that ensures equal chance to each condition.

A group in an experiment that does not receive the treatment or intervention, used as a baseline for comparison.

A fake treatment or substance that resembles the real treatment but has no active ingredients.

A research design involving multiple measurements over time, both before and after an intervention, in two or more groups that are not equivalent.

A research design where one group receives a treatment and another doesn't. Both groups are measured before and after the treatment. After the initial measurements, the groups switch roles: the control group gets the treatment, while the original treatment group continues.

Similar to switching replication design, but the treatment is removed from the first group instead of switched. It involves a measurement of the dependent variable after the removal to see if the change is reversed.

Observing behaviors in their natural environment without interference. It can be done secretly or openly.

Participants behave unnaturally because they are aware they are being observed.

Observing behaviors by becoming an active participant in the environment or group being studied.

Observing behaviors with specific parameters set by the researcher. May or may not occur in a natural setting.

Manipulating a variable in a natural setting to observe its effects.

An organized system of categories and examples used to identify and document behaviors during observation.

A coding system used to identify keywords, phrases, or ideas in a text or other data.

An experimental design with two or more independent variables.

Each independent variable in a factorial design. Each factor must have at least two levels.

When two or more variables collectively influence an outcome. It moderates the association between another variable and the outcome.

The effect of a single independent variable on the dependent variable while controlling for other independent variables.

A factorial design that combines within-subjects and between-subjects approaches. At least one independent variable is manipulated between subjects, and at least one is manipulated within subjects.

A research design where each participant is assigned to only one experimental condition. This helps to avoid order effects but may require a larger sample size.

A research design where each participant experiences all experimental conditions. This can be more efficient but risks order effects.

A confound that arises when the order of experimental conditions influences the dependent variable. These can include practice effects, carry-over effects, and contrast effects.

A type of order effect where the experience of one condition influences the participant's performance on a subsequent condition even though they are different.

A type of order effect where participants' experience with the different conditions influences their perception of the study. This can reveal the study hypothesis.

A technique used to control for order effects by creating different sequences of experimental conditions and presenting them randomly to participants.

A type of counterbalancing where each participant completes every possible order of conditions.

A type of counterbalancing where the order of conditions is randomly determined for each participant. It's a more practical approach than full counterbalancing.

A specific type of counterbalancing where every condition appears in each ordinal position only once. It creates a matrix where each condition appears once in each row and column.

The process of repeating a study to see if the same results are obtained. This helps to increase confidence in the original findings.

A type of replication where the original study is recreated as closely as possible to see if the results are consistent.

The use of shortcuts by researchers that can distort the accuracy of study findings. Examples include p-hacking, selective reporting, and misleading conclusions.

A type of QRP where researchers manipulate statistical analyses to get a significant result, even if the data doesn't actually support it.

The tendency for studies with positive results to be more likely to be published than those with null results, which can create a distorted view of the field.

A movement towards more transparent and accountable scientific practices, including pre-registration of studies, sharing materials and data, and publishing null findings.

A systematic process of gathering information through observation and experience. This forms the basis of the scientific method.

A type of research question that can be answered by systematically observing the world.