Experimental Designs Overview

A method of selecting participants for a study where each individual has an equal chance of being chosen. This helps ensure the sample accurately reflects the broader population.

The extent to which the findings of a study can be generalized to other people, settings, and times.

Repeating a study using different procedures or operational definitions of the key variables.

A threat to external validity where the sample is not representative of the population.

A threat to external validity where participants are more likely to be motivated or have certain traits.

When simply taking a pretest alters participants' subsequent behavior, making it difficult to isolate the true effect of the treatment.

A research design that measures participants before and after a manipulation, but lacks a control group for comparison.

A group in an experiment that doesn't receive the treatment, serving as a baseline for comparison with the treatment group.

Statistical methods used to make inferences about a larger population based on a sample of data.

Statistics that summarize and describe the characteristics of a data set, without making inferences about a population.

A statement claiming there is no effect of the independent variable on the dependent variable.

A statement proposing that the independent variable has an effect on the dependent variable.

The likelihood of observing a specific outcome if the null hypothesis were true, helping researchers decide if their results are statistically significant.

A type of experiment focusing on one individual (or a small group) where cause-and-effect relationships are examined by manipulating a treatment and observing its impact.

A single-case design where a treatment is introduced, then removed to see if the behavior reverts back to its initial state.

Observing behavior across different individuals, settings, or behaviors before and after introducing the manipulation.

A research design that tries to approximate a true experiment, but without random assignment to groups, making it harder to establish cause-and-effect.

A quasi-experimental design where a group is exposed to a treatment and then measured, without a control group or pretest.

A quasi-experimental design that compares an experimental group with a separate control group, but groups are not randomly assigned.

A quasi-experimental design that combines a pre- and post-test measurement with an experimental and a nonequivalent control group.

Inferential statistics allows us to make conclusions about a population based on data from a sample. It uses probability to determine if the difference between groups is due to a real effect or just random chance.

A Type I error occurs when we reject the null hypothesis, but it is actually true. We conclude there is a difference when there really isn't.

A Type II error occurs when we fail to reject the null hypothesis, even though it is false. We miss a real difference between groups.

The null hypothesis states that there is no difference or relationship between the groups being studied. It represents the 'status quo' we are trying to disprove.

Effect size quantifies the strength of a relationship or difference between groups. It tells us how meaningful the finding is, regardless of sample size.

The t-test is used to compare the means of two groups. It determines if there is a statistically significant difference between the groups.

An F-test is used to compare the variances of two or more groups. It tells us if the amount of spread within the groups is significantly different.

ANOVA is a broader statistical test that compares means across multiple groups. It's like a more general version of a t-test for more than two groups.

A research design that involves two baseline (A) periods and two treatment (B) periods. It allows for the observation of two reversals in behavior when the treatment is introduced and removed. This helps strengthen conclusions about the effectiveness of the treatment.

Ending an ABAB design with a treatment phase is beneficial because the last observation shows the effect of the treatment, rather than a withdrawal period. This strengthens the evidence for the treatment's impact on behavior.

A type of multiple baseline design where the same behavior is measured in different settings (e.g., home and work). The treatment is introduced at different times for each setting, allowing researchers to see if the behavior change is specific to the manipulation.

A type of multiple baseline design that measures several different behaviors of a single participant over time. The treatment is introduced at different times for each behavior, allowing researchers to see if the change in behavior is specific to the manipulation.

A type of multiple baseline design that measures the behavior of several participants over time. The treatment is introduced at different points in time for each subject, allowing researchers to see if the change in behavior is specific to the manipulation.

Factors that can influence the outcome of a study, making it difficult to determine if the observed effect is truly due to the manipulation. These threats can weaken the conclusions drawn from the study.

A statistical phenomenon where extreme scores tend to move closer to the average score on subsequent measurements. This can be a threat to internal validity in one-group pretest-posttest designs, as it can appear that the treatment is causing the change, when it's actually just a statistical effect.

The deviation of group means from the grand mean (overall average). It reflects the spread of group means and indicates how different the groups are from each other.

A theoretical probability distribution that shows the likelihood of obtaining different sample statistics if the null hypothesis is true. It helps determine how likely your results are if there's no real effect.

A research study that aims to precisely replicate the procedures of a previous study. It helps to confirm the consistency and reliability of the original findings.

Making broad conclusions about a population based on studies involving only one gender, which may not hold true for the entire population.

Repeating a research study to confirm its findings and assess the reliability of its results. It helps overcome generalization problems and builds confidence in the validity of the original study.