Statistics for the Behavioral Sciences

Flashcards covering key terms and concepts from the lecture on statistics for behavioral sciences.

Independent Sample

Participants in each group or sample are unrelated and are observed once in only one sample.

Related Sample

Participants in each group or sample are related, observed in more than one group or matched based on common characteristics.

Repeated-Measures Design

A research design where the same participants are observed in each sample.

Pre-Post Design

A design in which researchers measure a dependent variable for participants before and after a treatment.

Matched-Pairs Design

A design where participants are selected and matched based on common characteristics, observing two groups.

Difference Score

The score obtained by subtracting two related scores.

Related-Samples t Test

A statistical procedure used to test hypotheses concerning two related samples with unknown population variance.

Effect Size

A measure of the magnitude of a phenomenon; Cohen's d, Eta-Squared, and Omega-Squared are measures for related-samples t test.

Cohen’s d

The most common measure of effect size used for the t test, measuring the number of standard deviations the mean difference scores shifted.

Degrees of Freedom

In the related-samples t test, calculated by subtracting one from the number of pairs of observations.

Null Hypothesis (H0)

The hypothesis that there is no mean difference in the sample being tested.

Alternative Hypothesis (H1)

The hypothesis that there is a mean difference in the sample being tested.

Standard Error

An estimate of the variability of a sample mean compared to the true population mean.

Power of a Test

The probability of correctly rejecting the null hypothesis when it is false.

APA Style Reporting

Guidelines for reporting the t statistic, df, and p value in the results of a related-samples t test.