1/19
Vocabulary flashcards covering homoscedasticity, independence, Pearson correlation, and t-tests from the lecture notes.
Name | Mastery | Learn | Test | Matching | Spaced |
---|
No study sessions yet.
Homoscedasticity
Homogeneity of variance across the data; a common assumption for parametric models; tested with Levene’s test; p<.05 suggests unequal variances; if violated, use alternatives like Welch’s t-test.
Homoscedastic
Describes data with equal variances across the range of values in the relationship.
Heteroscedastic
Describes data where variances differ across the range of values in the relationship.
Levene’s test
A test for homogeneity of variance; uses an F statistic; p<.05 indicates violation of equal variances.
Welch’s t-test
A t-test variant used when variances are unequal; does not assume equal variances.
Independence
Observations are independent (unrelated; not affecting each other); an assumption for parametric tests; checked by logic, not by a formal test.
Paired t-test (dependent samples)
Two related samples (same participants) analyzed as a paired comparison.
Independent t-test (between-subjects)
Two groups from different participants compared.
Pearson correlation (r)
Measures linear association between two variables; requires linearity, normality, homoscedasticity, independence; at least one variable is continuous; r ranges from -1 to 1.
Linear relationship
A straight-line relationship between two variables; required to interpret Pearson correlation.
Scatterplot
Graph plotting two variables to visually assess linearity before running a correlation.
r = 0
Indicates no linear relationship between the two variables.
r = 1
Indicates a perfect positive linear relationship.
r = -1
Indicates a perfect negative linear relationship.
Cohen’s d
A measure of effect size for t-tests that expresses the magnitude of group differences.
Degrees of freedom (df)
A value used in test statistics (e.g., t(df), r(df)) reflecting sample size and model structure.
p-value
Probability of observing data as extreme as the sample under the null hypothesis; commonly p<.05 indicates statistical significance.
t-test
Statistical test to compare two means; assumes normality, independence, and homoscedasticity; DV is continuous; IV is dichotomous; can be paired or independent.
DV continuous
Dependent variable that is measured on a continuous scale.
IV dichotomous
Independent variable that has two categories (groups or time points).