click below
click below
Normal Size Small Size show me how
t-tests and ANOVA
| Definition | Term |
|---|---|
| Involved using two sample means to make an inference about two population means | Independent -Samples t-test |
| Conditions that need to be met for the tests to be valid | Assumptions |
| Populations have equal variances | Homogeneity |
| If some assumptions are violated... | the test is no longer valid |
| Minimal impact of heterogeneous variance, assuming equal | Robust (not a big deal) |
| s^2/largest/ s^2 smallest | Fmax |
| t= observed difference between sample means / standard error of the difference between the means | Formula for Independent t-test |
| Paired-samples t) Used to examine change in scores within individuals across repeated assessments *same subjects twice* | Dependent samples t-test |
| observed difference between 1st and 2nd and variable mean / standard error of the difference between the means | Formula for Dependent t-test |
| The number of values in your data that are free to vary after certain rules are applied | Degrees of freedom |
| A measure of how strong or big the relationship or difference is | Effect size |
| Hypothesis test that allows you to examine mean differences between two or more groups on a numeric DV | ANOVA |
| A categorical independent variable that designates group | Factor |
| Individual conditions or categories WITHIN the factor | Level |
| Having one factor | one way anova |
| If levels are between subjects | one-way between subjects |
| One factor with levels within subject | one-way within subjects |
| More than one factor | Factorial |
| Assumes that the error is normally distributed | Normality |
| Breaking down the total variation | Partioning the variance |
| Represents the sum of squared deviations between one group means and the grand mean | SSb |
| The mean of all scores in all the groups combined on the dependent variable | Grand mean |
| Represents the sum of the squared deviations between individual scores and their respective group means on the dependent variable | SSe (sum of squares errors) |