Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
11 Cards in this Set
- Front
- Back
Parametric tests Data has characteristics (Parameters) Use when; data normally distributed shows equal variation within population (homogeneity) on an interval/ratio scale in which distances are equal |
Independent means T-test Dependent means T-test Pearsons R |
|
Non-Parametric tests Data has no characteristics (random?) Use when; data not normally distributed shows non equal variation (inhomogeneity) on an ordinal scale (ranks) |
Mann Whitney test Wilcoxon test Spearmans correlation Chi square test Kruskall Wallis test Friedman's ANOVA |
|
Mann Whitney test |
2 conditions separate group of subjects perform each appropriate when answers are in rating form |
|
Independent means T-test |
2 independent means no overlap between means (can only be one not other eg male/female) interval/ratio measurement scale numerical variable comparing averages from 2 means |
|
Wilcoxon test |
2 conditions both performed by same subjects each subject produces 2 scores (1percondition) |
|
Dependent means T-test |
1 dependent variable 1 categorical variable compares means of 2 related groups |
|
Pearson's R |
numerical data look at scatterplot first p value - tells whether to reject null hypothesis r value - gives indication of strength of relationship |
|
Spearmans correlation |
2 ordinal variables look at scatterplot first p value - tells whether to reject null hypothesis r value - gives indication of strength of relationship |
|
Chi-square test |
2 categorical variables organised into categories in a contingency table finds out degrees of freedom |
|
Kruskall Wallis test |
several independent groups of scores separate group of subjects perform each ranked data |
|
Friedman's ANOVA |
several dependent groups of scores each subject produces several scores ranked data |