Flashcards
RMP 3
Cards in this deck (16)
- 1Null hypothesis significance testingcomputing a test statistic that represents the alternative hypothesis (effect exists) and calculate the probability that we would get a value as big as the one we have if the null hypothesis were true. If this probability is less than .05 we reject the idea that there is no effect and say we have a statistically significant finding.
- 2Cohen's deffect size measure: the difference between two means divided by the standard deviation of the mean of the control group
- 3Pearson's correlation coefficient: reffect size measure
- 4Mann-Whitney U test use:when data is ranked (ordinal) and/or you planned to do a between groups t-test but violated assumptions
- 5ordinal datanumerical scores that exist on an arbitrary numerical scale where the exact numerical quantity has no significance other than relevance to other points
- 6Mann-Whitney u definitionNon-parametric equivalent of independent t-test. works by looking at differences in ranked positions of scores in 2 different groups aka Wilcoxon's rank-sum
- 7How to do Mann-Whitney ULook at row labelled Asympototic sig, or exact sig for small sample. Value < .05 then two conditions are significantly different
- 8Kruskal-Wallis test:non-parametric equivalent to ANOVA. used for testing whether samples originate from the same distribution. Used for comparing two or more independent samples of equal or different sample sizes.
- 9Kruskal-Wallis cram sam:use when you have one nominal variable and one ranked variable. Compares several condition when different participants take part in each condition and the resulting data have unusual cases or violate assumptions.
- 10What Kruskal-Wallis does:Extends Mann-Whitney when there are more than 2 groups.
Ranks order all scores
put scores back into groups and sum the ranks
compare the summed ranks between the groups - 11Independent Samples t-testparametric test for interval data. Used to examine the differences between means derived from two independent groups. AKa two experimental conditions and different participants assigned to each group
- 12explanation of tt = variance between groups divided by variance within groups
- 13Paired-samples t-testused when there are two experimental conditions and the same participants took part in both conditions of the experiment
- 14Between-groups t-testused when there is one IV, two conditions (or levels within an IV), participants are assigned to either one or the other levels.
- 15Assumptions of independent samples t-testdata must be on an interval or ratio scale. data must be normally distributed. homogeneity of variance
- 16repeated measures testparametric (repeated measures or within groups t-test) non-parametric (Wilcoxon test)
Information
- Description
- Flashcards on RMP 3, created by James Rowland on 29/12/2015.
- Created by
- James Rowland
- Views
- 0
- Rating