Data: Statistical Tests Flashcards
What are the different tests
- Sign test
- Chi-squared test
- Mann-Whitney U test
- Wilcoxon Matched Pairs Signed Ranks Test
- Spearman’s Rho test
How would you know which test is appropriate to use
1) based on level of measurement (nominal, ordinal….)
2) based on the experimental design used (only relevant for experiments)
3) based on what it is testing for (difference or relationship)
—> remember: No I Can C MRS Will Smith
What’s the appropriate test to use if:
1) Nominal data
2) testing for difference
3) Repeated measures design
Sign-test
How do you calculate the critical value for a Chi-squared test
- find out direction of hypothesis (one/two-tailed), level of significance (the probability, e.g. p<0.05), and number of participants
- then calculate the Df (degrees of freedom), by doing number of cells DIVIDED by (rows-1) x (columns-1)
- then use this to find the critical value on a critical values table
How do you calculate the critical value for a Spearman’s ranked test
- find out direction of hypothesis (one/two-tailed), level of significance (the probability, e.g. p<0.05), and number of participants
- using the number of participants, find the critical value on a critical values table
How do you calculate the critical value for a Mann-Whitney U test
- find out direction of hypothesis (one/two-tailed), level of significance (the probability, e.g. p<0.05), and number of participants in both conditions
- N1 (for IV1) and N2 (for IV2)
- then use these 2 values to find the critical value on the critical values table
How do you calculate the critical value for a Sign test
- find out direction of hypothesis (one/two-tailed), level of significance (the probability, e.g. p<0.05), and total number of differences
- e.g. you work this out as shown in image
- then use this value to find the critical value on the critical values table
How do you calculate the critical value for a Wilcoxon test
- find out direction of hypothesis (one/two-tailed), level of significance (the probability, e.g. p<0.05), and total number of differences
- e.g. you work this out as shown in image
- then use this value to find the critical value on the critical values table
If the observed value is greater than or equal to the critical value, which statistical test has an observed significance
- spearman’s
- chi-squared
If the critical value is greater than or equal to the observed, which statistical test has an observed significance
- Mann-Whitney U
- Sign test
- Wilcoxon
- There will be a positive correlation between a person’s height, and their reaction time. Participants: 7 men. Observed value: +0.699
- give a model answer for which hypothesis do you accept/reject
- the results are not significant because the observed value of +0.699 was smaller than the critical value of 0.714 for a one-tailed test at p<0.05
- this means that we accept the null hypothesis and reject the alternative hypothesis because…
- there is no significant difference in a person’s height and their reaction time, and the results are likely to be due to chance