Research Methods- Test of difference: Mann-Whitney and Wilcoxon Flashcards
What is the Mann-Whitney test used for in this example?
The Mann-Whitney test is used to look for a difference between two groups of employers based on their rating of whether a candidate (who had experienced schizophrenia) was suitable for a job interview. The design is unrelated, and the level of measurement is ordinal, as data is based on scores converted to ranks.
What is the aim of the study on the effects of labelling in schizophrenia?
The study aims to determine if there is a difference in someone’s perceived employability based on whether they had been diagnosed with schizophrenia in the past. Employers were shown an application form and asked to rate the candidate’s likelihood of being called for an interview on a scale of 1-20.
What is the alternative hypothesis in the Mann-Whitney study?
The alternative hypothesis is that there is a difference in ratings for suitability for an interview based on whether a job applicant is described as having been diagnosed with schizophrenia (Group A) or not (Group B). (non-directional, two-tailed)
What is the null hypothesis in the Mann-Whitney study?
The null hypothesis is that there is no difference in ratings for suitability for an interview based on whether a job applicant is described as having been diagnosed with schizophrenia (Group A) or not (Group B).
What is Step 1 in the Mann-Whitney analysis?
Step 1 involves ranking the ratings from both Groups A and B together. The lowest number has a rank of 1, and tied ranks are given the mean rank. The sum of the ranks for Group A (R₁) and Group B (R₂) is then calculated.
What is Step 2 in the Mann-Whitney analysis?
Step 2 involves calculating the smaller value of U, which is U = R₁ - [N₁(N₁ + 1)]/2. In this example, U = 65.5 - [10 × (10 + 1)]/2 = 10.5.
What is Step 3 in the Mann-Whitney analysis?
Step 3 involves comparing the calculated value of U (10.5) to the critical value of U (17) for a two-tailed test at the 0.05 level where N₁ = 10 and N₂ = 8. Since the calculated value is less than the critical value, the result is significant (p ≤ 0.05).
What conclusion is drawn from the Mann-Whitney analysis?
The null hypothesis is rejected, and the alternative hypothesis is accepted: There is a difference in ratings for suitability for an interview based on whether a job applicant is described as having been diagnosed with schizophrenia (Group A) or not (Group B) (p ≤ 0.05).
What is the Wilcoxon test used for in this example?
The Wilcoxon test is used to look for a difference in anger scores before and after using an anger management programme. The design is repeated measures (related), and the data is ordinal, based on a subjective self-report questionnaire.
What is the aim of the study on anger management?
The study aims to assess the effectiveness of a new anger management programme. Twenty teenagers in a young offenders institute completed an anger questionnaire before and after eight intensive sessions of anger management, and their scores were compared.
What is the alternative hypothesis in the Wilcoxon study?
The alternative hypothesis is that there is a difference in young offenders’ scores on an anger questionnaire before and after treatment. (non-directional, two-tailed)
What is the null hypothesis in the Wilcoxon study?
The null hypothesis is that there is no difference in young offenders’ scores on an anger questionnaire before and after treatment.
What is Step 1 in the Wilcoxon analysis?
Step 1 involves calculating the difference between the two sets of data (before and after treatment) and ranking the differences, ignoring the signs. If the difference is zero, the data is not included in the ranking.
What is Step 2 in the Wilcoxon analysis?
Step 2 involves calculating the value of T, which is the sum of the ranks of the less frequent sign. In this example, T = 9.
What is Step 3 in the Wilcoxon analysis?
Step 3 involves comparing the calculated value of T (9) to the critical value of T (8) for a two-tailed test at the 0.05 level when N = 10. Since the calculated value is more than the critical value, the result is not significant (p > 0.05).
What conclusion is drawn from the Wilcoxon analysis?
The null hypothesis is accepted: There is no difference in young offenders’ scores on an anger questionnaire before and after treatment (p > 0.05). The alternative hypothesis is rejected at p ≤ 0.05.
Is the result of the Wilcoxon test significant?
No, the result is not significant because the calculated value of T (9) is more than the critical value of T (8) at the 0.05 level.
What conclusion can be drawn from the Wilcoxon study?
The conclusion is that there is no significant difference in young offenders’ anger scores before and after the anger management programme (p > 0.05).
