Test
Mann Whitney Test
Este test tiene tipos de pregunta que se abren en el reproductor de siempre.
Preguntas del test (21)
1We are looking for [blank_start]differences[blank_end] in groups
- Adifferences
2What sort of data do you have?
- Ainterval and ratio
- BNominal
- COrdinal
3What am I doing?
- Arepeated measures
- BIndependent groups
4Is my data normally distributed?
- AParametric
- BNon-parametric
5non-parametric equivalent to the [blank_start]independent[blank_end] t-test
- Aindependent
6Under the null hypothesis the distributions of both groups are equal, so that the probability of an observation from one population (X) exceeding the observation from the second population (Y) equals the probability of an observation from Y exceeding an observation from X, that is there is symmetry between populations with respect to probability of random decision drawing of a larger population.
- AVerdadero
- BFalso
7For a Mann-Whitney test we assume:
What the alternative hypothesis the probability of an observation from one population (X) exceeding an observation from the second population (Y) (after exclusion of outliers) is more than 0.5
The alternative may also be stated in terms of a one-sided test for example:
P (X >Y) + 0.5 P(X=Y) >0.5
Or P(X=Y) < 0.05- AVerdadero
- BFalso
8The test involves the calculation of a statistic, usually called [blank_start]U[blank_end], whose distribution under the null hypothesis is known.
- AU
9Method one:
For small samples a direct method is recommended. It is very quick, and gives an insight into the meaning of the U statistic.
Choose the sample for which the ranks seem to be smaller (The only reason to do this is to make computation easier). Call this "sample 1," and call the other sample "sample 2."
Taking each observation in sample 1, count the number of observations in sample 2 that have a smaller rank (count a half for any that are equal to it). The sum of these counts is [blank_start]U[blank_end].- AU
10The Mann Whitney U test . . .
- AIs a parametric test to compare the mean of two independent groups
- BIs a non-parametric test to compare the median of two independent groups
- CIs a non-parametric test to compare the medians of two related groups
- DIs a parametric test to compare the means of two related groups
- EIs a non-parametric test used to correlate nominal variables
11The Mann Whitney U test is . . .
- AA useful way of dealing with data that does not meet the assumptions of parametric tests
- BHas high power to detect significant effects
- CDoes not have very high power to detect significant effects
- DShould never be used as parametric tests are more powerful
- ENone of the above
12When can you use the Mann Whitney U test?
- ATo compare the median scores of men and women on a verbal reasoning task, when the data are not normally distributed and samples do not show homogeneity of variance
- BWhen you want to see if age is associated with height
- CWhen you want to compare the number of pull ups before and after 4 weeks of bootcamp training
- DWhen you want to compare the frequency of cats who danced when trained with food as opposed to being trained with affection
13What data can the Mann Whitney U test be used to analyse?
- AInterval or ratio data that is normally distributed and for more than one group shows homogeneity of variance
- BInterval or ratio data that is not normally distributed and for more than one group does not show homogeneity of variance
- CNominal or ordinal level data
- DFrequency data
- ECategorical variables
14The SPSS output below shows the results of a Kolmogorov Smirnov test, carried out on Beck Depression Inventory scores of clubbers who either took Ecstasy or Alcohol at the club the night before.
The results of the K-S test suggest . . . .
- AThat the data are normally distributed
- BIt is appropriate to carry out an independent samples t-test
- CThe data only for the Alcohol group is not normally distributed
- DThe data only for the ecstasy group is not normally distributed
- EIt is appropriate to carry out a Mann Whitney U test on this data
15The SPSS output below shows the results of a Mann Whitney U test comparing the Beck Depression Inventory scores of clubbers who either took Ecstasy or Alcohol the night before.
Referring to the SPSS output below, how many people took part in each condition?
- A20
- B10
- C40
- D30
- ENone of the above
16Referring to the SPSS outputs above, what is the correct way of reporting the results of the Mann Whitney U test?
- AU=88, z=12.2, p<0.01
- BU=-1.29, z=8.8, p=.194
- CU=33, z=88, p=.194
- DU=33, z=-1.298, p=.194
17Referring to the SPSS output below, what can you conclude from the results of the Mann Whitney U test?
- AThere was a significant difference in the BDI scores of clubbers who ingested ecstasy as compared to alcohol
- BThere was no significant difference in the BDI scores of clubbers who ingested ecstasy as compared to alcohol
- CResults should be interpreted with caution as the data should have been analysed using parametric tests
- DClubbers who ingested alcohol had significantly higher BDI scores than clubbers who ingested ecstasy
18What should you always include when reporting the results of a Mann Whitney U test?
- AThe Mann Whitney U statistic
- BThe z score
- CThe number of participants
19What does the Z value in the Mann Whitney U test tell you?
- Apeople have a standardized measure of the size of the effect that can be compared with other studies
- BIt tells you whether the data is normally distributed
- CYou can infer how many participants where in the study
- DIt tells you about the homogenity of variance in the data
- EAll of the above
20R ([blank_start]effect size[blank_end]) = Z/[blank_start]square root[blank_end] N
- Asquare root
- Beffect size
21Effect size
Large: >[blank_start]0.5[blank_end]
Medium: >[blank_start]0.3[blank_end]
Small: <[blank_start]0.3[blank_end]- A0.3
- B0.3
- C0.5
Información
- Descripción
- MY DEGREE Test sobre Mann Whitney Test , creado por Toyin Oshodi el 11/03/2017.
- Autor
- Toyin Oshodi
- Idioma
- English
- Visitas
- 0
- Etiquetas
- Valoración
- Aún sin valoraciones Valora este test