Chapter 17: Nonparamatric Tests- Kriskul-Wallis Test Flashcards Preview

Statistics > Chapter 17: Nonparamatric Tests- Kriskul-Wallis Test > Flashcards

Flashcards in Chapter 17: Nonparamatric Tests- Kriskul-Wallis Test Deck (8):

The kruskal wallis test is used in place of the _____ when there is an extreme violation of at least one assumption of the ____. Requires at least __ scaling of DV. (or ___ and ___ is required but not met)

-one way anova
-interval, ratio


What are the assumptions for the kruskal wallis test?

1. at least ordinal
2. at least 5 in each group


Null hypothesis for this test?

u1=u2=u3 etc



- at least one mean of the groups is different from at least one of the other groups mean.


What statistic is being calculated for this test?

Hobt = [ 12/N(N+1)][E(Ri)^2/ni]-3(N+1)
** the summation part occurs for each group in the experiment!


How are the scores ranked in this test?

- you rank across all conditions together as if all in one condition!
- no negative ranks
L> Ri= sum of ranks in that condition
L> do not use absolute values.... sign means something!


In nonparametric tests such as this one...what is analysis looking at in terms of scores etc?

- its looking at the ranks not the actual scores!
L> a reason why they are less powerful than parametric tests....


How does this test get done in SPSS?

1. enter data just you would with an ANOVA. (raw data is all put into one column and group variables are assigned to identify the group)
2. Analysis---> nonparametric-->legacy dialogues---> K-independent sample
3. DV goes into test list
L> group goes to grouping variable ox
L> defined: min=1, x=max-3 (groups)