Chapter 1 the study of collocations

Table 36.  Nemenyi's multiple comparisons tests of mean rank differences for 
the translation data - Group 1 
Types 
1  5  11 14 16 27 13 23 
1. Noun Prep 
 
---  .687 .237 .264 .039 1.044 1.186 2.26* 
5. Adj Prep 
   
--- .45 .423 .648 .357 1.87* 
2.95* 
11. SV(O) Prep O 
 
 
 
---  .027 .198 .807 1.42* 2.50* 
14. SVV-ing  
 
 
 
--- 
.225 
.78 
1.45* 
2.53* 
 
288

---

16. SVO Inf 
     
--- 
1.005 
1.225 
2.30* 
27. Verb Noun(creat) 
      
--- 
2.23* 
3.31* 
13. SV Inf 
       
--- 
1.083 
23. SV(O) Adverb          
--- 
*: Significant at the .05 level 
 
4.2.2.2.2  Friedman Test for the Translation Data - Group 2 
 
The results of the Friedman test for Group 2 show a significant 
difference in the students' mean accuracy of translation of the 6 types of 
collocation in the translation data (Friedman c
2
 (5, N = 6) = 74.279, p = .0001).  
Nemenyi's multiple comparisons tests based on Friedman's rank sums were 
performed on the data.  The results of these tests are summarised below in 
Table 37.  According to the results of the post-hoc analysis, only Type 11. SV(O) 
Prep O is significantly more accurately translated than all the other types.