>From a somewhat ill-designed education experiment, I have categorical data
with two between subject variables and one within subject variable. Since it
is categorical (essentially counts of answer choices on multiple choice
questions), I'm looking for some chi-squared method.
I know how to generalize Pearson's chi-square for n between subject
dimensions, and I know McNemar's test for a within subject factor, but how
can I mix these methods?
Also, I need to be able to do post-hoc comparisons in all dimensions.
Any ideas or references?
I'd be happy to share more details as needed.
Here is a sample from the data. All together, there are 366 subjects. There
are 4 levels of Test_no (1,2,3,4), Ans1 and Ans2 are the within subject
measures, and there are 8 levels of Ans* (cor, SE, CP, CPSE, FoM, FoMSE,
zero, other).
Thanks, again!
SID Test_No Ans1 Ans2
1 1 other other
2 1 CPSE CP
3 1 other other
4 1 SE SE
5 1 FoM CP
6 1 FoM CPSE
7 2 cor cor
8 2 cor cor
9 2 cor cor
10 2 CPSE CPSE
11 2 cor cor
12 2 CPSE cor
13 2 CPSE cor
14 3 CP cor
15 3 cor cor
16 3 CP FoM
17 3 cor cor
18 3 cor cor
19 3 zero other
20 3 SE CP
21 3 SE FoM
22 3 CP CP
23 4 zero SE
24 4 CPSE cor
25 4 SE cor
26 4 CP CP
27 4 SE cor
28 4 SE SE
29 4 CPSE cor
I would like to be able to compare different answers within a test, and how
answers are different for different tests.
--
View this message in context:
http://www.nabble.com/analysis-of-categorical-data-tp25140738p25140738.html
Sent from the R help mailing list archive at Nabble.com.
