Dear Statalist
I have a small dataset (n=51 with many missing values). There are about
17 variables, all categorical with 6 to 10 categories in each (although
some categories can be sensibly combined). I also have a list of 24
comparisons that the researcher would like to look at.
It seems to me the only viable approach is to simply display the data in
a way that highlights interesting features. True?
So I would like to know what commands I should be investigating, whether
built-in or user-written.
As an example, here is one tabulation from the dataset:
Use policy | Knowledge of PEG
guide | Poor Adequate Above ave | Total
-----------+---------------------------------+----------
1 | 0 6 2 | 8
2 | 6 2 1 | 9
3 | 0 3 1 | 4
4 | 0 7 1 | 8
5 | 0 7 3 | 10
-----------+---------------------------------+----------
Total | 6 25 8 | 39
Knowledge was actually a 5-point scale from None to Excellent.
Use policy guide is 3 categories of No (don't need to; no guide exists;
guide not suitable) and 2 categories of Yes.
I think the interesting result is that all the people with poor
knowledge claimed that no guide exists.
The table can show this (and of course will be better with proper
labelling), but I am sure there are better ways to present this.
-scatter- with -jitter- gives me a graph that I think is a good starting
point. But then adding categorical labels to the axes becomes a hassle.
I expect -scatter- is not the right tool -- what more appropriate
commands exist?
Or is my whole approach to this dataset wrong?
Tim
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
