st: multiple responses additional info

["ann fitzmaurice" <annfitz@btinternet.com>]

Please see below

I can generate a table using
tabstat v1_*, by (name) stats (sum n)

is there any way of adding a statistics so that it counts the number of 1's
within each group (name), and then can I test if the patterns are
different??


    name |      v1_2      v1_3      v1_4      v1_5      v1_6
---------+--------------------------------------------------
       1 |         1         1         0         0         1
         |         1         1         1         1         1
---------+--------------------------------------------------
       2 |         0         1         0         0         1
         |         1         1         1         1         1
---------+--------------------------------------------------
       3 |         0         0         1         0         0
         |         1         1         1         1         1
---------+--------------------------------------------------
       4 |         0         1         1         0         1
         |         1         1         1         1         1
---------+--------------------------------------------------
   Total |         1         3         2         0         3
         |         4         4         4         4         4
-----------------------------------------------------------
Hi 

Can anyone suggest what analyses that I can do with multiple responses as
shown in the table below:

name   v1_1          v1_2           v1_3            v1_4          v1_5
v1_6
1.00	1.00	   1.00	      .00	            .00   	1.00
98.00
2.00	.00	1.00	     .00		.00	1.00	98.00
3.00	.00	.00	    1.00		.00	.00	1.00
4.00	.00	1.00	1.00		.00	1.00	98.00
						
						
Have 6  variable v1_v6 coded 1, (yes) 0 (no) and 98 (not applicable) which
were asked of four people

The dataset is in wide format with 7 columns and 4 rows

What I would like to do is to test if the pattern of positive (coded 1)
responses is different between the four responders , 

To do this I think I have to count the number of yes?s and total number of
responses (yes / no) and then calculate percentage

After this what test would I use ??    would it be a chi test??????

Also can this be done using immediate in stata

Thanks
Ann







*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/