Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: re counting missing


From   "Sergiy Radyakin" <Radyakin@aoek.uni-hannover.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: re counting missing
Date   Fri, 23 Feb 2007 08:30:43 +0100

Hello Richard,

first thing that comes into my mind (not quite a ready program, but quite straightforward):

1. create a small file with a single variable listing all possible class5 categories
2. -contract- your data to keep only unique ids
3. -cross- the two datasets. This will create all pairwise combinations of id and class5
4. -merge- this dataset with the original data by id and class5. you will have missings in t and number for some combinations
5. -sort- by id and t.
6. Now go with -by(id)- and -replace- number=0 if t==.
7. Go by(id) again and replace t=t[1]
Be sure not to switch steps 6 and 7
8. -gen- proportion=number/t

You might need to sort your data appropriately before merging if Stata complains.

Surely this can be done more efficiently.

Best regards,
Sergiy




----- Original Message ----- From: "Richard Hiscock" <rhiscock@netspace.net.au>
To: <statalist@hsphsun2.harvard.edu>
Sent: Friday, February 23, 2007 8:03 AM
Subject: st: re counting missing



In study of swallowing I have oesophageal pressures measured many times on each patient and within patients these are
coded into one of 5 contraction types. Subjects may have none up to all of the types of contraction & many or no pressures
measured for each type.
I wish to count the number of pressures readings measured for each type of contraction for each patient.
I have achieved this by (may be a bit long handed)
by id class5: gen n =_n

by id class5: gen number =_N

by id: gen t=_N

drop if n < number

gen proportion = number/t

format proportion %9.2f

list id group class5 t n number proportion if id <3

+--------------------------------------------------------+
| id group class5 t number propor~n |
|--------------------------------------------------------|
1. | 1 reflux Normal 20 12 0.60 |
2. | 1 reflux synchronous 20 6 0.30 |
3. | 1 reflux High amplitude 20 2 0.10 |
4. | 2 reflux synchronous 12 3 0.25 |
5. | 2 reflux High amplitude 12 1 0.08 |
6. | 2 reflux Failure 12 8 0.67 |


In examining the data I wish to look at the distribution of proportion within each class5 category. To do this I need

to record zero in the proportions for class5 categories that did not occur within a subject. For example for subject id 2

+--------------------------------------------------------+
| id group class5 t number propor~n |
|--------------------------------------------------------|
| 2 reflux Normal 12 0 0 |
| 2 reflux synchronous 12 3 0.25 |
| 2 reflux High amplitude 12 1 0.08 |
| 2 reflux Failure 12 8 0.67 |
| 2 reflux Ineffective 12 0 0 |

I am unable to achieve this.

Any help would be greatly appreciated.

Richard Hiscock



*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index