Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Need Help with Datamanagement and Survival analysis
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: Need Help with Datamanagement and Survival analysis
Date
Sun, 2 Dec 2012 10:33:38 +0000
You should show code that you typed, not paraphrase it.
Most crucially, the code you show makes no reference to previous
values (or to folllowing dates).
Prakash also misses this point in his reply to you.
bysort name (date) : gen tag = type[_n-1] == "Telephone" & type == "In-patient"
Now such observations can be selected by -if tag-
by name : egen flag = total(tag)
Now such _patients_ have positive values of -flag- and can be selected
by -if flag-.
Nick
On Sun, Dec 2, 2012 at 5:41 AM, Dudekula, Anwar <[email protected]> wrote:
> In the following dataset :
>
> Telephone : Is a phone call made by the patient.
> Office Visit: is a clinicl visit
> Inpatient: is admission to hospital
>
> I am trying to find a set of patients in whom a Telephone(Type of Encounter)is followed by Inpatient(Type of Encounter) without any interspread Office Visit
>
> My stata code was keep if (Type of Encounter=="Telephone"|Type of Encounter=="Inpatient") but I got lot of observations with successive telephone calls followed by inpatien.
>
> I only want to see only those observations if a telephone is followed by Inpatient(event) or only telephone(censored) ; Is there a stata code for it .
>
> In next step, is there any stata macro to convert that to survival dataset format if failure= havig inpatient admission after telephone call in observed timeperiod(year 2011)
>
> Pt Name Date Type of Encounter
> --------------------------------------
> pt x 4-Apr-11 Office Visit
> pt x 20-May-11 Telephone
> pt x 12-Jun-11 Inpatient
> pt x 15-Jun-11 Office Visit
> pt x 8-Aug-11 Inpatient
> pt y 12-Jul-11 Telephone
> pt y 13-Jul-11 Telephone
> pt y 14-Jul-11 Telephone
> pt y 15-Jul-11 Telephone
> pt y 16-Jul-11 Telephone
> pt y 17-Jul-11 Telephone
> pt y 19-Jul-11 Inpatient
> pt y 4-Aug-11 Office Visit
> pt y 4-Sep-11 Telephone
*
* 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/