Statalist The Stata Listserver


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

st: Further to Extrapolating records using results from -sts list-


From   "David Winter" <d.l.winter@bham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Further to Extrapolating records using results from -sts list-
Date   Fri, 19 May 2006 17:12:29 +0100

Regarding the request for assistance below

"This is an expansion on a previous theme, for which I am indebted to Austin Nichols for advice.
..
..
To recap:  I have a dataset of 1341 observations of cancer patients having a subsequent malignancy.  I have calculated the period at risk in proportions of a year for each observation 
..
I need to extract the values from a life table.  I need to 'insert' blank records for the missing records (e.g. 40, 43 and 46) and extrapolate the relevant data.  Any suggestions would be welcome.
..
"

Having been able to spend some time with Statalist FAQs I now realise that (a) I am working with 'time series data', (b) an easy resolution can be obtained by using -tsset- and -tsfill- and (c) there is a whole manual devoted to time series analysis.

I believe there is an expression that goes "a little knowledge can be dangerous" - an addendum should perhaps be "especially in the absence of appropriate language to describe any problem arising from using that knowledge". My previous message could have been condensed into a couple of sentences and I could have answered it myself.  Apologies.

Dave 

*
*   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