Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: R:R: Was( Help)


From   "Carlo Lazzaro" <carlo.lazzaro@tin.it>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: R:R: Was( Help)
Date   Wed, 9 Sep 2009 18:36:00 +0200

Dear Delly,
After -stset- your data (please, invoke -help stset- from within Stata. My
release is 9.2/SE):

stset Risk_time, failure(Maintenance==1) 

Try: 

xi: streg age I.Inspection, d(weibull).

Where age is the age of the asset and I.Inspection is an indicator variable
created to plug in the right hand of Weibull regression model the 5-degree
ordered Inspection variable.

For more details on -xi- function, please invoke -help xi - from within
Stata).

Sorry I cannot be more helpful.
I do hope that Statalist stalwarts can chime in with better hints.

Kind Regards,
Carlo
-----Messaggio originale-----
Da: Dlamini, Delly [mailto:d.dlamini@cranfield.ac.uk] 
Inviato: mercoledì 9 settembre 2009 11.37
A: Carlo Lazzaro
Oggetto: RE: Help


Dear Carlo,

Many thanks for your response. The aim of my research is to build a model
that will determine water  distribution asset remaining life - based on its
historical perofrmance, condition and current age. Available asset
historical performance data is mainly its maintenance history, which
represent its failure history. Condition is determined by physical asset
inspection and a grade (1- 5) given, with 1 being goood condition and 5
being very bad condition. The use of the Weibull formula is a specific
requirement of the research.

The inputs are asset;
- Maintennace history data (failure data)
- Age
- Condition grades (1 - 5)
And use Weibull estimator.

The output; 
- Asset remaining life estimating model or formula 

Just wondering how to use all these factors together to create one model
that will determine the asset remaining life. And what other alternative
formula would be usefull, either than the Weibull.

Best regards
Delly





Dear Delly,
your problem might call for a regression model. However, to increase your
chances to get a reply from Statalisters, you should better describe in more
detail your dataset and the aim of your research endeavour. Unfortunately,
the current outline seems too poor.

Kind Regards,
Carlo

-----Messaggio originale-----
Da: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di Dlamini, Delly
Inviato: lunedì 7 settembre 2009 17.09
A: statalist@hsphsun2.harvard.edu
Oggetto: st: Help

Dear All

I wa swondering if anyone could help me. I am looking at building a modle to
predict asset remaining life by using asset performance historical data. Any
suggestions please.

Regards
Delly


*
*   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/



*
*   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/



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