s-news
[Top] [All Lists]

Help with modelling

To: s-news@lists.biostat.wustl.edu
Subject: Help with modelling
From: Tristan Lorino <tristan.lorino@lcpc.fr>
Date: Thu, 11 May 2006 15:45:37 +0200
Organization: LCPC
Reply-to: Tristan Lorino <tristan.lorino@lcpc.fr>
Hi,

Here is my question, concerning statistical theory... I have repeated
measures on road sections, corresponding to cracks survey. The dependent 
variable
is, for each section, the couple (age, length of crack). There is also 
covariates (types
of pavement, climatic covariates, etc.).

The aim is 1. to highlight the role of the covariates into the
cracking process, 2. to predict the evolution of the road, and ideally,
to be able to determine the crack level at a given age.

The evolution of the crack over time is non linear (slow deterioration
in the first years, acceleration in the last years with an asymptot).
The adjacent sections belonging to a same road are correlated, because
of the coavraites they share (same pavement structure, same
climat...).

Another level of complexity is the introduction of maintenance:
a sort of "renewal" process...

Any suggestion?

Thank you,
Tristan Lorino

-- 
Laboratoire Central des Ponts et Chaussées
[Division ESAR ? Section AGR]
Route de Bouaye BP 4129
44341 Bouguenais Cedex
France
Tél 33 (0)2 40 84 56 18
Fax 33 (0)2 40 84 59 92


<Prev in Thread] Current Thread [Next in Thread>
  • Help with modelling, Tristan Lorino <=