Infrastructure distress models predict the initiation and progression of distress on a facility over time as a function of age, design characteristics, environmental factors, etc. Cracking, potholing, and rutting are several examples of facility distress. A large number of structural zeros on a facility condition survey data set indicates an absence of distress at the time of observation. Most distress progression models are simple regression models that are estimated using the sample of observations for which distress has begun. The selectivity bias due to the nonrandom nature of the estimation sample used renders the models statistically erroneous. This paper applies two econometric methods to predict joint discrete-continuous models of infrastructure distress initiation and progression while correcting for selectivity bias. Heckman's procedure and the full information maximum likelihood method are the two methods applied. An empirical case study demonstrates these techniques for the case of highway-pavement-cracking models. Selectivity bias can be very serious in these models.


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00711559
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Sep 19 1995 12:00AM