Use of various deterioration models in the area of infrastructure management has provided decision makers with a vehicle for predicting future deterioration. This paper presents a methodology for predicting the likelihood that a particular infrastructure system is in a deficient state, using logistic regression models, a special case of linear regression. What distinguishes these two models is that the outcome variable in the logistic regression model is binary or dichotomous and assumes a Bernoulli distribution. The methodology is illustrated in a case study involving the evaluation of the local sewer system of Edmonton, Alta. Canada. Variables of age, diameter, material, waste type, and average depth of cover are modeled, using historical data, as factors contributing to deterioration of the sewer network. The outcome of this model does not produce a prediction of condition rating but rather uses historical inspection records to provide decision makers with a means of evaluating sewer sections for the planning of future scheduled inspection, based on the deficiency probability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.