Prediction of Bridge Component Ratings Using Ordinal Logistic Regression Model

Abstract

Prediction of bridge component condition is fundamental for well-informed decisions regarding the maintenance, repair, and rehabilitation (MRR) of highway bridges. The National Bridge Inventory (NBI) condition rating is a major source of bridge condition data in the United States. In this study, a type of generalized linear model (GLM), the ordinal logistic statistical model, is presented and compared with the traditional regression model. The proposed model is evaluated in terms of reliability (the ability of a model to accurately predict bridge component ratings or the agreement between predictions and actual observations) and model fitness. Five criteria were used for evaluation and comparison: prediction error, bias, accuracy, out-of-range forecasts, Akaike’s Information Criteria (AIC), and log likelihood (LL). In this study, an external validation procedure was developed to quantitatively compare the forecasting power of the models for highway bridge component deterioration. The GLM method described in this study allows modeling ordinal and categorical dependent variable and shows slightly but significantly better model fitness and prediction performance than traditional regression model.

Evaluation of the Factors and Strategies for Water Infrastructure Project Delivery in South Africa

“…Ordinal regression models were used to assess the relative influence of the various factors on the project delivery and the plausible strategic measures, which would improve the situation. The ordinal regression model is generally used to forecast the behavior of the ordinal dependent variable (whose values exist on an arbitrary scale) with a set of independent variables [31][32][33]. The dependent variable should be the order response category variable and the independent variables may be categorical or continuous variables.…”

“…The dependent variable should be the order response category variable and the independent variables may be categorical or continuous variables. It focuses on the strength of the relationships between two or more variables and assumes a dependence or causal relationship between one or more independent variables and one dependent variable [31][32][33]. Furthermore, ordinal regression models offer the advantage to make full use of ranked data [34][35][36].…”

The Restriction Factors and Mechanism Analysis Model Design of the Commercial Serious Disease Insurance in Connection with Serious Disease Insurance

“…Secondly, each explanatory variable was introduced into the model one by one, and the rationality of the logistic regression model was judged by the significant level of the variables. After the introduction of a new variable, if the variable-2 log-likelihood value is less than the results in the previous step and the pAfter introducing a new variable, if the logarithmic likelihood value of the variable -2 is less than the result of the previous step, and the p value is less than 1%, it indicates that the explanatory variable has a significant correlation with the explanatory variable "on the basis that the major disease insurance is willing to join the commercial major disease insurance," and the logistic regression model "on the basis that the major disease insurance is willing to join the commercial major disease insurance" is reasonable [16][17][18][19][20]. Table 2 shows the regression results in the final step, and the odds ratio reflects the explanatory variables screening process and regression system, the final model includes "health status," "sex," "per capita income," "gender," "age," "education," and "number of children."…”

LR-BCA: Label Ranking for Bridge Condition Assessment

“…By comparing and analyzing the performance of two models under various conditions, it concluded that the artificial neural network was more suitable for the bridge condition assessment. Lu et al [34] proposed an ordinal logistic regression algorithm for bridge condition assessment.…”