Airport pavement missing data management and imputation with stochastic multiple imputation model

Abstract

In practice, missing data in pavement condition databases have been one of the most prevalent problems in airport pavement management systems. Missing data present problems in pavement performance analysis and uncertainties in pavement management decision making. A number of data imputation approaches are available for handling missing data. This paper examines the limitations of the conventional data imputation methods and proposes a stochastic multiple imputation (MI) approach to overcome major limitations associated with conventional data imputation methods. A case study is presented to appraise the effectiveness of the proposed approach against three conventional data imputation methods, namely, substitution by mean, substitution by interpolation, and substitution by regression methods. The roughness and friction data of a 4-km-long runway pavement and the roughness data of a 4-km-long taxiway pavement were considered in the study. The effectiveness of auxiliary variables in data imputation models was also demonstrated. Results from the performance appraisal indicated that the proposed stochastic MI method yielded the smallest errors for the roughness as well as friction data. Furthermore, the substitution by mean method resulted in imputed values with the highest amount of deviations from the observed values, followed by the substitution by regression method, and the substitution by interpolation method. Therefore, it is concluded that the proposed stochastic MI method outperformed conventional methods in handling missing runway and taxiway pavement roughness and friction data and provides an effective approach to impute missing data required in an airport pavement management system.