Faculty of Economics and Business Administration Publications Database

Further improvements in the calculation of Censored Quantile Regressions

Volume: 235
Number: 5
Pages: 1429 - 1445
Month: January
Link External Source: Online Version
Year: 2011
Keywords: Censored quantile regression; Genetic algorithms; Threshold accepting; Simulated annealing; Global optimization

Censored Quantile Regressions of Powell (1984, 1986) are very powerful inferencing tools in economics and engineering. As the calculation of censored quantile regressions involves minimizing a nonconvex and nondifferentiable function, global optimization techniques can be the only breakthroughs. The first implementation of a global optimization technique, namely Threshold Accepting of Fitzenberger and Winker (1998, 2007), is challenged by the Genetic Algorithm (GA) in this paper. The results show that the GA provides substantial improvements over Threshold Accepting for cases with randomly distributed censoring points.