2 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 2 / 2
Yayın On the sensitivity of desirability functions for multiresponse optimization(American Institute of Mathematical Sciences, 2008-11) Aksezer, Sezgin ÇağlarDesirability functions have been one of the most important multiresponse optimization technique since the early eighties. Main reasons for this popularity might be counted as the convenience of the implementation of the method and it's availability in many experimental design software packages. Technique itself involves somehow subjective parameters such as the importance coefficients between response characteristics that are used to calculate overall desirability, weights used in determining the shape of each individual response and the size of the specification band of the response. However, the impact of these sensitive parameters on the solution set is mostly uninvestigated. This paper proposes a procedure to analyze the sensitivity of the important characteristic parameters of desirability functions and their impact on pareto-optimal solution set. The proposed procedure uses the experimental design tools on the solution space and estimates a prediction equation on the overall desirability to identify the sensitive parameters. For illustration, a classical desirability example is selected from the literature and results are given along with the discussion.Yayın Assessing the efficiency of hospitals operating under a unique owner: a DEA application in the presence of missing data(Inderscience Publishers, 2010-05) Aksezer, Sezgin Çağlar; Benneyan, James C.Originally developed in the late 1970s to assess the efficiency of comparable operating units, Data Envelopment Analysis (DEA) has since been used in a variety of contexts. Although incomplete data sets are often encountered in practice, the best approach in such situations is unclear in general. This paper explores methods such as multiple imputation, bootstrapping and smart dummy variable replacement, borrowed from similar missing data problems in regression analysis. Each missing data method is tested on a library of DEA problems that are gathered from the DEA literature. These problems are selected in such a way as to represent a thorough cross-section of problem sizes (small, medium, large) and types (type of DEA model, number of decision-making units, number of inputs, number of outputs, etc.). The results are illustrated by comparing the solutions of complete data sets against the simulated versions of the same data sets with missing data. The sensitivity of each method on the efficiency scores and ranking of the decision-making units is presented.
