Endüstri Mühendisliği Bölümü Yayın Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/279
Browse
2 results
Search Results
Article Citation - WoS: 20Citation - Scopus: 22Shipment Consolidation With Two Demand Classes: Rationing the Dispatch Capacity(Elsevier Science Bv, 2018) Erenay, Fatih Safa; Bookbinder, James H.; Satir, BenhurWe analyze the problem faced by a logistics provider that dispatches shipment orders (parcels or larger packages) of two order classes, viz. expedited and regular. Shipment orders arrive according to a compound Poisson process for each class. Upon an arrival, the logistics provider may continue consolidating arriving orders by paying a holding cost. Alternatively, the provider may dispatch, at a fixed cost, a vehicle containing (a portion of) the load consolidated so far. In addition, the provider must specify the composition of each dispatch by allocating (rationing) the volume of the vehicle between expedited and regular shipment orders. We model this problem as a continuous-time Markov Decision Process and minimize the expected discounted total cost. We prove the existence of quantity-based optimal threshold policies under particular conditions. We also structurally analyze the thresholds of these optimal policies. Based on these structural properties, we develop an efficient solution approach for large problem instances which are difficult to solve using the conventional policy-iteration method. For two real-life applications, we show that the quantity-based threshold policies derived using the proposed approach outperform the time policies used in practice. (C) 2018 Elsevier B.V. All rights reserved.Article Citation - WoS: 8Citation - Scopus: 12Estimating Parameters of a Multiple Autoregressive Model by the Modified Maximum Likelihood Method(Elsevier, 2010) Bayrak, Oezlem Tuerker; Akkaya, Aysen D.We consider a multiple autoregressive model with non-normal error distributions, the latter being more prevalent in practice than the usually assumed normal distribution. Since the maximum likelihood equations have convergence problems (Puthenpura and Sinha, 1986) [11], we work Out modified maximum likelihood equations by expressing the maximum likelihood equations in terms of ordered residuals and linearizing intractable nonlinear functions (Tiku and Suresh, 1992) [8]. The solutions, called modified maximum estimators, are explicit functions of sample observations and therefore easy to compute. They are under some very general regularity conditions asymptotically unbiased and efficient (Vaughan and Tiku, 2000) [4]. We show that for small sample sizes, they have negligible bias and are considerably more efficient than the traditional least Squares estimators. We show that Our estimators are robust to plausible deviations from an assumed distribution and are therefore enormously advantageous as compared to the least squares estimation. We give a real life example. (C) 2009 Elsevier B.V. All rights reserved.