nep-cmp New Economics Papers
on Computational Economics
Issue of 2013‒05‒19
eight papers chosen by
Stan Miles
Thompson Rivers University

  1. Parallel Sequential Monte Carlo for Efficient Density Combination: The Deco Matlab Toolbox By Roberto Casarin; Stefano Grassi; Francesco Ravazzolo; Herman K. van Dijk
  2. Comparison of Two Yield Management Strategies for Cloud Service Providers By Mohammad Mahdi Kashef; Azamat Uzbekov; Jorn Altmann; Matthias Hovestadt
  3. Would a euro's depreciation improve the French economy? By Riccardo Magnani; Luca Piccoli; Martine Carré; Amedeo Spadaro
  4. The R Package MitISEM: Mixture of Student-t Distributions using Importance Sampling Weighted Expectation Maximization for Efficient and Robust Simulation By Nalan Basturk; Lennart Hoogerheide; Anne Opschoor; Herman K. van Dijk
  5. Pruning in Perturbation DSGE Models - Guidance from Nonlinear Moving Average Approximations By Hong Lan; Alexander Meyer-Gohde; ;
  6. The structure of a machine-built forecasting system By Jiaqi Chen; Michael L. Tindall
  7. Monte Carlo approximation to optimal investment By L C G Rogers; Pawel Zaczkowski
  8. Retirement Incentives in Belgium: Estimations and Simulations Using SHARE Data By Jousten, Alain; Lefèbvre, Mathieu

  1. By: Roberto Casarin (University Ca' Foscari of Venice and GRETA); Stefano Grassi (CREATES, Aarhus University); Francesco Ravazzolo (Norges Bank, and BI Norwegian Business School); Herman K. van Dijk (Erasmus University Rotterdam, and VU University Amsterdam)
    Abstract: This paper presents the Matlab package DeCo (Density Combination) which is based on the paper by Billio et al. (2013) where a constructive Bayesian approach is presented for combining predictive densities originating from different models or other sources of information. The combination weights are time-varying and may depend on past predictive forecasting performances and other learning mechanisms. The core algorithm is the function DeCo which applies banks of parallel Sequential Monte Carlo algorithms to filter the time-varying combination weights. The DeCo procedure has been implemented both for standard CPU computing and for Graphical Process Unit (GPU) parallel computing. For the GPU implementation we use the Matlab parallel computing toolbox and show how to use General Purposes GPU computing almost effortless. This GPU implementation comes with a speed up of the execution time up to seventy times compared to a standard CPU Matlab implementation on a multicore CPU. We show the use of the package and the computational gain of the GPU version, through some simulation experiments and empirical applications.
    Keywords: Density Forecast Combination, Sequential Monte Carlo, Parallel Computing, GPU, Matlab
    JEL: C11 C15 C53 E37
    Date: 2013–04–09
    URL: http://d.repec.org/n?u=RePEc:dgr:uvatin:2013055&r=cmp
  2. By: Mohammad Mahdi Kashef (TEMEP, College of Engineering, Seoul National University); Azamat Uzbekov (TEMEP, College of Engineering, Seoul National University); Jorn Altmann (TEMEP, College of Engineering, Seoul National University); Matthias Hovestadt (Department of Computer Science, Hanover University of Applied Sciences)
    Abstract: Several Cloud computing business models have been developed and implemented, including dynamic pricing schemes. This paper extends the known concepts of revenue management to the specific case of Cloud computing from two perspectives. First, we propose system architecture for Cloud service providers for combining demand-based pricing and scheduling. Second, a comparison of two yield management methods for cloud computing has been compared: Limited Discount Period Algorithm and VM Reservation Level Algorithm. By taking advantage of demand estimation, the two algorithms find the optimum number of VMs that are sold at full price and the optimum time period before the allocation when the prices should change. Simulation results show that both yield management methods outperform static pricing models and the algorithms perform differently considering the deviation of demand.
    Keywords: Cloud Computing, Revenue Management, Pricing Strategy, Autonomic Resource Management.
    JEL: C61 C63 D81 L86 M15
    Date: 2013–05
    URL: http://d.repec.org/n?u=RePEc:snv:dp2009:2013103&r=cmp
  3. By: Riccardo Magnani (CEPN - Université Paris XIII and CEPII); Luca Piccoli (Universitat de les Illes Balears); Martine Carré (LEDa - Université Paris-Dauphine); Amedeo Spadaro (Universitat de les Illes Balears)
    Abstract: In this paper, we use a Micro-Macro model to evaluate the effects of a euro's depreciation on the French economy, both at the macro and micro level. Our Micro-Macro model consists of a Microsimulation model that includes an arithmetical model for the French fiscal system and two behavioral models used to simulate the effects on consumption behavior and labor supply, and a multisectoral CGE model which simulates the macroeconomic effects of a reform or a shock. The integration of the two models is made using an iterative (or sequential) approach. We find that a 10% euro's depreciation stimulates the aggregate demand by increasing exports and reducing imports which increases production and reduces the unemployment rate in the economy. At the individual level, we find that the macroeconomic shock reduces poverty and, to a lesser extent, income inequality. In particular, the decrease in the equilibrium wage, determined in the macro model, slightly reduces the available income for people who have already a job, while the reduction in the level of unemployment permits to some individuals to find a job, substantially increasing their income and, in many cases, bringing them out of poverty.
    Keywords: Exchange rates; Microsimulation; CGE models
    JEL: F40 C63 C68
    Date: 2013
    URL: http://d.repec.org/n?u=RePEc:ubi:deawps:60&r=cmp
  4. By: Nalan Basturk (Erasmus University Rotterdam); Lennart Hoogerheide (VU University Amsterdam); Anne Opschoor (Erasmus University Rotterdam); Herman K. van Dijk (EUR & VU)
    Abstract: This paper presents the R package MitISEM, which provides an automatic and flexible method to approximate a non-elliptical target density using adaptive mixtures of Student-t densities, where only a kernel of the target density is required. The approximation can be used as a candidate density in Importance Sampling or Metropolis Hastings methods for Bayesian inference on model parameters and probabilities. The package provides also an extended MitISEM algorithm, ‘sequential MitISEM’, which substantially decreases the computational time when the target density has to be approximated for increasing data samples. This occurs when the posterior distribution is updated with new observations and/or when one computes model probabilities using predictive likelihoods. We illustrate the MitISEM algorithm using three canonical statistical and econometric models that are characterized by several types of non-elliptical posterior shapes and that describe well-known data patterns in econometrics and finance. We show that the candidate distribution obtained by MitISEM outperforms those obtained by ‘naive’ approximations in terms of numerical efficiency. Further, the MitISEM approach can be used for Bayesian model comparison, using the predictive likelihoods.
    Keywords: finite mixtures, Student-t distributions, Importance Sampling, MCMC, Metropolis-Hastings algorithm, Expectation Maximization, Bayesian inference, R software
    JEL: C11 C15
    Date: 2012–09–20
    URL: http://d.repec.org/n?u=RePEc:dgr:uvatin:2012096&r=cmp
  5. By: Hong Lan; Alexander Meyer-Gohde; ;
    Abstract: We derive recursive representations of nonlinear moving average (NLMA) perturbations of DSGE models. As the stability of higher order NLMA representations follows directly from stability at first order, these recursive representations provide rigorous support for the practice of pruning that is becoming widespread. Our recursive representation differs from pruned perturbations in that it centers the approximation and its coefficients at the approximation of the stochastic steady state consistent with the order of approximation. We compare our algorithm with six different pruning algorithms at second and third order, documenting the differences between these six algorithms and standard (non pruned) state space perturbations at first, second, and third order in a unified notation compatible with the popular software package Dynare. While our third order algorithm is the most accurate, the gains over two alternate algorithms are modest, suggesting that this choice is unlikely to be a potential source of error.
    Keywords: Perturbation; DSGE; nonlinear; pruning
    JEL: C52 C63 E30
    Date: 2013–05
    URL: http://d.repec.org/n?u=RePEc:hum:wpaper:sfb649dp2013-024&r=cmp
  6. By: Jiaqi Chen; Michael L. Tindall
    Abstract: This paper describes the structure of a rule-based econometric forecasting system designed to produce multi-equation econometric models. The paper describes the functioning of a working system which builds the econometric forecasting equation for each series submitted and produces forecasts of the series. The system employs information criteria and cross validation in the equation building process, and it uses Bayesian model averaging to combine forecasts of individual series. The system outperforms standard benchmarks for a variety of national economic datasets.
    Keywords: Econometrics
    Date: 2013
    URL: http://d.repec.org/n?u=RePEc:fip:feddop:1:x:1&r=cmp
  7. By: L C G Rogers; Pawel Zaczkowski
    Abstract: This paper sets up a methodology for approximately solving optimal investment problems using duality methods combined with Monte Carlo simulations. In particular, we show how to tackle high dimensional problems in incomplete markets, where traditional methods fail due to the curse of dimensionality.
    Date: 2013–05
    URL: http://d.repec.org/n?u=RePEc:arx:papers:1305.3433&r=cmp
  8. By: Jousten, Alain (University of Liège); Lefèbvre, Mathieu (CREPP, Université de Liège)
    Abstract: The paper studies retirement behavior of wage‐earners in Belgium – for the first time using rich survey data to explore retirement incentives as faced by individuals. Specifically, we use SHARE data to estimate a model à la Stock and Wise (1990). Exploring the longitudinal nature of SHARELIFE, we construct measures of financial and non‐financial incentive. Our analysis explicitly takes into account the different take‐up rates of the various early retirement exit paths across time and ages. The results show that financial incentives play a strong role. Health and education also matter, as does regional variation – though the latter in an unexpected way. A set of policy simulations illustrate the scope and also the limits associated with selective parametric reforms.
    Keywords: pensions, social security, disability, early retirement, unemployment, labor force participation
    JEL: H55 J21 J26 J14
    Date: 2013–05
    URL: http://d.repec.org/n?u=RePEc:iza:izadps:dp7387&r=cmp

This nep-cmp issue is ©2013 by Stan Miles. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at http://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.