Simulation-based inference for simultaneous processes on regular lattices

作者: Xavier De Luna , Marc G. Genton

DOI: 10.1023/A:1014830401806

关键词: AlgorithmSimulation basedArtificial intelligenceIndirect InferenceInferenceMonte Carlo methodRobust statisticsFocus (optics)Component (UML)Machine learningMaximum likelihoodMathematics

摘要: The article proposes a simulation-based inferential method for simultaneous processes defined on regular lattice. focus is spatio-temporal with component, that such contemporaneous spatial neighbors are potential explanatory variables in the model. new has advantage of being simpler to implement than maximum likelihood and allows us propose robust estimator. We give asymptotic properties, present Monte Carlo study an illustrative example.

参考文章(25)
Alain Monfort, Christian Gourieroux, Simulation-based econometric methods ,(1996)
Kurt Brännäs, Xavier De Luna, Generalized method of moment and indirect estimation of the ARasMA model Computational statistics (Zeitschrift). ,vol. 13, pp. 485- 494 ,(1998)
H.T. Kiiveri, FITTING SPATIAL CORRELATION MODELS: APPROXIMATING A LIKELIHOOD APPROXIMATION Australian & New Zealand Journal of Statistics. ,vol. 34, pp. 497- 512 ,(1992) , 10.1111/J.1467-842X.1992.TB01065.X
R. Douglas Martin, Victor J. Yohai, Influence Functionals for Time Series Annals of Statistics. ,vol. 14, pp. 781- 818 ,(1986) , 10.1214/AOS/1176350027
Frank R. Hampel, The Influence Curve and Its Role in Robust Estimation Journal of the American Statistical Association. ,vol. 69, pp. 383- 393 ,(1974) , 10.1080/01621459.1974.10482962
H. Kunsch, Infinitesimal Robustness for Autoregressive Processes Annals of Statistics. ,vol. 12, pp. 843- 863 ,(1984) , 10.1214/AOS/1176346706
Elvezio M. Ronchetti, Peter J. Rousseeuw, Werner A. Stahel, Frank R. Hampel, Robust statistics: the approach based on influence functions ,(1986)
Peter J. Huber, Finite Sample Breakdown of $M$- and $P$-Estimators Annals of Statistics. ,vol. 12, pp. 119- 126 ,(1984) , 10.1214/AOS/1176346396