A New Recursive Estimation Method for Single Input Single Output Models

Ouakasse, Abdelhamid; Mélard, Guy

doi:10.1111/jtsa.12210

Cited by 2 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…0 2 Parameter estimation of ARMAX models is established on the Melard's algorism (A. Ouakasse & G. Melared, 2009). Further, finding suitable orders of p and q in the ARMA p q ( , ) model can be assisted by plotting the partialautocorrelation functions for determining p, and similarly using the autocorrelation functions for determining q.…”

Section: Autoregressive: Moving Average Exogenous Inputs Modelmentioning

confidence: 99%

The Bullwhip Effect

Yebabe

2014

International Journal of Applied Logistics

View full text Add to dashboard Cite

Supply chain management is a fledgling science which concerned with synchronization of both material flow and information flow by integrating companies for a common objective to meet the requirements of the end customer. Bullwhip effect is an important research topic of the supply chain management. The Bullwhip effect is precarious to both short and long run competitive advantage, the dependability sustainability advantage of the chain. This paper proposes to show the impact of the Bullwhip effect on the supply chain using experimentally simulated data from Beer distribution game. The game represents a simple supply chain which consists of factory, distributor, wholesaler and retailer. The paper used empirical models of ANOVA, spectral density estimation, ARMAX and Cochrane- Orcutt autoregression. The result of the study prevails that when we quantify the impact of the Bullwhip effect to different actors of the supply chain with respect of inventory holding cost and stock-out case it is found that different cost implications. When quantifying the impact of the Bullwhip effect to the whole supply chain it is found that at least one of the competitive advantages of the chain is lost. When generalizing it the all the actors in the supply chain will suffer from the Bullwhip effect. The overall evidence from statistical causality analysis suggest that without proper both intra-organizational and inter-organizational coordination of the companies across the supply chain it is difficult to have effective and efficient customer relationship management, customer demand management and inventory management.

show abstract

Section: Autoregressive: Moving Average Exogenous Inputs Modelmentioning

confidence: 99%

The Bullwhip Effect

Yebabe

2014

International Journal of Applied Logistics

View full text Add to dashboard Cite

show abstract

“…For the treatment of the single-input single-output (SISO) models and the multiple-input singleoutput (MISO) models, several recent papers have discussed either the asymptotic Fisher information matrix (Klein and Mélard (1994b) and Klein and Mélard (2004)) or the exact Fisher information matrix (Klein, Mélard and Zahaf (1998), Klein and Mélard (1994a) and Zadrozny (1989Zadrozny ( , 1992)) but we have seen no indication of the approach used to estimate the parameters of these models. Ouakasse and Mélard (2014) have proposed a complicated recursive estimation method for SISO models where the recurrence for updating the Hessian is avoided but the recurrence for updating the estimator makes use of the Fisher information matrix. In this paper, we describe a simple iterative algorithm for estimating the parameters of a MISO model given by the equation (1) where is the endogenous variable, are the exogenous variables, is the backshift operator such that , are normally and independently random variables with mean zero and constant variance and is the delay of transmission of influence between the th exogenous variable and the endogenous variable, or the delay parameter which represents the number of complete time intervals before a change in begins to have an effect on , is the vector of parameters to be estimated where…”

Section: Introductionmentioning

confidence: 99%

A New Iterative Algorithm for Estimating Parameters and Orders of Multiple-Input Single-Output Time Series Models

Kiseta

Mbambe

Sotazo

et al. 2021

ISR

View full text Add to dashboard Cite

In this paper, we propose a new iterative algorithm for estimating the parameters and orders of a multiple-input single-output (MISO) time series model. This algorithm is based on a method suggested by Hannan and Rissanen (1982) for estimating an ARMA model. The key is the use of pseudo-linear regression techniques to derive the iterative nonlinear least-squares estimators by using the Gauss-Newton algorithm. Simulation results are presented to compare the new algorithm with the exact maximum likelihood method (EML) and the generalized least squares (GLS) method proposed by Sabiti (1997).

show abstract

A New Recursive Estimation Method for Single Input Single Output Models

Cited by 2 publications

References 41 publications

The Bullwhip Effect

The Bullwhip Effect

A New Iterative Algorithm for Estimating Parameters and Orders of Multiple-Input Single-Output Time Series Models

Contact Info

Product

Resources

About