Displaying similar documents to “On Kaiman Filtering, Posterior Mode Estimation and Fisher Scoring in Dynamic Exponential Family Regression.”

Time series analysis: recursive methods and their modifications for time series with outliers and missing observations.

Tomás Cipra, Asunción Rubio, José Trujillo (1991)

Extracta Mathematicae

Similarity:

The recursive methods are popular in time series analysis since they are computationally efficient and flexible enough to treat various changes in character of data. This paper gives a survey of the most important type of these methods including their classification and relationships existing among them. Special attention is devoted to i) robustification of some recursive methods, capable of facing outliers in time series, and ii) modifications of recursive methods for time series with...

Computational aspects of robust Holt-Winters smoothing based on M -estimation

Christophe Croux, Sarah Gelper, Roland Fried (2008)

Applications of Mathematics

Similarity:

To obtain a robust version of exponential and Holt-Winters smoothing the idea of M -estimation can be used. The difficulty is the formulation of an easy-to-use recursive formula for its computation. A first attempt was made by Cipra (Robust exponential smoothing, J. Forecast. (1992), 57–69). The recursive formulation presented there, however, is unstable. In this paper, a new recursive computing scheme is proposed. A simulation study illustrates that the new recursions result in smaller...