Curve Forecasting by Functional Autoregression

By Vladislav Kargin, A. Onatski. 2008

142 citations recorded by the source corpus.

Subfields: Applied Mathematics, Economics and Econometrics, Finance

View Paper: https://www.semanticscholar.org/paper/16fbba0c3e101517163dd2b421ea815d573c9055

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Mathematics

In Economics and Econometrics

In Finance

Citations in the corpus

Functional linear regression with functional response (2017, methodology): “Our model is also related to the functional autoregressive (FAR) model studied by Bosq (2000), Kargin and Onatski (2008), and Aue, Norinho, and Hormann (2015), among others.”
Determining the order of the functional autoregressive model (2013, methodology): “The FAR(1) model has been applied and studied in many contexts, we list Besse et al. (2000), Damon and Guillas (2002), Antoniadis and Sapatinas (2003), Antoniadis et al. (2006), Kargin and Onatski (2008), Horváth et al. (2010) and Didericksen et al. (2012), among many others.”
Prediction of functional ARMA processes with an application to traffic data (2016, background): “The class of functional AR ( p ) processes is an exception, where explicit prediction formulas have been given (e.g. Bosq [3], Chapter 3, and Kargin and Onatski [4]).”
Weakly dependent functional data (2010, background): “Kargin and Onatski [38] show that a basis different than the eigenfunctions vk is optimal for prediction with a functional AR(1) model.”
Portmanteau Test of Independence for Functional Observations (2007, methodology): “Out of many possible directional alternatives, we focus on the ARH(1) (where H stands for Hilbert space) model of Bosq (2000), which has been used in several interesting applications (see, e.g., Laukaitis and Račkauskas 2002; Fernández de Castro, Guillas, and Gonzáles Manteiga 2005; Kargin and Onats”
A FUNCTIONAL VERSION OF THE ARCH MODEL (2011, methodology): “They observed that the parameter estimation based method worked as well or better than the more complex method developed by Kargin and Onatski [22] for prediction in autoregressive functional models.”
Rainbow Plots, Bagplots, and Boxplots for Functional Data (2010, background): “This is in accordance with the analysis of López-Pintado and Romo (2009), who inferred that the functional depth approach does not take shape outliers into account, and thus could potentially result in false detection.”
White Noise Testing and Model Diagnostic Checking for Functional Time Series (2016, methodology): “Various nonparametric and prediction methods for the FAR(1) models have been developed, and numerous applications have been found; see Besse et al. (2000), Laukaitis and Rac̆kauskas (2002), Antoniadis and Sapatinas (2003), Fernández de Castroa et al. (2005), Kargin and Onatski (2008), among others.”
Extensions of some classical methods in change point analysis (2014, methodology): “The model is used for prediction in Kargin and Onatski (2008).”
Estimation of the mean of functional time series and a two‐sample problem (2011, methodology): “Except in the case of independent observations in each of the two samples, these quantities cannot be computed by using existing software because D̂ is not an empirical covariance operator of a functional IID sample. We have developed an algorithmic procedure to compute âi and λ̂i which for brevity ”
Testing stationarity of functional time series (2014, methodology): “The main model employed for such series has been the functional autoregressive model of order one, which has received a great deal of attention, see Bosq (2000), Antoniadis and Sapatinas (2003), Antoniadis et al. (2006) and Kargin and Onatski (2008), among many others.”
A Plug‐in Bandwidth Selection Procedure for Long‐Run Covariance Estimation with Stationary Functional Time Series (2016, background): “…where ‰.f /.t/ D Z 1 0 .t; s/f .s/ds; (9) and ¹ `; ` 2 Zº is a sequence of i.i.d. random elements of L2Œ0; 1 satisfying Ek 0k2 < 1; see Chapter 3 of Bosq (2000) for a rigorous mathematical development, and Besse et al. (2000) and Kargin and Onatski (2008) for some novel applications of this model.”