Nonparametric Transfer Function Model

Jun Liu

Nonparametric Transfer Function Model

Information Systems & Analytics

Research output: Contribution to conference › Presentation

Abstract

A new approach is proposed to model the relationship between an output and some input time series, perturbed by correlated noise. The functional form of this relationship (the transfer function) is unknown but assumed to be smooth. We propose to model the transfer function by nonparametric smoothing methods and model the noise as an ARIMA process. By using nonparametric smoothing, the model is very flexible and can be used to model highly nonlinear relationships of unknown form; by modeling the noise, the correlation in the data is removed so the transfer function can be estimated more efficiently; additionally, the estimated ARIMA structure can be used to improve the forecasting performance. The estimation procedures are introduced and the asymptotic properties of the estimators are studied. The finite-sample properties of the estimators are studied by simulation and real-life examples.

Original language	American English
State	Published - Aug 10 2006
Event	Joint Statistical Meetings - Duration: Aug 3 2011 → …

Conference

Conference	Joint Statistical Meetings
Period	08/3/11 → …

Keywords

Nonparametric regression
Local polynomial regression
Regression splines
Nonlinear time series analysis
Transfer function model
ARIMA

DC Disciplines

Business

Cite this

@conference{ec482de72b864ed0b3c451f93344034e,

title = "Nonparametric Transfer Function Model",

abstract = " A new approach is proposed to model the relationship between an output and some input time series, perturbed by correlated noise. The functional form of this relationship (the transfer function) is unknown but assumed to be smooth. We propose to model the transfer function by nonparametric smoothing methods and model the noise as an ARIMA process. By using nonparametric smoothing, the model is very flexible and can be used to model highly nonlinear relationships of unknown form; by modeling the noise, the correlation in the data is removed so the transfer function can be estimated more efficiently; additionally, the estimated ARIMA structure can be used to improve the forecasting performance. The estimation procedures are introduced and the asymptotic properties of the estimators are studied. The finite-sample properties of the estimators are studied by simulation and real-life examples. ",

keywords = "Nonparametric regression, Local polynomial regression, Regression splines, Nonlinear time series analysis, Transfer function model, ARIMA",

author = "Jun Liu",

note = "This is the preliminary program for the 2006 Joint Statistical Meetings in Seattle, Washington.; Joint Statistical Meetings ; Conference date: 03-08-2011",

year = "2006",

month = aug,

day = "10",

language = "American English",

}

TY - CONF

T1 - Nonparametric Transfer Function Model

AU - Liu, Jun

N1 - This is the preliminary program for the 2006 Joint Statistical Meetings in Seattle, Washington.

PY - 2006/8/10

Y1 - 2006/8/10

N2 - A new approach is proposed to model the relationship between an output and some input time series, perturbed by correlated noise. The functional form of this relationship (the transfer function) is unknown but assumed to be smooth. We propose to model the transfer function by nonparametric smoothing methods and model the noise as an ARIMA process. By using nonparametric smoothing, the model is very flexible and can be used to model highly nonlinear relationships of unknown form; by modeling the noise, the correlation in the data is removed so the transfer function can be estimated more efficiently; additionally, the estimated ARIMA structure can be used to improve the forecasting performance. The estimation procedures are introduced and the asymptotic properties of the estimators are studied. The finite-sample properties of the estimators are studied by simulation and real-life examples.

AB - A new approach is proposed to model the relationship between an output and some input time series, perturbed by correlated noise. The functional form of this relationship (the transfer function) is unknown but assumed to be smooth. We propose to model the transfer function by nonparametric smoothing methods and model the noise as an ARIMA process. By using nonparametric smoothing, the model is very flexible and can be used to model highly nonlinear relationships of unknown form; by modeling the noise, the correlation in the data is removed so the transfer function can be estimated more efficiently; additionally, the estimated ARIMA structure can be used to improve the forecasting performance. The estimation procedures are introduced and the asymptotic properties of the estimators are studied. The finite-sample properties of the estimators are studied by simulation and real-life examples.

KW - Nonparametric regression

KW - Local polynomial regression

KW - Regression splines

KW - Nonlinear time series analysis

KW - Transfer function model

KW - ARIMA

UR - https://ww2.amstat.org/meetings/jsm/2006/onlineprogram/index.cfm?fuseaction=abstract_detailsabstractid=306535

M3 - Presentation

T2 - Joint Statistical Meetings

Y2 - 3 August 2011

ER -

Nonparametric Transfer Function Model

Abstract

Conference

Keywords

DC Disciplines

Other files and links

Fingerprint

Cite this