On Long Memory Origins and Forecast Horizons

Research output: Working paperResearch

Abstract

Most long memory forecasting studies assume that the memory is generated by the fractional difference operator. We argue that the most cited theoretical arguments for the presence of long memory do not imply the fractional difference operator, and assess the performance of the autoregressive fractionally integrated moving average (ARFIMA) model when forecasting series with long memory generated by nonfractional processes. We find that high-order autoregressive (AR) models produce similar or superior forecast performance than ARFIMA models at short horizons. Nonetheless, as the forecast horizon increases, the ARFIMA models tend to dominate in forecast performance. Hence, ARFIMA models are well suited for forecasts of long memory processes regardless of the long memory generating mechanism, particularly for medium and long forecast horizons. Additionally, we analyse the forecasting performance of the heterogeneous autoregressive (HAR) model which imposes restrictions on high-order AR models. We find that the structure imposed by the HAR model produces better long horizon forecasts than AR models of the same order, at the price of inferior short horizon forecasts in some cases. Our results have implications for, among others, Climate Econometrics and Financial Econometrics models dealing with long memory series at different forecast horizons. We show in an example that while a short memory autoregressive moving average (ARMA) model gives the best performance when forecasting the Realized Variance of the S&P 500 up to a month ahead, the ARFIMA model gives the best performance for longer forecast horizons.
Original languageEnglish
PublisherArXiv
Number of pages19
Publication statusPublished - 21 Dec 2017

Fingerprint

Long memory
Forecast horizon
Autoregressive model
Moving average
Integrated
Forecasting performance
Operator
Forecast performance
Long memory process
Autoregressive moving average model
Financial econometrics
Climate
Econometric models
Realized variance
Econometrics

Cite this

@techreport{54d203db466f4d0897f6c6e949413460,
title = "On Long Memory Origins and Forecast Horizons",
abstract = "Most long memory forecasting studies assume that the memory is generated by the fractional difference operator. We argue that the most cited theoretical arguments for the presence of long memory do not imply the fractional difference operator, and assess the performance of the autoregressive fractionally integrated moving average (ARFIMA) model when forecasting series with long memory generated by nonfractional processes. We find that high-order autoregressive (AR) models produce similar or superior forecast performance than ARFIMA models at short horizons. Nonetheless, as the forecast horizon increases, the ARFIMA models tend to dominate in forecast performance. Hence, ARFIMA models are well suited for forecasts of long memory processes regardless of the long memory generating mechanism, particularly for medium and long forecast horizons. Additionally, we analyse the forecasting performance of the heterogeneous autoregressive (HAR) model which imposes restrictions on high-order AR models. We find that the structure imposed by the HAR model produces better long horizon forecasts than AR models of the same order, at the price of inferior short horizon forecasts in some cases. Our results have implications for, among others, Climate Econometrics and Financial Econometrics models dealing with long memory series at different forecast horizons. We show in an example that while a short memory autoregressive moving average (ARMA) model gives the best performance when forecasting the Realized Variance of the S&P 500 up to a month ahead, the ARFIMA model gives the best performance for longer forecast horizons.",
author = "Vera-Vald{\'e}s, {J. Eduardo}",
year = "2017",
month = "12",
day = "21",
language = "English",
publisher = "ArXiv",
type = "WorkingPaper",
institution = "ArXiv",

}

On Long Memory Origins and Forecast Horizons. / Vera-Valdés, J. Eduardo.

ArXiv, 2017.

Research output: Working paperResearch

TY - UNPB

T1 - On Long Memory Origins and Forecast Horizons

AU - Vera-Valdés, J. Eduardo

PY - 2017/12/21

Y1 - 2017/12/21

N2 - Most long memory forecasting studies assume that the memory is generated by the fractional difference operator. We argue that the most cited theoretical arguments for the presence of long memory do not imply the fractional difference operator, and assess the performance of the autoregressive fractionally integrated moving average (ARFIMA) model when forecasting series with long memory generated by nonfractional processes. We find that high-order autoregressive (AR) models produce similar or superior forecast performance than ARFIMA models at short horizons. Nonetheless, as the forecast horizon increases, the ARFIMA models tend to dominate in forecast performance. Hence, ARFIMA models are well suited for forecasts of long memory processes regardless of the long memory generating mechanism, particularly for medium and long forecast horizons. Additionally, we analyse the forecasting performance of the heterogeneous autoregressive (HAR) model which imposes restrictions on high-order AR models. We find that the structure imposed by the HAR model produces better long horizon forecasts than AR models of the same order, at the price of inferior short horizon forecasts in some cases. Our results have implications for, among others, Climate Econometrics and Financial Econometrics models dealing with long memory series at different forecast horizons. We show in an example that while a short memory autoregressive moving average (ARMA) model gives the best performance when forecasting the Realized Variance of the S&P 500 up to a month ahead, the ARFIMA model gives the best performance for longer forecast horizons.

AB - Most long memory forecasting studies assume that the memory is generated by the fractional difference operator. We argue that the most cited theoretical arguments for the presence of long memory do not imply the fractional difference operator, and assess the performance of the autoregressive fractionally integrated moving average (ARFIMA) model when forecasting series with long memory generated by nonfractional processes. We find that high-order autoregressive (AR) models produce similar or superior forecast performance than ARFIMA models at short horizons. Nonetheless, as the forecast horizon increases, the ARFIMA models tend to dominate in forecast performance. Hence, ARFIMA models are well suited for forecasts of long memory processes regardless of the long memory generating mechanism, particularly for medium and long forecast horizons. Additionally, we analyse the forecasting performance of the heterogeneous autoregressive (HAR) model which imposes restrictions on high-order AR models. We find that the structure imposed by the HAR model produces better long horizon forecasts than AR models of the same order, at the price of inferior short horizon forecasts in some cases. Our results have implications for, among others, Climate Econometrics and Financial Econometrics models dealing with long memory series at different forecast horizons. We show in an example that while a short memory autoregressive moving average (ARMA) model gives the best performance when forecasting the Realized Variance of the S&P 500 up to a month ahead, the ARFIMA model gives the best performance for longer forecast horizons.

M3 - Working paper

BT - On Long Memory Origins and Forecast Horizons

PB - ArXiv

ER -