Premium
Forecasting Inflation Using Constant Gain Least Squares
Author(s) -
Antipin JanErik,
Boumediene Farid Jimmy,
Österholm Pär
Publication year - 2014
Publication title -
australian economic papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 15
eISSN - 1467-8454
pISSN - 0004-900X
DOI - 10.1111/1467-8454.12017
Subject(s) - autoregressive model , constant (computer programming) , mathematics , univariate , least squares function approximation , ordinary least squares , inflation (cosmology) , statistics , residual sum of squares , econometrics , generalized least squares , non linear least squares , recursive least squares filter , explained sum of squares , multivariate statistics , computer science , algorithm , estimator , physics , theoretical physics , adaptive filter , programming language
This paper assesses the usefulness of constant gain least squares when forecasting inflation. An out‐of‐sample forecast exercise is conducted, in which univariate autoregressive models for inflation in A ustralia, S weden, the U nited K ingdom and the U nited S tates are used. The results suggest that it is possible to improve the forecast accuracy by employing constant gain least squares instead of ordinary least squares. In particular, when using a gain of 0.05, constant gain least squares generally outperforms the corresponding autoregressive model estimated with ordinary least squares. In fact, at longer forecast horizons, the root mean square forecast error is reliably lowered for all four countries and for all lag lengths considered in the study.