search for




 

Forecasting consumer price indices: A case study using the time series causal model and factor analysis
Journal of the Korean Data & Information Science Society 2018;29:903-13
Published online July 31, 2018
© 2018 Korean Data and Information Science Society.

Ro Jin Pak1

1Department of Applied Statistics, Dankook University
Correspondence to: Professor, Department of Applied Statistics, Dankook University, Jukjun-Dong, Suji-Gu, Yongin 16890, Korea. E-mail: rjpak@dankook.ac.kr
Received June 4, 2018; Revised June 27, 2018; Accepted June 28, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
We tried to predict the consumer price index. The eighteen consumer survey indices associated with the consumer price index were used as the independent variables. However, there were too many independent variables in estimating the predictive model so that it turned out to be difficult to construct the model itself. In this paper, we first tried to combine the consumer survey indices through time series factor analysis, and then tired to construct the model with less independent variables. The causal model with the consumer survey indices as the independent variables was not feasible, but the model for the consumer price index with the combined indices have been established well. Even, the predictions by the proposed method for the consumer price index were more like the actual value than those by an ARIMA model.
Keywords : Customer price index, customer survey index, Granger causal model, impulse response analysis, variance decomposition, vector autoregressive model, vector error correction model.