Template-Type: ReDIF-Article 1.0
Author-Name: Ki-Ho Kim
Author-Email: kihokim@bok.or.kr
Author-Workplace-Name: Institute for Monetary and Economic Research, The Bank of Korea
Title: Estimation of Korean Monthly GDP with Mixed-Frequency Data using the Unobserved Component Error Correction Model (in Korean)
Abstract: Since GDP is announced on a quarterly basis, the data frequency of GDP is relatively lower than those of other major macro variables published on a monthly basis. Therefore, the utility of GDP in judging the economy swiftly is in reality not high. In terms of data utility, the utility of GDP is low as well. If GDP is used, the other monthly data must be converted into quarterly data, and the result is a reduction to one-third of the total number of observations. Meanwhile, considering that the Bank of Korea determines its call rate policy on a monthly basis, it is essential to grasp the monthly GDP trend. Such policy-based demand can also be resolved by estimating monthly GDP.
In this paper, monthly GDP is obtained by using monthly information data such as the IPI (Industrial Production Index) and the WRSI (wholesale and retail sale index), which are substantially connected with GDP. To acquire monthly GDP, this paper suggests applying the unobserved component vector error correction model that can utilize mixed frequency data in estimation directly, without extra procedures for data transformation (monthly to quarterly).
In order to judge whether monthly GDP is estimated appropriately, this paper compares actual quarterly GDP with estimated quarterly GDP based on the final monthly GDP estimates. The RMSPE (root mean square percentage error) of this estimated quarterly GDP shows around 0.01. The final monthly GDP is produced by combining two individual monthly GDP figures (one estimated using the IPI and the other by the WRSI) and then benchmarking the combined figure, and it is then compared to the actual quarterly GDP. The RMSPE of the final monthly GDP is close to 0. Meanwhile, the correlation coefficient and the lagged correlation coefficient between the estimated monthly GDP and the cyclical component of the CCI (Coincident Composite Index) are high and significant, and the estimated monthly GDP leads CCI by approximately one to three months.
Classification-JEL: C31, C43, C51
Keywords: mixed frequency data, unobserved component vector error correction model, monthly GDP
Journal: Economic Analysis (Quarterly)
Pages: 70-110
Volume: 13
Issue: 3
Year: 2007
Month: September
DOI:
File-URL: http://imer.bok.or.kr/attach/imer_kor/2545/2013/12/1386573102690.pdf
File-Format: Application/pdf
Handle: RePEc:bok:journl:v:13:y:2007:i:3:p:70-110