• 한국항만경제학회지
• /
• 제39권2호
• /
• pp.129-141
• /
• 2023

본 연구는 오차교정모형을 활용해 건화물선과 유조선 일간 해상운임의 동태적 특성과 예측 정확도를 분석한다. 공적분된 시계열 자료의 오차를 계산하기 위해 본 연구는 공통 확률적 추세 모형(Common Stochastic Trend Model, CSTM 모형)과 벡터오차교정모형(Vector Error Correction Model, VECM 모형)을 활용한다. 먼저, CSTM 모형의 오차를 사용한 오차교정모형이 VECM 모형의 경우보다 교정계수(adjustment speed coefficient)가 경제학적 이론에 더 부합하는 결과를 보인다. 나아가 조정결정계수(adjR²) 측면에서도 CSTM 모형의 경우가 VECM 모형에 비해 모형 적합도가 큰 것으로 나타난다. 둘째, 예측 정확도를 판단하는 지표인 평균 절대 오차와 평균 절대 척도 오차를 살펴보면, CSTM 모형의 오차를 이용한 모형이 VECM 모형의 오차를 이용한 모형보다 총 15가지 경우 중에 12가지 경우에서 예측 정확도가 높은 것을 확인할 수 있다. 미래 연구주제로서 1) 두 가지 오차를 모두 활용하는 분석 및 예측 과제, 2) 원자재 및 에너지 자원 시장의 데이터를 추가하는 과제, 3) 오차항의 부호에 따라 교정계수를 다르게 추정하는 과제 등을 제시한다.

• 아태비즈니스연구
• /
• 제15권3호
• /
• pp.385-397
• /
• 2024

Purpose - The purpose of this study was to analyze the dynamic relationship between oil prices and macroeconomic variables (gross domestic product, consumer price index, and interest rate). Long-run and short-run effects of oil prices on these macroeconomic variables are examined. Design/methodology/approach - The vector error correction model (VECM) is used to examine the short-run and long-term causality of oil prices, and a hierarchical Bayesian vector autoregressive model (HBVAR) is used to find the impulse of oil shock and the response of other variables. Findings - First, oil prices do not have short-term causality with macroeconomic variables, but they have long-term causality with interest rates and GDP. Second, the long-term stable relationship of oil prices and other macroeconomic variables is important to find out causality. Third, oil shock increases interest rates and decreases GDP and consumer price. Research implications or Originality - The significance of this study is a new attempt to analyze the dynamic relationship between oil prices and macroeconomic variables by linking VECM and HBVAR. Although VECM can analyze the long-term relationship and short-term dynamics between oil prices and macroeconomic variables, it was difficult to identify the transmission path of the oil price shock. HBVAR is confirmed to be flexible because it can bypass the process of selecting VAR or VECM through unit root test and cointegration analysis, and it is expected to reduce uncertainty of selecting hyperparameters.

• 대한산업공학회지
• /
• 제36권3호
• /
• pp.203-211
• /
• 2010

This study examines a cointegrated vector autoregressive (VAR) model where parameters are subject to switch across the regimes in the term structure of interest rates. To employ the regime switching framework, the Markov-switching vector error correction model (MS-VECM) is allowed to the regime shifts in the vector of intercept terms, the variance-covariance terms, the error correction terms, and the autoregressive coefficient parts. The corresponding approaches are illustrated using the term structure of interest rates in the US Treasury bonds over the period of 1958 to 2009. Throughout the modeling procedure, we find that the MS-VECM can form a statistically adequate representation of the term structure of interest rate in the US Treasury bonds. Moreover, the regime switching effects are analyzed in connection with the historical government monetary policy and with the recent global financial crisis. Finally, the results from the comparisons both in information criteria and in forecasting exercises with and without the regime switching lead us to conclude that the models in the presence of regime dependence are superior to the linear VECM model.

• Ocean and Polar Research
• /
• 제34권2호
• /
• pp.185-195
• /
• 2012

This paper focused on forecasting a short-term production of oysters, which have been farmed in Korea, with distinct periodicity of production by year, and different production level by month. To forecast a short-term oyster production, this paper uses monthly data (260 observations) from January 1990 to August 2011, and also adopts several econometrics methods, such as Multiple Regression Analysis Model (MRAM), Seasonal Autoregressive Integrated Moving Average (SARIMA) Model, and Vector Error Correction Model (VECM). As a result, first, the amount of short-term oyster production forecasted by the multiple regression analysis model was 1,337 ton with prediction error of 246 ton. Secondly, the amount of oyster production of the SARIMA I and II models was forecasted as 12,423 ton and 12,442 ton with prediction error of 11,404 ton and 11,423 ton, respectively. Thirdly, the amount of oyster production based on the VECM was estimated as 10,425 ton with prediction errors of 9,406 ton. In conclusion, based on Theil inequality coefficient criterion, short-term prediction of oyster by the VECM exhibited a better fit than ones by the SARIMA I and II models and Multiple Regression Analysis Model.

• Ocean and Polar Research
• /
• 제40권1호
• /
• pp.49-58
• /
• 2018

This study aimed to analyze the causality of hairtail prices among import and domestic distribution channels using a Vector Error Correction Model(VECM). The results are as follows. First, since the ADF unit-root test suggests that each of the price variables, apart from retail price, has a unit root, the price variables should be 1st-differenced to secure the stability of the prices. Next, through the Johansen co-integration test, it was discovered that there are long-term relationships among the price variables. On the basis of the co-integration test, VECM analysis shows that the producer price has a long-run balance with the import and wholesale prices. In particular, when the prices deviate from the balance, the producer price dynamically adjusts to return to the long-term relationship among prices. It also indicates that the producer price has an impact on the import, wholesale, and retail prices in the short-term, and the import price has an influence on the producer and wholesale prices. In addition, the impulse response analysis demonstrates that the impulse of import and producer prices has a lasting impact on each of the prices.

• International Journal of Advanced Culture Technology
• /
• 제10권3호
• /
• pp.25-32
• /
• 2022

This study analyzes the impact of occupational accidents on economic growth and labor productivty losses in Korea between January 2008 and July 2018, using the Vector Error-Correction Model (VECM). According to the analysis, the occurrence of occupational accidents was revealed to reduce the number of employed workers and also hinder economic growth. This can be reinterpreted as the reduction of occupational accidents does not cause labor losses in the industry, rather may induce economic growth. Also, the findings discovered that an increase in the number of workers may lead to increase in the probability of occupational accidents in the short term. This suggests that greater number of work-related accidents may occur during the early stages- due to new employees' lack of knowledge related to safety at workplace.

• 지역연구
• /
• 제35권1호
• /
• pp.47-57
• /
• 2019

본 연구의 목적은 계량분석을 통해 우리나라 지역내총생산에 영향을 미치는 주요 요인별 영향력을 분석하는 것이다. 본 연구는 분석대상 지역으로 대구광역시를 선정했는데 대구광역시는 영남 지역의 중추기능을 지속적으로 수행해 왔으며, 우리나라 섬유 화학제품 등의 수출 전략기지로 지위하고 있다. 또한 영남 지역에 도달하는 주요 수입화물의 기종점 역할을 수행하는 등 이처럼 대구 지역은 우리나라 수출입 무역 확대와 국가경제 성장에 기여하는 바가 높다. 이를 위해 본 연구는 공적분모형(Co-integration Model)과 벡터오차수정모형(Vector Error Correction Model; VECM)을 사용하여 대구 지역내총생산에 영향을 미치는 장기균형함수를 추정하였다. 본 연구는 우리나라 지역내총생산에 영향을 미치는 주요 요인들의 영향력을 정량적인 방식을 통해 추정하고 장기 균형 시점의 총생산으로부터 괴리가 발생했을 때 얼마나 빠른 속도로 장기균형으로 수렴하는가를 추정하였다는 점에서 의의가 있다.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권1호
• /
• pp.37-46
• /
• 2020

The paper examines the dynamic relationship of domestic credit and stock market liquidity on the economic growth of the Philippines from 1995 to 2018 applying the autoregressive distributed lag (ARDL) bounds testing approach to cointegration, together with Granger causality test based on vector error correction model (VECM). The ARDL model indicated a long-run relationship of domestic credit and stock market liquidity on GDP growth. When the GDP per capita is the dependent variable there is weak cointegration. Also, the Johansen cointegration test confirmed the existence of long-run relationship of domestic credit and stock market liquidity both on GDP growth and GDP per capita. The VECM concludes a long-run causality running from domestic credit and stock market liquidity to GDP growth. At levels, domestic credit has significant short-run causal relationship with GDP growth. As for stock market liquidity at first lag, has significant short-run causal relationship with GDP growth. With regards to VECM for GDP per capita, domestic credit and stock market liquidity indicates no significant dynamic adjustment to a new equilibrium if a disturbance occurs in the whole system. At levels, the results indicated the presence of short-run causality from stock market liquidity and GDP per capita. The CUSUMSQ plot complements the findings of the CUSUM plot that the estimated models for GDP growth and GDP per capita were stable.

• 해운물류연구
• /
• 제34권4호
• /
• pp.545-563
• /
• 2018

본 연구의 목적은 VLCC(Very Large Crude Oil Carrier) 운임에 영향을 미치는 주요 결정요인의 장기적 탄성치를 추정하는 것이다. 이를 위해 본 연구는 영국 해운 전문 기업인 클락슨이 공표하는 연간 VLCC 운임을 종속변수로, 원유(Crude oil) 물동량, VLCC 선복량, 벙커유 가격, Libor 금리를 설명변수로 사용하였다. 본 연구는 벡터오차수정모형(Vector Error Correction Model; VECM)을 사용하여 운임 결정 장기균형함수를 추정하였으며, 추정결과 물동량 1.0% 증가 시 운임 6.4% 증가, 선복량 1.0% 증가 시 운임 1.9% 감소, 벙커유 가격 1.0% 증가 시 운임 0.3% 감소, 금리 1.0% 증가 시 운임은 0.18% 증가하는 것으로 나타났다. 벙커유 가격의 경우 일반적인 직관과 반대되는 마이너스(-) 부호로 계수가 추정되었는데, 이는 설명변수 중 벙커유 가격이나 금리 등의 2차 변수가 운임에 미치는 영향력은 적은 반면 직접적인 수급 변수가 운임을 결정하는 주요 요인이기 때문인 것으로 이해된다. 후속연구에서 컨테이너선, 건화물선 등 다른 선종들을 대상으로 연구를 수행하고 다양한 선종별 운임의 결정요인을 비교 분석하는 것이 필요하다.

• The Journal of Asian Finance, Economics and Business
• /
• 제5권3호
• /
• pp.7-17
• /
• 2018

This paper examines short-run and long-run dynamic relationships between selected macroeconomic variables and stock prices in the Korea Stock Exchange. The data is restricted to the period for which monthly data are available from January 1986 to October 2016 (370 observations) retrieved from the Economic Statistics System database sponsored by the Bank of Korea. The study employs unit root test, cointegration test, vector error correction estimates, impulse response test, and structural break test. The results of the Johansen cointegration test indicate at least three cointegrating equations exist at the 0.05 level in the model, confirming that there is a long-run equilibrium relationship between stock prices and macroeconomic variables in Korea. The results of vector error correction model (VECM) estimates indicate that money supply and short-term interest rate are not related to stock prices in the short-run. However, exchange rate is positively related to stock prices while the industrial production index and inflation are negatively related to stock prices in the short-run. Furthermore, the VECM estimates indicate that the external shock, such as regional and global financial crisis shocks, neither affects changes in the endogenous variables nor causes instability in the cointegrating vector. This study finds that the endogenous variables are determined by their own dynamics in the model.