• Journal of Korean Society of Transportation
• /
• v.29 no.5
• /
• pp.139-155
• /
• 2011

This study is to estimate the dynamic change of the regional railway passenger traffic and, based on the estimated, to forecast the future regional railway passenger traffic by using the Seasonal ARIMA model. The existing studies using ARIMA failed to consider seasonality nor the monthly or the quarterly data. It was attempted in this study to use the monthly regional railway passenger traffic data to propose a model that estimates dynamic change of demand. The authors employed the Seasonal ARIMA model previously developed and used (1) the numbers of monthly passenger data and (2) the monthly passenger-km data. The test results showed that the numbers of passengers in 2015 and 2020 would increase by 36% and 71%, respectively, compared to those in 2008. The numbers of passenger-kms in 2015 and 2020 would increase by 25% and 78%, respectively, compared to those in 2008.

• Journal of Korea Port Economic Association
• /
• v.29 no.3
• /
• pp.1-23
• /
• 2013

This paper estimates and forecasts the container throughput of Busan port using the monthly data for years 1992-2011. To do this, this paper uses the several seasonal multiplicative ARIMA models. Among several ARIMA models, the seasonal multiplicative ARIMA model $(1,0,1){\times}(1,0,1)_{12}$ is selected as the best model by AIC, SC and Hannan-Quin information criteria. According to the forecasting values of the selected seasonal multiplicative ARIMA model $(1,0,1){\times}(1,0,1)_{12}$, the container throughput of Busan port for 2013-2020 will increase steadily annually, but there will be some volatile variations monthly due to the seasonality and other factors. Thus, to forecast the future container throughput of Busan port and to develop the Busan port efficiently, we need to use and analyze the seasonal multiplicative ARIMA model $(1,0,1){\times}(1,0,1)_{12}$.

• The Korean Journal of Applied Statistics
• /
• v.22 no.5
• /
• pp.1007-1017
• /
• 2009

Forecasting for air demand such as passengers and freight has been one of the main interests for air industries. This research has mainly focus on the comparison the performance between the univariate seasonal ARIMA models and the multivariate time series models. In this paper, we used real data to predict demand on international passenger and freight. And multivariate time series models are better than the univariate models based on the accuracy criteria.

• Journal of Korea Port Economic Association
• /
• v.31 no.1
• /
• pp.69-84
• /
• 2015

The purpose of this study is to forecast the seaborne trade volume during January 1994 to December 2014 using the multiplicative seasonal autoregressive integrated moving average (ARIMA) along with intervention factors and an artificial neural network (ANN) model. Diagnostic checks of the ARIMA model were conducted using the Ljung-Box Q and Jarque-Bera statistics. All types of ARIMA process satisfied the basic assumption of residuals. The ARIMA(2,1,0) $(1,0,1)_{12}$ model showed the lowest forecast error. In addition, the prediction error of the artificial neural network indicated a level of 5.9% on hidden layer 5, which suggests a relatively accurate forecasts. Furthermore, the ex-ante predicted values based on the ARIMA model and ANN model are presented. The result shows that the seaborne trade volume increases very slowly.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1410-1414
• /
• 2010

최근 들어 가뭄과 국지성 호우 등의 기상이변이 지속적으로 발생하고 있으며, 이는 국민 삶의 발전과 향상에 밀접한 관계가 있는 것으로 전세계적으로 이에 대한 관심이 증가하고 있는 추세이다. 특히 댐의 효율적 관리와 안정적인 운영은 홍수피해 방지, 안정적인 용수공급과 같은 국민 생활과 밀접한 관계를 가지고 있어 수자원의 효율적인 운영과 이용은 장기적인 관점을 통하여 수립해야 한다. 이와 같이 댐 유입량의 예측은 유출모형의 목적 중 중요한 부분으로 확정론적 모형이 시 혹은 일유량과 같은 매우 짧은 시간의 유출을 예측하는데 주로 사용되지만 이는 매개변수의 추정이 불가능하거나 실제유역에서의 측정이 불가능 할 경우에는 모형적용에 한계가 있다. 이에 반해 추계학적 모형에 의한 유출예측은 장기간의 유출을 과거자료의 통계학적 특성변수를 매개변수로 하여 예측하는 방법으로 모형의 적용에 필요한 매개변수가 적어 그 적용성이 간편한 장점이 있다. 본 연구에서는 계절형 ARIMA모형을 적용하여 과거자료의 적용범위, 매개변수의 산정, 적합성 판정에 대하여 판단하고, 이 모형이 월유입량의 예측에 적합한지를 검토하였다.

• The Korean Journal of Applied Statistics
• /
• v.24 no.1
• /
• pp.93-102
• /
• 2011

In this paper, we compared the performance of the several time series models for tourism demand forecasting. We showed that seasonal effects in the data(Japan, China, USA, and Philippines) exist in the tourism data and the forecasting accuracies are compared by the RMSE criterion.

• Journal of Korea Port Economic Association
• /
• v.23 no.1
• /
• pp.149-162
• /
• 2007

The purpose of this study is to forecast the marine trading volumes using multiplicative seasonal Autoregressive Integrated Moving Average(ARIMA) model. The paper proceeds by comparing the forecasting performances of the unload volumes with those of the load volumes with Box-Jenkins ARIMA model. Also, I present the predicted values based on the ARIMA model. The result shows that the trading volumes increase very slowly.

• The Korean Journal of Applied Statistics
• /
• v.34 no.4
• /
• pp.623-632
• /
• 2021

Through this study, we studied how to consider environment variables (such as temperatures, weekend, holiday) closely related to electricity demand, and how to consider the characteristics of Korea electricity demand. In order to conduct this study, Smoothing method, Seasonal ARIMA model and regression model with AR-GARCH errors are compared with mean absolute error criteria. The performance comparison results of the model showed that the predictive method using AR-GARCH error regression model with environment variables had the best predictive power.

• Journal of the Korean Society for Railway
• /
• v.17 no.4
• /
• pp.307-312
• /
• 2014

This study suggested the ARIMA model taking into consideration the seasonal characteristic factor as a method for efficiently forecasting passenger transport demand of the Joongang Line. The forecasting model was built including the demand for the central inland region tourist train (O-train, V-train), which was opened to traffic in April-, 2013 and run in order to reflect the recent demand for the tourism industry. By using the monthly time series data (103) from January-, 2005 to July-, 2013, the optimum model was selected. The forecasting results of passenger transport demand of the Joongang Line showed continuous increase. The developed model forecasts the short-term demand of the Joongang Line.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.05a
• /
• pp.139-144
• /
• 2002

계절변동조정방법인 X-12-ARIMA방법을 이용할 때에는 우리 실정에 적합한 옵션을 선택하고, 우리만에 특수한 명절과 조업일수영향을 사전에 조정해야한다. 본고에서는 명절과 조업일수영향을 측정하는 모형을 설정하고, 이것으로 추정된 사전조정요인을 원계열에서 제거했을 때 계절변동 및 계절변동조정계열의 안정성이 향상되었는가를 진단하고, 분류별로 적합한 X-12-ARIMA방법의 옵션을 제안하였다.