• Communications for Statistical Applications and Methods
• /
• v.18 no.1
• /
• pp.13-21
• /
• 2011

This paper studies the analysis of multivariate nonstationary time series with seasonality. Three types of multivariate time series models are considered: seasonal cointegration model, nonseasonal cointegration model with seasonal dummies, and vector autoregressive model in seasonal differences that are compared for forecasting performances using Korean macro-economic time series data. The cointegration models produce smaller forecast errors in short horizons; however, when longer forecasting periods are considered the vector autoregressive model appears preferable.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.4
• /
• pp.723-733
• /
• 2016

This study aims to analyze the effects of urban characteristics on the amount of damage caused by natural disasters. It is focused on the areas of a municipal level in Korea. Also, it takes into account the spatial autocorrelation of the damage caused by natural disasters. Moran's I statistics was estimated to examine the spatial autocorrelation in the damage from the study area. Subsequent to evaluating the suitability for spatial regression models and the OLS regression model, the spatial lag model was employed as an empirical analysis for the study. It showed that the increase in residential area leads to the decrease in the amount of natural disaster damage. On the other hand, the increase in green area and river basin is associated with the increase in the damage. As a result of empirical analysis, appropriate policy establishment and implementation about the damage-adding factors is needed in order to reduce the amount of damage in the future.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.103-117
• /
• 2017

In longitudinal data analysis, the serial correlation of repeated outcomes must be taken into account using covariance matrix. Modeling of the covariance matrix is important to estimate the effect of covariates properly. However, It is challenging because there are many parameters in the matrix and the estimated covariance matrix should be positive definite. To overcome the restrictions, several Cholesky decomposition approaches for the covariance matrix were proposed: modified autoregressive (AR), moving average (MA), ARMA Cholesky decompositions. In this paper we review them and compare the performance of the approaches using simulation studies.

• The Korean Journal of Applied Statistics
• /
• v.30 no.2
• /
• pp.271-280
• /
• 2017

Real-estate values and related economics are often the first read newspaper category. We are concerned about the opinions of experts on the forecast for real estate prices. The Box-Jenkins ARIMA model is a commonly used statistical method to predict housing prices. In this article, we tried to predict housing prices by combining independent component analysis (ICA) in multivariate data analysis and the Box-Jenkins ARIMA model. The two independent components for both the selling price index and the long-term rental price index were extracted and used to predict the future values of both indices. In conclusion, it has been shown that the actual indices and the forecast indices using ICA are more comparable to the forecasts of the ARIMA model alone.

• The Korean Journal of Applied Statistics
• /
• v.36 no.1
• /
• pp.21-32
• /
• 2023

The amount of money processed in medicine from the Korea Consumer Agency was studied by the various time series models. The medical data set from the Korea Consumer Agency were consisted of counseling, damage relief and conciliation. For the analysis of time series, autoregressive moving average model, vector autoregressive model and the transfer function model were used. We considered the stationarity and cross correlation function for the identification and fitting. As a result, the transfer function model showed a better prediction. Whereas, the vector autoregressive model also provided good information for the degree and duration of the influence of variables.

• The Korean Journal of Applied Statistics
• /
• v.31 no.2
• /
• pp.303-313
• /
• 2018

This study considers time series models to forecast drug expenditures in national health insurance. We adopt autoregressive error model (ARE) and transfer function model (TFM) with segmented level and trends (before and after 2012) in order to reflect drug price reduction in 2012. The ARE has only a segmented deterministic term to increase the forecasting performance, while the TFM explains a causality mechanism of drug expenditure with closely related exogenous variables. The mechanism is developed by cross-correlations of drug expenditures and exogenous variables. In both models, the level change appears significant and the number of drug users and ratio of elderly patients variables are significant in the TFM. The ARE tends to produce relatively low forecasts that have been influenced by a drug price reduction; however, the TFM does relatively high forecasts that have appropriately reflected the effects of exogenous variables. The ARIMA model without the exogenous variables produce the highest forecasts.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.4
• /
• pp.791-799
• /
• 2015

In random walk hypothesis, we assume that current change of financial time series is independent of past values. It is interpreted as an existency of a unit root in ARMA models and many researches have been focused on whether ${\rho}$ < 1 or not. If some financial data are generated from an explosive autoregressive model, the chance of a bubble economy increases. We have to find the symptoms of it in advance. Since some well-known parameter estimators contain the parameter itself and other statistic is constructed under a specific parameter structure assumption, those are difficut to be adopted. In this paper we investigate a test for explosive autoregressive models using slope signs. We found the properties of the slope sign test statistic under both independent error and correlated error conditions, mainly by simulations.

• The Korean Journal of Applied Statistics
• /
• v.27 no.6
• /
• pp.1039-1047
• /
• 2014

An autoregressive model with normal errors is a natural model that attempts to fit time series data. More flexible models that include normal distribution as a special case are necessary because they can cover normality to non-normality models. The skewed exponential power distribution is a possible candidate for autoregressive models errors that may have tails lighter(platykurtic) or heavier(leptokurtic) than normal and skewness; in addition, the use of skewed exponential power distribution can reduce the influence of outliers and consequently increases the robustness of the analysis. We use SIR algorithm and grid method for an efficient Bayesian estimation.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.3
• /
• pp.419-425
• /
• 2010

Kernel machine learning is gaining a lot of popularities in analyzing large or high dimensional nonlinear data. We use this technique to estimate a GARCH model for predicting the conditional volatility of stock market returns. GARCH models are usually estimated using maximum likelihood (ML) procedures, assuming that the data are normally distributed. In this paper, we show that GARCH models can be estimated using kernel machine learning and that kernel machine has a higher predicting ability than ML methods and support vector machine, when estimating volatility of financial time series data with fat tail.

• Journal of the Korean Data and Information Science Society
• /
• v.11 no.1
• /
• pp.1-18
• /
• 2000

In this paper, we study several parameter estimation methods used for autoregressive processes and compare them in view of forecasting. The least square estimation, least absolute deviation estimation, robust estimation are compared through Monte Carlo simulations.