• KDI Journal of Economic Policy
• /
• v.22 no.1_2
• /
• pp.3-55
• /
• 2000

본 연구는 세입증가율 예측을 위해 사용되는 각종 세수추계모형의 예측능력을 상호비교하는 데 목적이 있다. 본 연구에서 고려하는 세수추계 방식은 네 가지이다. 첫째는 단순 ECM 모형으로서 오차수정모형(error correction model)을 각각의 세목에 적용하여 세수를 예측하는 것이다. 둘째는 SUR-ECM 모형으로서 단순 ECM 모형의 개별 회귀방정식을 통합하여 SUR(Seemingly Unrelated Regression) 방식으로 추정한 후 이를 이용하여 세수를 예측하는 것이다. 셋째와 넷째는 흔히 사용되는 탄성치 방식으로서, 과거의 연도별 탄성치를 5년간 또는 10년간 평균하여 이를 바탕으로 향후의 세수를 예측하는 것이다. 이러한 모형비교를 통해 얻은 결과는 다음과 같이 요약될 수 있다. 첫째, 단순 ECM 모형과 5년 평균 탄성치 모형은 예측력에 있어 큰 차이가 없다. 둘째, SUR-ECM 모형과 10년 평균 탄성치 모형은 예측력에 있어 큰 차이가 없다. 셋째, 단순 ECM 모형보다는 SUR-ECM 모형의 예측력이 높으며, 5년 평균 탄성치 모형보다는 10년 평균 탄성치 모형의 예측력이 높다. 넷째, 어느 경우에든 예측 오차가 상당히 크고 이러한 오차는 예측시계가 넓어질수록 커진다. 예를 들어, 5년 후의 세수에 대한 예측치는 평균적으로 오차의 절대값이 10% 수준에 이른다. 탄성치 모형이 단순 ECM 모형이나 SUR-ECM 모형에 비해 그리 나쁜 예측결과를 낳지 않는다는 것은 새로운 사실이다. 또한 5년 평균 탄성치보다 10년 평균 탄성치를 사용하는 것이 더 나은 예측치를 낳는다는 것은 세수예측에 있어 최근의 자료만을 사용하는 것보다는 과거 꽤 오랜 기간의 자료를 사용하는 것이 바람직하다는 점을 시사한다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.3
• /
• pp.23-33
• /
• 2016

This study identified the factors that affect travel time budget by mode for traveler in Seoul using the SUR model. Individual, household and TAZ characteristics were selected as the explanatory variables. Transportation modes are summarized from 18 types to 6 types(walking, personal car, bus, subway, rail and bicycle). The results showed a distinct difference between personal transportation and public transportation. First of all, People who owned a car and driver's licence tend to prefer personal transportation. In addition, we can confirm the relationship between the bus and the subway which are most typical public transportation. Passengers who can available a personal mode preferred the subway than the bus. It is expected to suggest various implications related to the public transportation policy for Seoul metropolitan area.

• The Korean Journal of Applied Statistics
• /
• v.27 no.6
• /
• pp.991-1002
• /
• 2014

Both Bayesian and maximum likelihood methods are efficient for the estimation of regression coefficients of various Tobit regression models (see. e.g. Chib, 1992; Greene, 1990; Lee and Choi, 2013); however, some researchers recognized that the maximum likelihood method tends to underestimate the disturbance variance, which has implications for the estimation of marginal effects and the asymptotic standard error of estimates. The underestimation of the maximum likelihood estimate in a seemingly unrelated Tobit regression model is examined. A Bayesian method based on an objective noninformative prior is shown to provide proper estimates of the disturbance variance as well as other regression parameters

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.627-641
• /
• 2016

In this paper, we consider a seemingly unrelated regression (SUR) model and propose a nonparametric Bayesian approach to SUR with a Dirichlet process mixture of normals for modeling an unknown error distribution. Posterior distributions are derived based on the proposed model, and the posterior inference is performed via Markov chain Monte Carlo methods based on the collapsed Gibbs sampler of a Dirichlet process mixture model. We present a simulation study to assess the performance of the model. We also apply the model to precipitation data over South Korea.

• The Korean Journal of Financial Management
• /
• v.25 no.2
• /
• pp.1-31
• /
• 2008

Before the financial crisis in 1997, Korean bond markets had been those of corporate bonds with relatively high market yield. During the period, most of major institutional investors tend to utilize passive strategies such as buying and holding. After the crisis, however, they could not help choosing active bond management strategies because of lowed yield level and intensified competition among the financial institutions. This study is forced on the yield curve, which is the reflection of all information on the bond investment environments. The study also make analysis on the major economic and securities market factors and its structural relationship with the shape of the curve such as level, curvature and slope. For these purposes, an empirical model based on the Nelson-Siegel Model is estimated with the data during $1999{\sim}2006$. Out-of-sample forecasting is also made to test the usefulness of the estimated model. In addition, the dependent variables which are the estimates of level and slope are estimated on the macro variables and securities market variables. VAR and SUR models are used for the estimation. Estimation results show that level and slope of the yield curve are influenced by the target call rate change, exchange rate change rate, inflation rate. These results provide practical implications for the active managements in the overall treasury bond markets.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.4
• /
• pp.62-72
• /
• 2015

Nowadays the issue of aging society has received considerable critical attention, especially in transportation planning and demand forecasting. This study identified the factors related to travel time budget for elderly by purpose using seemingly unrelated regression model (SUR model). The SUR model is suitable when error terms of each equation are assumed to be correlated across the equations in terms of travel time budget which is constant in 2 hours per day commonly. The results showed that elderly's travel time budget was affected by individual, household, urban facility and transportation service. The leisure travel comprised a large proportion of total travel time and had a positive relationship with elderly, sports, religious facilities. Moreover, the elderly who had low income or unemployed person had low frequency of social activity such as leisure, shopping and business. This study can provide a comprehensive implications of forecasting the future travel demand and analyzing the travel behavior.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.180-191
• /
• 2020

This study analyzes factors that affect average daily travel time budgets, using the Time Use Survey data from 1999 to 2014 in Seoul. We first developed multivariate regression models for travel time from each year, considering demographic and socio-economic variables as well as non-home activity time. The model results showed that household and personal characteristics and non-home activities significantly affect travel time, and their effects are different over time. In addition, we developed seemingly unrelated regression (SUR) models for time allocation for non-home activity and travel, considering their correlations, and explanatory variables were compared over time. Overall, demographic and socio-economic variables significantly affect travel time as well as non-home activity time.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.186-195
• /
• 2014

The purpose of this research is to explain what affects the volunteer center's performance on the basis on the program logic model. We assume that internal factors and external factors influence the organizational performance. For the empirical analysis, we use SUR(seemingly unrelated regression). The major findings of this research are as follows: Frist, organizational budget as internal factors are important influential factors. Second, civil society's capacity variable and stakeholder's support variable affect positively volunteer center's performance. Third, the contract out variable's effect as an operation types is not proven statistically. In case of estimating the multi organizational performance, lastly, the SUR method is prefer to the OLS method in the aspect methodology. However, more systemic study is complemented the panel data for organizational performance.

• Journal of Environmental Policy
• /
• v.9 no.4
• /
• pp.53-76
• /
• 2010

This paper attempts to estimate and compare environmental Kuznets curves (EKC) for$CO_2$ emissions of five regions constituting South Korea. For this, panel data of $CO_2$ emission for these regions are constucted for the period 1990 - 2007. Close inter-dependency among these five regions is considered by using a seemingly unrelated regression (SUR) model. In addition to real per-capita income, price index of energy sources and population dens ity are included as control variables. Results of estimates show the robust existence of EKC's in all these regions. EKC turning points of five regions range between 13.7 and 21.6 million Korean Won, showing a large variation. This difference among regions should be conisidered for the effective implementation of policies targeting the reduction of $CO_2$ emmission. In addition, the increase of energy price is found help reduce the $CO_2$ emmision while the rise of population density seems to lead to the increase of $CO_2$ emission.

• Journal of the Economic Geographical Society of Korea
• /
• v.10 no.4
• /
• pp.414-426
• /
• 2007

The purpose of this study is to analyze whether the spatial externalities of agglomeration economy of manufacturing has been changed or not, from 1991 to 2005. To find this spatial SUR model was used to consider covariance of each equation and it was estimated by 3SLS. This paper found that spatial externalities has been decreased and there is economy of scale in same sector. As a result, we can conclude that there is industrial specialization in region whereas interregional linkage are weaken. This finding supports the desirability of creating supra-regional agencies promoting interregional linkage because supra-regional agencies can internalize spatial externality of agglomeration economy.