SP 패널데이터의 Bias를 고려한 동적모델

남궁문,성수련,최기주,이백진 대한교통학회 2000 大韓交通學會誌 Vol.18 No.6

SP 데이터는 데이터 수집의 효율이 RP 데이터 보다 높고 장래의 교통 시스템의 조건이나 속성에 대한 응답자들의 태도를 조사 할 수 있다는 점에서 많이 사용되고 있으나 SP 데이터는 주요하게 두 가지 편위를 가지고 있는데 SP 설문조사시에 발생하는 응답편위와 SP 패널조사시에 발생하는 누락편위이다. 이러한 SP 데이터의 편위가 수정되지 않으면 장래의 잘못된 교통수요예측을 유발할 수 있다. 따라서 본 연구에서는 이러한 SP 모델의 편위와 상태의존을 고려한 모델을 구축하기 위하여 6개의 횡단면 모델과 동적모델을 제안하였다. 횡단면 모델 중 RP데이터의 선택결과를 고려한 모델을 이용하여 SP모델의 편위를 보완할 수 있는 모델을 구축할 수 있었으며 동적모델의 경우에 패널데이터의 상태의존도를 지수함수로 가정하여 상태의존도를 고려한 동적모델을 구축하였다. 또한 패널조사시에 필연적으로 발생하는 누락데이터에 의한 누락편위를 모델에 고려하기 위하여 WESML방법을 적용하여 모델을 구축하였으며 그 결과 상태의존도를 보다 세밀하게 제어함으로서 모델의 설명력을 개선시키고 향후 SP 패널데이터를 이용한 동적모델의 적용성을 높일 수 있음을 알 수 있었다. 본 연구에서는 모델의 유용성을 검토하기 위하여 전주시의 외각 지역인 호남제일문 방향에서 도심으로 접근하는 3개의 주경로(천변로, 기린로, 팔달로)에 대한 패널조사 자료를 바탕으로 모델을 구축하였다. Stated Preference (SP) data has been regarded as more useful than Revealed Preference (RP) data, because researchers can investigate the respondents\` Preference and attitude for a traffic condition or a new traffic system by using the SP data. However, the SP data has two bias: the first one is the bias inherent in SP data and the latter one is the attrition bias in SP panel data. If the biases do not corrected, the choice model using SP data may predict a erroneous future demand. In this Paper, six route choice models are constructed to deal with the SP biases, and. these six models are classified into cross-sectional models (model I∼IH) and dynamic models (model IV∼VI) From the six models. some remarkable results are obtained. The cross-sectional model that incorporate RP choice results of responders with SP cross-sectional model can correct the biases inherent in SP data, and also the dynamic models can consider the temporal variations of the effectiveness of state dependence in SP responses by assuming a simple exponential function of the state dependence. WESML method that use the estimated attrition probability is also adopted to correct the attrition bias in SP Panel data. The results can be contributed to the dynamic modeling of SP Panel data and also useful to predict more exact demand.

동태적 패널모형의 회계이익률 예측능력 검증

심상규 ( Sang Gyoo Shim ),허영빈 ( Young Pin Huh ),김창수 ( Chang Soo Kim ) 한국회계학회 2004 會計學硏究 Vol.29 No.2

회계이익률은 Ohlson의 초과이익할인모형, NCI 지식자산평가모형 등의 회계분야 연구와 금융기관 및 신용평가기관의 기업평가업무에서 중요한 지표로 사용되고 있음에도 불구하고 이에 대한 예측연구는 미비하다. 또한, 기존의 회계이익예측 연구에서 사용되는 시계열모형은 자기변수 영향만을 반영하여 예측치를 추정하므로 단일변량 모형수립에는 적합하지만 외부요소 영향을 반영하지 못하는 한계를 갖는다. 이러한 배경에서 본 연구는 동태적 패널(dynamic panel)모형을 이용하여 회계이익률을 예측한다. 동태적 패널모형은 자기변수 이외에도, 외생변수와 개별기업 효과를 반영하여 예측치를 추정하게 되어 시계열모형의 단점을 극복할 수 있다. 본 연구는 가동률지수, 생산자제품재고지수 및 3년 만기 회사채수익률을 외생변수로 하는 동태적 패널모형을 사용하여 매출액영업이익률과 매출액순이익률을 예측한다. 예측능력은 실제치와 예측치 차이로 측정되는 예측정확성, 그리고 예측치와 주식수익률의 관련성으로 측정되는 시장기대이익 대용치로서 적절성을 기준으로 랜덤웍(random work) 모형과 비교하여 평가한다. 검증결과에 의하면, 동태적 패널모형은 모든 예측대상 회계이익률에서 높은 예측정확성을 나타냈으나 시장기대이익 대용치로의 적절성에서는 우월성을 보여주지 못하였다. 이러한 검증결과는 표본기간, 기업규모 및 업종을 달리하여도 동일하였다. This study examines the forecasting ability of the dynamic panel model about accounting income ratios. The motive of a study stems from the following. First, although accounting income ratios are used as an important index in accounting study and practical business forecasting studies using them are rare. Second, time- series models used in the existing study have limits not verifying the relationship between dependent and independent variables, and consideration of the effect of external factors. The dynamic panel model can overcome those limits by considering the effect of the extraneous variable and individual company as well as auto-variable. We design the forecasting model using the dynamic panel model and select operating index, producer`s inventory index and 3year company bond returns as the extraneous variables. The forecasting objectives are the ratio of operating income to sales and the ratio of net income to sales. The forecasting ability is estimated by the relative superiority to random work model on the basis of forecast accuracy and proxies for market earnings expectations The results indicate that the dynamic panel model shows a higher degree of forecasting accuracy and does not provide a more proper investors` expectation income than the random work model. These results are robust in most years, firm size and industries.

동태적 패널모형을 이용한 중소기업의 회계이익 예측에 관한 연구

허영빈,심상규 한국중소기업학회 2003 中小企業硏究 Vol.25 No.2

본 연구는 동태적 패널모형을 이용하여 우리나라 중소기업의 회계이익을 예측하는 것이다. 실증분석은 제조업에 속하는 28, 835개 표본기업에 대하여 매출액순이익률 및 매출액영업이익률을 회계이익으로 정의하고, 고용경기실사지수, 산업생산능력지수 및 가동률지수를 외생변수로 선정하였다. 예측과정은 선정된 변수들의 5개년(1996-2000) 자료를 이용하여 예측모형을 수립하고, 그 예측모형에 의해 1001년도 회계이익을 예측한다. 예측정확성은 절대 예측오차(AFE)를 기준으로 랜덤웍(random work) 모형과 비교하여 평가한다. 실증분석결과, 동태적 패널모형은 매출액순이익률 및 매출액영업이익률 모두에서 랜덤웍 모형보다 높은 예측정확성을 보였다. 이 결과는 매출액영업이익률보다는 매출액순이익률에서, 그리고 소규모 업종에서도 높은 예측정확성을 보였다. The study attempts to forecasting small and medium businesses' accounting income using dynamic panel model. We define the ratio of net income to sales(RNS) and the ratio of operating income to sale(R0S) as the accounting income. To test empirically the forecasting ability of dynamic panel model. We design the forecasting model used employment business survey index and industry production ability index and operating ratio index as the surrogate of extraneous variables, and sample 28.836 manufacturing firms among the small and medium business of Korea. The panel data of sampled firms during 5 year( 1996-2000) is collected. The Wilcoxon rank sum analysis of absolute forecasting error(2001) is carried out to test the relative superiority of dynamic panel model to random work model. The results confirm that the forecasting ability of dynamic panel model is superior to that of random work model and dynamic panel model shows a higher forecasting ability in RNS(large and medium company) than ROS(smal1 company).

Dynamic Relationship Among Education Fiscal Expenditure, Economic Growth, and Human Capital in the Provincial Regions: Application of Standard Research Methodology and Suggestion

강기춘,곽영식 표준인증안전학회 2023 표준인증안전학회지 Vol.13 No.4

This study empirically analyzed the dynamic relationship among regional education fiscal expenditure, regional economic growth, and regional human capital by 16 cities and provinces in Korea from 1998 to 2021 to find “stylized facts” and how to use them to establish local fiscal policies. In addition to analyzing the 16 cities and provinces, the capital, non-capital, metropolitan-city, and provincial regions were analyzed and compared. The main contents of the study are as follows. We used panel data such as regional education fiscal expenditure, human capital, and economic growth to perform the panel unit root test, panel cointegration test, panel Granger causality test, and estimated the Panel Vector Error Correction (PVEC) model for impulse response and forecasting error variance decomposition based on the standard research methodology. The analysis results of this study are summarized as follows. First, as a result of the first and second-generation panel unit root tests, it was found that unit roots exist in all three variables. Second, as a result of the panel cointegration test, it was found that there was one independent cointegration relationship among the three variables. Third, we used the PVEC model according to the results of the panel unit root test and the panel cointegration test, and the PVEC model with a lag length of 4 was estimated. As a result of the panel Granger causality test, we found that the long-term causal relationship between regional education fiscal expenditure and regional economic growth to regional human capital exists. Fourth, according to the impulse response, the growth rate of the three variables is most affected by their shock. Fifth, regional education fiscal expenditure and regional human capital are limited but mutually explanatory. The mutual explanatory power of all three variables was more significant in the capital regions than in the non-capital regions and more significant in the provincial regions than in the metropolitan-city region. In this study, we obtained robust research results by applying all of the standard research methodologies used in the analysis using the VAR model. However, we need to utilize the characteristics of the panel data when the PVAR or PVEC model is used. We applied a methodology to analyze the entire region, capital region, non-capital region, metropolitan-city region, and provincial region. We compared the results and confirmed its usefulness. Therefore, we propose that this methodology be used as one of the standard research methodologies in future studies.

Dynamic responses analysis of P and S-FGM sandwich cylindrical shell panels using a new layerwise method

Abhilash Karakoti,Shashank Pandey,Vishesh Ranjan Kar 국제구조공학회 2021 Structural Engineering and Mechanics, An Int'l Jou Vol.80 No.4

This research work presents a comparison of the dynamic response of the functionally graded sandwich cylindrical shell panels (FGSCS) using a new layerwise method. The layerwise method developed assumes a first-order shear deformation theory (FSDT) for top and bottom facesheets and a third-order shear deformation theory for the core. The strain-displacement relation for FGSCS panels is obtained using Sander’s first approximation. Two different sandwich configurations are considered, one having a pure metallic core with top and bottom facesheets made of functionally graded material (FGM) and the other one having an FGM core with top and bottom facesheets made of pure ceramic and pure metal, respectively. Material properties of the FGM layers for the two configurations are varied along the thickness direction according to the power-law (P-FGM) and the sigmoid models (S-FGM) respectively. The newly developed layerwise finite element model in conjunction with Hamilton’s principle is employed to obtain the governing differential equation. Subsequently, the Newmark-Beta time integration scheme is used to obtain the dynamic response of P and S functionally graded sandwich cylindrical shell (P and S-FGSCS) panels for two configurations. The results obtained are first compared with the exact analytical results available in the literature. Numerical results are presented to investigate the effect of volume fraction index, loading conditions, core-to-facesheet thickness ratio, curvature ratio and boundary conditions on the transient response of P and S-FGSCS panels. The analysis reveals by selecting optimum parameters and gradation model, the amplitude and frequency of dynamic response of P and S-FGSCS panels can be controlled substantially.

공간패널모형을 활용한 절도 및 폭력범죄와 사회구조적 변인 간의 관계 분석

염윤호 한국형사정책연구원 2020 형사정책연구 Vol.123 No.-

This study examined the relationship between crime and social structural variables using a spatial panel dataset collected in Y district, X city from 2015 to 2017. A volume of study has analyzed such a relationship with different statistical tools but failed to consider both cross-sectional and longitudinal features inherent in criminal phenomena. Even panel data analysis models considering both aspects simultaneously failed to consider spatial dependence inherent in the spatial panel dataset. Thus, among various spatial panel data models, this study applied a ‘dynamic spatial Durbin model’ that simultaneously considers both spatial and temporal dependence within variables. In this process, this study analyzed the discriminatory effects of social structural variables on the two types of crime, theft and violent crime. As a result, this study found that each type of crime is temporally and spatially dependent, but the spatial dependence is partially or completely offset by temporal dependence. This indicates that crime in a specific time and space is influenced by crimes in the same space, but with different time rather than crimes in adjacent areas. Moreover, this study estimated that theft decreases as CCTV density, alcohol outlet density, and multi-family housing increase whereas violent crime decreases as population density and multi-family housing increase, and single-household decreases. Based on these results, this study suggested that customized crime prevention activities, such as the installation of CCTVs in the spatial and temporal hotspot of theft, be implemented depending on crime types and socioeconomic conditions. 본 연구는 X시 Y구의 집계구를 연구의 지역적 분석단위로 설정하고, 2015년∼2017년 수집된 공간패널 자료를 활용하여 범죄와 사회구조적 변인 간의 관계를 분석하였다. 사회구조적 관점에서 범죄 현상을 분석한 종래의 연구는 주로 횡단적 혹은 종단적 연구방법을 택일하거나, 두 측면을 동시에 고려할 수 있는 단순 패널 모형을 활용하더라도 자료에 내재한 공간적 종속성 문제를 해결하는 데에 한계가 있다. 이에, 본 연구는 다양한 공간패널모형 중, 종속 및 독립변수에 내재한 시공간적 종속성을 동시적으로 고려할 수 있는 동적 공간더빈 모형(dynamic spatial Durbin model)을 적용하여, 사회구조적 변인의 절도 및 폭력범죄에 대한 차별적 영향력을 분석하였다. 그 결과, 본 연구는 각 유형의 범죄는 시공간적으로 종속되어 있으나, 시간적 종속성은 동시적으로 존재하는 공간적 종속성의 일부 혹은 전부를 상쇄함을 확인하였다. 이는 특정 시공간에서의 범죄 발생은 인접지역의 공간가중된 영향력보다는 동일 공간에서 시차를 두고 발생한 범죄에 더 많은 영향을 받음을 의미한다. 한편, 본 연구는 외생변수로 측정한 CCTV 밀집도, 주류업소밀집도, 다세대주택 비율이 증가할수록 절도범죄가 감소함을 추정하였고, 인구밀도, 대세대주택 비율이 증가할수록 1인 가구 비율이 감소할수록 폭력범죄가 감소함을 추정하였다. 이러한 결과를 토대로, 절도범죄 다발지역에 CCTV를 집중적으로 설치하는 등 범죄유형 및 사회구조적 특성에 따라 개별화된 경찰활동을 시행할 것을 제안하였다.

열해석 모델 간략화 및 동적특성에 관한 연구

전형열(Hyoung Yoll Jun),김정훈(Jung-Hoon Kim) 한국전산유체공학회 2014 한국전산유체공학회지 Vol.19 No.4

A detailed satellite panel thermal model composed of more than thousands nodes can not be directly integrated into a spacecraft thermal model due to its node size and the limitation of commercial satellite thermal analysis programs. For the integration of the panel into the satellite thermal model, a reduced thermal model having proper accuracy is required. A thermal model reduction method was developed and validated by using a geostationary satellite panel. The temperature differences of main components between the detailed and the reduced thermal model were less than 1 in steady state analysis. Also, the dynamic responses of the detailed and the reduced thermal model show very similar trends. Thus, the developed reduction method can be applicable to actual satellite thermal design and analysis with resonable accuracy and convenience.

An accurate and simple model for flexible satellites for three-dimensional studies

Shahram Shahriari,Shahram Azadi,Majid M. Moghaddam 대한기계학회 2010 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.24 No.6

In this paper, an accurate and simple model of a satellite with two flexible solar panels for three-dimensional dynamic studies is proposed and compared with other models. In the proposed model, each solar panel is assumed to be rigid and attached to the satellite body via a simple hinge, a torsional spring, and a torsional damper. Kane's method is utilized to derive the equations of motion. The model of flexible satellite with the assumption of Euler-Bernoulli beam for the solar panels, generally used in the literature, has been introduced for comparison. A comprehensive model of flexible satellite, considering solar panels as flexible and finite element panels, has been provided in ADAMS environment as a reference when comparing the two mentioned models. The Euler-Bernoulli model does not appropriately simulate the three-dimensional motion of satellite. Conversely, the hinged, rigid-panel model proposed in this paper provides suitable results in both two- and three-dimensional maneuvers.

Empirical likelihood for spatial dynamic panel data models

Li Yinghua,Qin Yongsong 한국통계학회 2022 Journal of the Korean Statistical Society Vol.51 No.2

Spatial dynamic panel data (SDPD) models have received great attention in economics in recent 10 years. Existing approaches for the estimation and test of SDPD models are quasi-maximum likelihood (QML) approach and generalized method of moments (GMM). In this article, we introduce the empirical likelihood (EL) method to the statistical inference for SDPD models. The EL ratio statistics are constructed for the parameters of spatial dynamic panel data models. It is shown that the limiting distributions of the empirical likelihood ratio statistics are chi-squared distributions, which are used to construct confdence regions for the parameters of the models. Simulation results show that the EL based confdence regions outperform the normal approximation based confdence regions.

동태패널모형에 의한 한국 인바운드 관광수요 분석

신범철 한국관광학회 2013 관광학연구 Vol.37 No.1

This paper empirically investigates determinants of inbound tourism demand for Korea using a dynamic panel data model. The empirical analysis uses the panel data set for the 34 countries over the period 1995-2009, estimating the dynamic panel model by the Generalized Method of Moment to control for the endogeneity of the lagged dependent variable. The endogeneity bias could be caused by the OLS estimation of the model which includes the lagged dependent variable as a regressor. Empirical results are as follows. First, the estimated coefficients of the lagged dependent variable are found to be statistically significant, which may reflect a high degree of consumer loyalty or an important effect of 'word of mouth' in determining international tourism demand for Korea. Second, empirical results show that the estimated coefficient of income elasticity of tourism demand to Korea should be positively significant, supporting the results of the previous studies. Third, the cost of tourism to Korea turns out to be statistically significant and thus an important factor in determining tourism demand. Finally, In contrast to theory prediction that foreign exchange rate can have positive effects on tourism demand, however, there is no robust evidence that nominal exchange rate should lead to an increase in tourism demand.