• The Korean Journal of Applied Statistics
• /
• v.20 no.3
• /
• pp.561-571
• /
• 2007

Local linear regression estimator is the most widely used nonparametric regression estimator which has a number of advantages over the traditional kernel estimators. It is well known that local linear estimator can produce erratic result in sparse regions in the realization of the design and the interpolation method of Hall and Turlach (1997) is the very efficient way to resolve this problem. However, it has been never pointed out that Hall and Turlach's interpolation method is very sensitive to outliers. In this paper, we propose the robust version of the interpolation method for adapting to sparse design. The finite sample properties of the method is compared with Hall and Turlach's method by the simulation study.

• The Korean Journal of Applied Statistics
• /
• v.33 no.2
• /
• pp.147-160
• /
• 2020

In this paper, we study an algorithm that automatically determines the orders of past observations and conditional mean values that play an important role in count time series models. Based on the orders of the ARIMA model, the algorithm constitutes the order candidates group for time series generalized linear models and selects the final model based on information criterion among the combinations of the order candidates group. To evaluate the proposed algorithm, we perform small simulations and empirical analysis according to underlying models and time series as well as compare forecasting performances with the ARIMA model. The results of the comparison confirm that the time series generalized linear model offers better performance than the ARIMA model for the count time series analysis. In addition, the empirical analysis shows better performance in mid and long term forecasting than the ARIMA model.

• Journal of Korean Society for Geospatial Information Science
• /
• v.12 no.2 s.29
• /
• pp.67-71
• /
• 2004

Increasing number and acquisition rate of satellite imagery promoted researches related with DEM generation based on satellite imagery. SPOT image gave us advantage to generate DEM which covers wide area of $60km{\times}60km$. In the case of rigorous sensor model of SPOT imagery, ephemeris data and several ground control points are need and requires arduous computational costs to produce DEM. In this study, using alternative sensor model based on Direct Linear Transform, we generated DEM using small number of ground control points. As a result, it was possible to acquire the DEM with suitable accuracy.

• Communications for Statistical Applications and Methods
• /
• v.5 no.3
• /
• pp.599-605
• /
• 1998

본 연구에서는 단순구조 순환신경망을 이용한 신경망예측과 전통적인 시계열예측 방법을 이용하여, 순환변동이 있는 시계열자료의 단기예측 오차를 비교한다. 순환신경망모형의 입력자료를 변화시키는 개선된 학습방법을 적용하여 시계열자료를 학습하고, 신경망예측의 결과는 선형 AR(9)모형, 비선형 SETAR모형 그리고 이들의 결합모형을 이용한 예측결과와 비교한다. 실증분석에 적용된 시계열자료는 1700년부터 1987년 까지의 태양흑점 자료이며 예측에 이용된 검정자료는 1980년부터 8년 간의 자료이다.

• The Korean Journal of Applied Statistics
• /
• v.31 no.4
• /
• pp.475-484
• /
• 2018

Gamma generalized linear models are useful for non-negative and skewed responses. However, these models have received less attention than Poisson and binomial generalized linear models. In particular, hypothesis testing for the significance of regression coefficients has not been thoroughly studied. In this paper we assess the performance of various test statistics for gamma generalized linear models based on numerical studies. Our results show that the likelihood ratio test and F-type test are generally recommended and that the partial deviance test should be avoided in practice.

• Journal of Korean Society of Transportation
• /
• v.28 no.5
• /
• pp.141-153
• /
• 2010

The study is about the development of operating speed prediction models aimed for an evaluation of design consistency of four lane rural roads. The main differences of this study relative to previous research are the method of data collection and classification of road alignments. The previous studies collected speed data at several points in the horizontal curve and approaching tangent. This method of collection is based on the assumption that acceleration and deceleration only occurs at horizontal tangents and the speed is kept constant at horizontal curves. However, this assumption leads to an unreliable speed estimation, so drivers' behavior is not well represented. Contrary to the previous approach, speed data were collected with one and data analysis using a speed profile is made for data selection before building final models. A total of six speed prediction models were made according to the combination of horizontal and vertical alignments. The study predicts that the speed data analysis and selection for model building employed in this study can improve the prediction accuracy of models and be useful to analyze drivers' speed behavior in a more detailed way. Furthermore, it is expected that the operating speed prediction models can help complement the current design-speed-based guidelines, so more benefits to drivers as real road users, rather than engineers or decision makers, can be achieved.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.315-319
• /
• 2022

This study investigates longitudinal writing development in terms of syntactic complexity using linear mixed effects (LME) model. This study employs essays written by four case study participants. Participants voluntarily wrote essays outside of the classroom and submitted the first and second drafts, after reflecting on the automated writing evaluation feedback (i.e., Criterion) every month over one year. A total of 48 first drafts were analyzed and syntactic complexity features were selected from Syntactic Complexity Analyzer. Results of LME showed that there was a significant positive linear relationship between time and mean length of T-unit and also between time and the ratio of dependent clauses to independent clauses, indicating that case study participants wrote longer T-units and also a higher proportion of dependent clauses over one year.

• The Korean Journal of Applied Statistics
• /
• v.14 no.2
• /
• pp.321-332
• /
• 2001

본 논문에서는 반응변수가 두 가지의 값을 갖는 회귀분석에 적용할 수 있는 사영추적회귀를 고려하였다. 회귀모형에 필요한 설명변수들의 선형결합이 하나이고 연결함수의 형태를 사전에 알지 못한다는 가정하에서 모의담금질 기법을 이용하여 모형에 필요한 선형결합을 찾는 알고리즘을 제시하였다. 이진 반응변수의 경우에는 평활모수의 값에 따라 잔차이탈도함수의 반응표면이 단봉의 형태를 갖지 않는 경우가 있어 비동질적 마코프체인을 이용한 모의담금질 기법을 적용하면 효율적으로 선형결합을 탐색할 수 있다.

• Proceedings of the Korean Society of Coastal and Ocean Engineers Conference
• /
• 2003.08a
• /
• pp.240-244
• /
• 2003

파랑의 변형 가운데 천수, 굴절, 회절, 반사를 예측하는 수학적 모형은 크게 두 가지 유형으로 나눌 수 있는데, 첫 번째로 파형경사인 ha(k：파수. $\alpha$：진폭)를 비선형의 매개변수로 하는 Stokes 파랑식이 있고, 두 번째로 상대파고인 $\alpha$/h를 비선형의 매개변수로 하고 상대수심인 kh를 분산성의 매개변수로 하는 천수방정식(Shallow water equation)이 있다. 파랑의 변형 가운데 천수, 굴절만을 예측하고 회절, 반사를 예측하지 못하는 수학적 모형으로는 에너지 이송방정식이 있다. (중략)

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.6
• /
• pp.1585-1592
• /
• 2016

Estimation of winning percentage in baseball has always been particularly interesting to many baseball fans. We have fitted models including linear regression and Pythagorean formula to the Korean baseball data of seasons from 1982 to 2015. Using RMSE criterion for both the linear formula and the Pythagorean formula, we compared two models in predicting the actual winning percentage. Pythagorean expectation is superior to linear formula when there is either high or low winning percentage. Two methods yield very similar efficiencies when the actual winning percentage is about 50%. To understand and use for estimating winning percentage, it is easier linear formula as estimated equations.