• Journal of the Korean Data and Information Science Society
• /
• v.20 no.5
• /
• pp.765-777
• /
• 2009

Our study aimed to illustrate long term trend in 10 micrometer particular matters excluding confounding effect. Daily 10 micrometer particular matters data were measured in 27 places and meteorological data (maximum temperature, humidity and maximum wind speed, solar radiation) were obtained from the national institute of environmental research for the period from January, 1996 to December 2000. To estimate the increasing and decreasing long term trend in a set of observed data, set up the model. The model included regression spline smooth function on the time and meteorological factors to capture the seasonal time trend and any possible nonlinear relationship. The result was estimated to decrease slightly after adjusting for meteorological factors and seasonal time trend.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.351-354
• /
• 2018

본 연구에서는 일 증발접시 증발량 모델링을 위한 다변량 적응 회귀 스플라인 (multivariate adaptive regression splines, MARS) 모델의 성능을 평가하였다. 모델 입력변수 집합은 부산 관측소 (기상청)로부터 수집된 기상자료를 활용하여 증발접시 증발량과의 상관성이 높은 변수들의 조합으로 구성되었으며, 일사량, 일조시간, 평균지상온도, 최대기온의 조합으로 구성된 세 가지 입력집합이 결정되었다. MARS 모델의 성능은 네 가지의 모델성능평가지표를 활용하여 정량적으로 산출되었으며, 그 결과를 인공신경망 (artificial neural network, ANN) 모델과 비교하였다. 입력변수로서 일사량 및 일조시간을 가지는 Set 1의 경우 MARS1 모델이 ANN1 모델보다 우수한 성능을 나타내었으며, Set 2 (일사량, 일조시간, 평균지상온도)의 경우 ANN2 모델, Set 3 (일사량, 일조시간, 평균지상온도, 최대기온)의 경우 MARS3 모델이 상대적으로 우수한 모델 성능을 나타내었다. 모든 분석 모델들을 비교하였을 때, MARS3, ANN2, ANN3, MARS2, MARS1, ANN1 모델의 순서로 우수한 모델 성능을 나타내었으며, 특히 MARS3 모델은 CE = 0.790, $r^2=0.800$, RMSE = 0.762, MAE = 0.587로서 가장 우수한 일 증발접시 증발량 모델링 성능을 나타내었다. 따라서 본 연구에서 적용한 MARS 모델은 지상관측 기상자료를 활용한 일 증발접시 증발량 모델링에서 효과적인 대안이 될 수 있을 것으로 판단된다.

• The Korean Journal of Applied Statistics
• /
• v.31 no.3
• /
• pp.343-352
• /
• 2018

We can use quantile regression and expectile regression analysis to estimate trends in extreme regions as well as the average trends of response variables in given explanatory variables. In this paper, we compare the performance between the parametric and nonparametric methods for expectile regression. We introduce each estimation method and analyze through various simulations and the application to real data. The nonparametric model showed better results if the model is complex and difficult to deduce the relationship between variables. The use of nonparametric methods can be recommended in terms of the difficulty of assuming a parametric model in expectile regression.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.1
• /
• pp.89-96
• /
• 2009

We examined the characteristics of temperature variation in Seoul between 1961 to 2008 using the spectral heteroscedastic model. The mean function in the propsed model explains the season effect using periodic functions and the overall increase using the quadratic regression spline. The variance function also had periodic functions to explain the seasonality of variance. We found that there has been annual mean temperature increase by about $1.5^{\circ}C$ for the last 48 years. The increase of annual mean temperature was mainly caused by the increase in winter, which made the amplitude decreased.

• Land and Housing Review
• /
• v.12 no.4
• /
• pp.31-40
• /
• 2021

In the present article we examine life-cycle housing demand for Korea. Distinguished in this work from prior research is the consideration of non-monocinity in the life-cycle housing demand. To this end, we adopt spline logistic regression models. Our findings suggest that life-cyclicity is most clear in Korean housing demand; namely, 1) small (mid-large) house ownership falls (grows) dramatically as households age into middle aged; 2) middle aged households do not participate in the rental or purchase market actively; 3) elderly population does not dispose of their housing to the same extent as younger generations acquire housing.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.3
• /
• pp.114-122
• /
• 2014

Sensor fusion is the one of the main research topics. It offers the highly reliable estimation of vehicle movement by processing and mixing several sensor outputs. But unfortunately, every sensor has drift which degrades the performance of sensor. It means a single degraded sensor output may affect whole sensor fusion system. Drift in most research is ideally assumed to be zero because it's usually a nonlinear model and has sample variation. Plus, it's very difficult for the acceleration to separate drift from the output signal since it contains many contributors such as vehicle acceleration, slope angle, pitch angle, surface condition and so on. In this paper, modified spline interpolation is introduced as a dynamic temperature compensation method covering sample variation. Using the last known output and the first initial output is suggested to build and update compensation factor. When the system has more compensation data, the system will have better performance of compensated output because of the regression compensation model. The performance of the dynamic temperature compensation system is evaluated by measuring offset drift between with and without the compensation.

• Journal of Korea Multimedia Society
• /
• v.12 no.5
• /
• pp.633-643
• /
• 2009

We propose a color transfer method that used color contrast based templates to express the visual difference clearly between objects, while remaining the quality of the input image. Our algorithm employs colors of both the input image and template distributed on the $a^{\ast}b^{\ast}$chrominance plane of CIE $L^{\ast}a^{\ast}b^{\ast}$color space. The templates are made by considering the effect of color contrast and have the shape of either a line or a curve represented color distribution of the basic colors based gradation image. These tempates can be modeled on spline curves. We also generate simply new templates with the different basic colors by moving the control points of that curve. The color transfer method using the templates is done through a regressive analysis and color matching. We maintained color coherence of the input image by transforming similarly the color distribution of an input image to the one of templates.

• The Korean Journal of Applied Statistics
• /
• v.29 no.7
• /
• pp.1295-1309
• /
• 2016

This paper is to reproduce the result of Kim et al. (2014) by deriving a benchmark dose lower bound (BMDL) of lead based on the 2005 cohort data set of Children's Health and Environmental Research (CHEER) data set. The ADHD rating scales in the 2005 cohort were not consistent along the three follow-ups since two different ADHD rating scales were used in the cohort. We first unified the ADHD rating scales in the 2005 cohort by deriving a conversion formula using a penalized linear spline. We then constructed two linear mixed models for the 2005 cohort which reflected the longitudinal characteristics of the data set. The first model introduced the random intercept and the random slope terms and the second model assumed the first order autoregressive structure of the error term. Using these two models, we derived the BMDLs of lead and reconfirmed the "regression to the mean" nature of the ADHD score discovered by Kim et al. (2014). We also noticed that there was a definite difference between the sampling distributions of the two cohorts. As a result, taking this difference into account, we were able to obtain the consistent result with Kim et al. (2014).

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.543-559
• /
• 2019

Data often include missing values due to various reasons. If the missing data mechanism is not MCAR, analysis based on fully observed cases may an estimation cause bias and decrease the precision of the estimate since partially observed cases are excluded. Especially when data include many variables, missing values cause more serious problems. Many imputation techniques are suggested to overcome this difficulty. However, imputation methods using parametric models may not fit well with real data which do not satisfy model assumptions. In this study, we review imputation methods using nonlinear models such as kernel, resampling, and spline methods which are robust on model assumptions. In addition, we suggest utilizing imputation classes to improve imputation accuracy or adding random errors to correctly estimate the variance of the estimates in nonlinear imputation models. Performances of imputation methods using nonlinear models are compared under various simulated data settings. Simulation results indicate that the performances of imputation methods are different as data settings change. However, imputation based on the kernel regression or the penalized spline performs better in most situations. Utilizing imputation classes or adding random errors improves the performance of imputation methods using nonlinear models.

• The Korean Journal of Applied Statistics
• /
• v.24 no.3
• /
• pp.465-475
• /
• 2011

In this paper, we have considered the problems of the estimation of the gross areas of a factory site relating to the areas of industrial complex lands based on a statistical forecasting model and the results of a sampling survey. In respect to the data of a gross areas of a factory site, we have only the sizes from 1981-2003. In 2009, the Korea Industrial Complex Corp. conducted a sampling survey to estimate its bulk size, and investigate the demands of its sizes for the next five years. In this study, we have adopted the sampling survey results, and have created a statistical growth model for the gross areas of a factory site to improve the prediction for the areas of a factory site. The three-different parts of data: the results of areas of a factory site by Korea National Statistical Office, imputation results by the statistical forecasting model, and sampling survey results have used as the basis for analysis. The combination of the three-different parts of data has created a new forecasting value of the areas of a factory site through the spline smoothing method.