• Communications for Statistical Applications and Methods
• /
• 제8권2호
• /
• pp.327-336
• /
• 2001

This work concerns estimating a regression function, which is not linear, using aggregate data. In much of the empirical research, data are aggregated for various reasons before statistical analysis. In a traditional parametric approach, a linear estimation of the non-linear function with aggregate data can result in unstable estimators of the parameters. More serious consequence is the bias in the estimation of the non-linear function. The approach we employ is the kernel regression smoothing. We describe the conditions when the aggregate data can be used to estimate the regression function efficiently. Numerical examples will illustrate our findings.

• Communications for Statistical Applications and Methods
• /
• 제10권1호
• /
• pp.31-38
• /
• 2003

A simple method is proposed to detect the number of change points and test the location and size of multiple change points with jump discontinuities in an otherwise smooth regression model. The proposed estimators are based on a local linear regression fit by the comparison of left and right one-side kernel smoother. Our proposed methodology is explained and applied to real data and simulated data.

• 전기학회논문지
• /
• 제56권12호
• /
• pp.2265-2267
• /
• 2007

The purpose of this work is to compare the local fitting and global fitting approaches while applying regression model to the PTT-BP data for the prediction of exercise blood pressures. We used linear and nonlinear regression models to represent the PTT-BP relationship during exercise. PTT-BP data were acquired both under resting state and also after cycling exercise with several load conditions. PTT was calculated as the time between R-peak of ECG and the peak of differential photo-plethysmogram. For the identification of the regression models, we used local fitting which used only the resting state data and global fitting which used the whole region of data including exercise BP. The results showed that the global fitting was superior to the local fitting in terms of the coefficient of determination and the RMS (root mean square) error between the experimental and estimated BP. The nonlinear regression model which used global fitting showed slightly better performance than the linear one (no significant difference). We confirmed that the wide-range of data is required for the regression model to appropriately predict the exercise BP.

• 전기학회논문지
• /
• 제65권5호
• /
• pp.851-856
• /
• 2016

Wind speed is heavily fluctuated and quite local than other weather elements. It is difficult to improve the accuracy of prediction only in a numerical prediction model. An MOS (Model Output Statistics) technique is used to correct the systematic errors of the model using a statistical data analysis. The Most of previous MOS has used a linear regression model for weather prediction, but it is hard to manage an irregular nature of prediction of wind speed. In order to solve the problem, a nonlinear regression method using SVR (Support Vector Regression) is introduced for a development of MOS for wind speed prediction. Experiments are performed for KLAPS (Korea Local Analysis and Prediction System) re-analysis data from 2007 to 2013 year for Jeju Island and Busan area in South Korea. The MLR and SVR based linear and nonlinear methods are compared to each other for prediction accuracy of wind speed. Also, the comparison experiments are executed for the variation in the number of UM elements.

• 품질경영학회지
• /
• 제28권2호
• /
• pp.57-69
• /
• 2000

This paper discusses the local influence approach to the linear regression models with AR(2) errors. Diagnostics for the linear regression models with AR(2) errors are proposed and developed when simultaneous perturbations of the response vector are allowed- That is, the direction of maximum curvature of local influence analysis is obtained by studying the curvature of a surface associated with the overall discrepancy measure.

• 응용통계연구
• /
• 제20권3호
• /
• pp.561-571
• /
• 2007

국소선형회귀모형의 추정량은 좋은 특성을 가지고 있는 추정량으로서 가장 흔히 사용되는 비모수적 회귀모형의 추정량이라고 하겠다. 이러한 국소선형 추정량이 자료가 희박한 구간에서는 심하게 왜곡된 추정결과를 보이는 문제가 있으며, Hall과 Turlach(1997)이 제안한 선형보간법이 이러한 문제에 대한 매우 효과적인 해결방안이라는 것은 잘 알려진 사실이다. 그러나 Hall과 Turlach가 제안한 선형보간법이 이상값에 매우 취약하다는 사실은 아직 지적된 적이 없는 문제이다. 이 논문에서는 이상값의 영향력을 감소시킬 수 있는 수정된 선형보간법에 의한 유사자료의 생성방법을 제안하고, 그 특성을 모의실험을 통하여 기존의 방법과 비교하였다.

• Communications for Statistical Applications and Methods
• /
• 제13권2호
• /
• pp.267-272
• /
• 2006

A procedure for selecting regressors in the linear regression model is suggested using local influence approach. Under an appropriate perturbation scheme, the effect of perturbation of regressors on the profile log-likelihood displacement is assessed for variable selection. A numerical example is provided for illustration.

• Journal of the Korean Statistical Society
• /
• 제31권2호
• /
• pp.237-250
• /
• 2002

Motivated by Cook's (1986) assessment of local influence by investigating the curvature of a surface associated with the overall discrepancy measure, this paper extends this idea to the linear regression model with AR(p) disturbances. Diagnostic for the linear regression models with AR(p) disturbances are discussed when simultaneous perturbations of the response vector are allowed. For the derived criterion, numerical studies demonstrate routine application of this work.

• Communications for Statistical Applications and Methods
• /
• 제13권2호
• /
• pp.379-387
• /
• 2006

Local polynomial regression is widely used because of good properties such as such as the adaptation to various types of designs, the absence of boundary effects and minimax efficiency Choi and Hall (1998) proposed an estimator of regression function using a convex combination idea. They showed that a convex combination of three local linear estimators produces an estimator which has the same order of bias as a local cubic smoother. In this paper we suggest another estimator of regression function based on a convex combination of five local constant estimates. It turned out that this estimator has the same order of bias as a local cubic smoother.

• Communications for Statistical Applications and Methods
• /
• 제7권2호
• /
• pp.574-574
• /
• 2000

Consider the problem of estimating regression function from a set of data which is contaminated by a long-tailed error distribution. The linear smoother is a kind of a local weighted average of response, so it is not robust against outliers. The kernel M-smoother and the lowess attain robustness against outliers by down-weighting outliers. However, the kernel M-smoother and the lowess requires the iteration for computing the robustness weights, and as Wang and Scott(1994) pointed out, the requirement of iteration is not a desirable property. In this article, we propose the robust nonparametic regression method which does not require the iteration. Robustness can be achieved not only by down-weighting outliers but also by transforming outliers. The rank transformation is a simple procedure where the data are replaced by their corresponding ranks. Iman and Conover(1979) showed the fact that the rank transformation is a robust and powerful procedure in the linear regression. In this paper, we show that we can also use the rank transformation to nonparametric regression to achieve the robustness.