• The Korean Journal of Applied Statistics
• /
• v.10 no.2
• /
• pp.241-251
• /
• 1997

Several studies have bee down on the work of dynamic graphical methods for regression diagnostics. The main propose of the methods were to investigate (1) the effects of change of data, or (2) the effects of change of regression coefficients on the regression models. But, by contrast, we can also investigate the effects of change of regression residuals on the regression model. This method can be used in fitting better a certain set of observations to a regression model than the other observations. Our research team approaches regression diagnostics by using dynamic graphics (REDS), and we introduce REDS in this thesis.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.609-617
• /
• 2006

A new fuzzy c-regression algorithm for switching regression analysis is presented, which combines fuzzy c-means clustering and least squares support vector machine. This algorithm can detect outliers in switching regression models while yielding the simultaneous estimates of the associated parameters together with a fuzzy c-partitions of data. It can be employed for the model-free nonlinear regression which does not assume the underlying form of the regression function. We illustrate the new approach with some numerical examples that show how it can be used to fit switching regression models to almost all types of mixed data.

• Communications for Statistical Applications and Methods
• /
• v.26 no.6
• /
• pp.539-556
• /
• 2019

This paper derive a method to solve change point regression problems via a process for obtaining consequential results using properties of a difference-based intercept estimator first introduced by Park and Kim (Communications in Statistics - Theory Methods, 2019) for outlier detection in multiple linear regression models. We describe the statistical properties of the difference-based regression model in a piecewise simple linear regression model and then propose an efficient algorithm for change point detection. We illustrate the merits of our proposed method in the light of comparison with several existing methods under simulation studies and real data analysis. This methodology is quite valuable, "no matter what regression lines" and "no matter what the number of change points".

• Journal of the Ergonomics Society of Korea
• /
• v.22 no.4
• /
• pp.59-78
• /
• 2003

Most regression models of anthropometric variables use stature and/or weight as regressors; however, these 'flat' regression models result in large errors for anthropometric variables having low correlations with the regressors. To develop more accurate regression models for anthropometric variables, this study proposed a method to estimate anthropometric variables in a hierarchical manner based on the relationships among the variables and a process to develop and improve corresponding regression models. By applying the proposed approach, a hierarchical estimation structure was constructed for 59 anthropometric variables selected for the occupant package design of a passenger car and corresponding regression models were developed with the 1988 US Army anthropometric survey data. The hierarchical regression models were compared with the corresponding flat regression models in terms of accuracy. As results, the standard errors of the hierarchical regression models decreased by 28% (4.3mm) on average compared with those of the flat models.

• Communications for Statistical Applications and Methods
• /
• v.22 no.2
• /
• pp.173-180
• /
• 2015

We propose a selection procedure of principal components in principal component regression. Our method selects principal components using variable selection procedures instead of a small subset of major principal components in principal component regression. Our procedure consists of two steps to improve estimation and prediction. First, we reduce the number of principal components using the conventional principal component regression to yield the set of candidate principal components and then select principal components among the candidate set using sparse regression techniques. The performance of our proposals is demonstrated numerically and compared with the typical dimension reduction approaches (including principal component regression and partial least square regression) using synthetic and real datasets.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.6
• /
• pp.1319-1325
• /
• 2010

Quantile regression provides a more complete statistical analysis of the stochastic relationships among random variables. Sometimes quantile functions estimated at different orders can cross each other. We propose a new non-crossing quantile regression method applying support vector median regression to restricted regression quantile, restricted support vector quantile regression. The proposed method provides a satisfying solution to estimating non-crossing quantile functions when multiple quantiles for high dimensional data are needed. We also present the model selection method that employs cross validation techniques for choosing the parameters which aect the performance of the proposed method. One real example and a simulated example are provided to show the usefulness of the proposed method.

• Communications for Statistical Applications and Methods
• /
• v.28 no.2
• /
• pp.205-215
• /
• 2021

Sufficient dimension reduction is useful dimension reduction tool in regression, and sliced inverse regression (Li, 1991) is one of the most popular sufficient dimension reduction methodologies. In spite of its popularity, it is known to be sensitive to the number of slices. To overcome this shortcoming, the so-called fused sliced inverse regression is proposed by Cook and Zhang (2014). Unfortunately, the two existing methods do not have the direction application to large p-small n regression, in which the dimension reduction is desperately needed. In this paper, we newly propose seeded sliced inverse regression and seeded fused sliced inverse regression to overcome this deficit by adopting iterative projection approach (Cook et al., 2007). Numerical studies are presented to study their asymptotic estimation behaviors, and real data analysis confirms their practical usefulness in high-dimensional data analysis.

• Journal of Aerospace System Engineering
• /
• v.2 no.4
• /
• pp.1-6
• /
• 2008

In generally, the regression rate was expressed with average value and oxidizer mass flux in hybrid propulsion system. This can not represent the local value of regression rate along with oxidizer flow direction. In this study, experimental studies were performed with Separation method and Cutting method for measure local regression rate. In axial injection, the local regression rate decreases rapidly with axial location near entrance and increases with axial direction from the leading edge and the empirical formula for local regression rate with function of oxidizer mass flux and location was derived. Swirl injection regression rate has higher value at the leading edge of the fuel and comparatively uniform regression rate at the downstream. Overall regression rate of swirl injection is higher increased about 54 % than regression rate of axial injection.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.4
• /
• pp.643-648
• /
• 2012

There are lots of analysis to determine the relation between dependent variable and explanatory variables. Often the regression analysis is used to do this, and we can analyze the how much the explanatory variable can be related with dependent variable and how much the regression model can explain the data. But the validation check of regression model is usually determined by coefficient of determination. We should check the validation of regression coefficient with different methods. This paper introduces the method for validation check the regression coefficient using the jackknife regression and bootstrap regression in clinical data.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.2
• /
• pp.327-344
• /
• 2007

Ridge partial least squares regression (RPLS) is a regression method which can be obtained by combining ridge regression and partial least squares regression and is intended to provide better predictive ability and less sensitive to overfitting. In this paper, explicit expressions for the shrinkage factor of RPLS are developed. The structure of the shrinkage factor is explored and compared with those of other biased regression methods, such as ridge regression, principal component regression, ridge principal component regression, and partial least squares regression using a near infrared data set.