• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.661-668
• /
• 2006

There have been some controversies on the use of the coefficient of determination for linear no-intercept model. One definition of the coefficient of determination, $R^2={\sum}\;{\widehat{y^2}}\;/\;{\sum}\;y^2$, is being widely accepted only for linear no-intercept models though Kvalseth (1985) demonstrated some possible pitfalls in using such $R^2$. Main objective of this note is to report that $R^2$ is not a desirable measure of fit for the no-intercept linear model. In fact it is found that mean square error(MSE) could replace $R^2$ efficiently in most cases where selection of no-intercept model is at issue.

• The Korean Journal of Applied Statistics
• /
• v.19 no.3
• /
• pp.545-554
• /
• 2006

We suggest a method for generating multidimensional random tables based on the log-linear models. A linear combination approach by Lee(1997) is applied to get the joint distribution with the well known Pearson chi-squared statistics. We can generate completely associated joint distributions which have the fixed association among three variables by using the suggested method. Therefore the method can be extended to more higher dimension than the three dimensional tables.

• The Korean Journal of Applied Statistics
• /
• v.21 no.1
• /
• pp.169-176
• /
• 2008

We explore the structure and usefulness of three dimensional CERES plot as a basic tool for dealing with curvature as a function of the new predictors in generalized linear models. If predictors have nonlinear effects and there are nonlinear relationships among the predictors, the partial residual plot is not able to display the correct functional form of the predictors. Unlike this plots, the CERES plot can show the correct form. This is illustrated by simulated data.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.213-222
• /
• 2002

The 3-hour-interval prediction of ground-level temperature up to +45 hours in Seoul area is performed using dynamic linear models(DLM). Numerical outputs and observations we used as input values of DLM. According to compare DLM forecasts to RDAPS forecasts using RMSE, DLM improve the accuracy of prediction and systematic error of numerical model outputs are eliminated by DLM.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.04a
• /
• pp.290-293
• /
• 2000

Knowledge discovery refers to the overall process of discovering useful knowledge from data. The linear programming model is a special form of useful knowledge that is embedded in a database. Since formulating models from scratch requires knowledge-intensive efforts, knowledge-based formulation support systems have been proposed in the DSS area. However, they rely on the strict assumption that sufficient domain knowledge should already be captured as a specific knowledge representation form. Hence, the purpose of this paper is to propose a methodology that finds useful knowledge on building linear programming models from a database. The methodology consists of two parts. The first part is to find s first-cut model based on a data dictionary. To do so, we applied the GPS algorithm. The second part is to discover a second-cut model by applying neural network technique. An illustrative example is described to show the feasibility of the proposed methodology.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.25 no.3
• /
• pp.91-107
• /
• 2000

The linear programming model is a special form of useful knowledge that is embedded in a database. Since formulating models from scratch requires knowledge-intensive efforts, knowledge-based formulation support systems have been proposed in the Decision Support Systems area. However, they rely on the assumption that sufficient domain knowledge should already be captured as a specific knowledge representation form. Hence, the purpose of this paper is to propose a methodology that finds useful knowledge on building linear programming models from a database. The methodology consists of two parts. The first part is to find s first-cut model based on a data dictionary. To do so, we applied the General Problem Solver(GPS) algorithm. The second part is to discover a second-cut model by applying neural network technique. An illustrative example is described to show the feasibility of the proposed methodology.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.18 no.4
• /
• pp.21-29
• /
• 2010

The main purpose of this study is to obtain linear models for the design of automatic flight controller in order to operate the Light Sport Aircraft as unmanned air vehicle. Flight test equipments installed on the aircraft to acquire flight test data are described and maneuvers for practical speed calibration are introduced. Parameters for the linear models of lateral and longitudinal motion are estimated by the Output error method as well as trim data analysis using the flight test data. Simulated data using the estimated parameters is shown to agree well with the measurement data. Estimated parameters obtained for several flight conditions can be used to improve the aerodynamic database of the simulation program.

• International Journal of Aeronautical and Space Sciences
• /
• v.11 no.2
• /
• pp.131-135
• /
• 2010

We report on the design of a three-axis missile autopilot using multi-objective control synthesis via linear matrix inequality techniques. This autopilot design guarantees $H_2/H_{\infty}$ performance criteria for a set of finite linear models. These models are linearized at different aerodynamic roll angle conditions over the flight envelope to capture uncertainties that occur in the high-angle-of-attack regime. Simulation results are presented for different aerodynamic roll angle variations and show that the performance of the controller is very satisfactory.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.759-768
• /
• 2011

Tree algorithms have been widely developed for regression problems. One of the good features of a regression tree is the flexibility of fitting because it can correctly capture the nonlinearity of data well. Especially, data with sudden structural breaks such as the price of oil and exchange rates could be fitted well with a simple mixture of a few piecewise linear regression models. Now that split points are determined by chi-squared statistics related with residuals from fitting piecewise linear models and the split variable is chosen by an objective criterion, we can get a quite reasonable fitting result which goes in line with the visual interpretation of data. The piecewise linear regression by a regression tree can be used as a good fitting method, and can be applied to a dataset with much fluctuation.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.209-216
• /
• 2015

Quantile regression models with covariate measurement errors have received a great deal of attention in both the theoretical and the applied statistical literature. A lot of effort has been devoted to develop effective estimation methods for such quantile regression models. In this paper we propose the partially linear support vector orthogonal quantile regression model in the presence of covariate measurement errors. We also provide a generalized approximate cross-validation method for choosing the hyperparameters and the ratios of the error variances which affect the performance of the proposed model. The proposed model is evaluated through simulations.