• Proceedings of the Korean Statistical Society Conference
• /
• 2005.11a
• /
• pp.13-17
• /
• 2005

In recent years, many people use R as a statistics system. R is frequently updated by many R project teams. We are interested in the method of multiple outlier detection and know that R is not supplied the method of multiple outlier detection. In this talk, we review these procedures for detecting multiple outliers and provide more efficient procedures combined with direct methods and indirect methods using R.

• Journal of the Korea Society for Simulation
• /
• v.21 no.3
• /
• pp.79-88
• /
• 2012

Recently, the study in efficient operation, maintenance, and equipment-design have been growing rapidly in military industry to meet the required missions. Through out these studies, the importance of Concurrent Spare Parts(CSP) are emphasized. The CSP, which is critical to the operation and maintenance to enhance the availability, is offered together when a equipment is delivered. Despite its significance, th responsibility for determining the range and depth of CSP are done from administrative decision rather than engineering analysis. The purpose of the paper is to optimize the number of CSP per item using simulation and multiple regression. First, the result, as the change of operational availability, was gained from changing the number of change in simulation model. Second, mathematical regression was computed from the input and output data, and the number of CSP was optimized by multiple regression and linear programming; the constraint condition is the cost for optimization. The advantage of this study is to respond with the transition of constraint condition quickly. The cost per item is consistently altered in the development state of equipment. The speed of analysis, that simulation method is continuously performed whenever constraint condition is repeatedly altered, would be down. Therefore, this study is suitable for real development environment. In the future, the study based on the above concept improves the accuracy of optimization by the technical progress of multiple regression.

• The Journal of Engineering Geology
• /
• v.16 no.1 s.47
• /
• pp.85-96
• /
• 2006

This study was conducted to suggest a method to determine weighting values of each parameter of the RMR system considered with geologic characteristics of a study area. This study reviewed the weighting values of the RMR system for the Cretaceous sedimentary rocks distributed in Ulsan area. Based on the data of field survey at the study area, a multiple regression analysis was used to set up an optimal weighting values of the RMR parameters. For the multiple regression analysis, each parameter of the RMR and the slope gradient were regarded as the independent variable and the dependent variable, respectively. The analysis result suggested a modified weighting values of the RMR parameters as follows; 30 for the intact strength of rock; 18 for RQD; 8 for spacing of discontinuities; 32 for the condition of discontinuities; and 12 for ground water.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.4
• /
• pp.887-896
• /
• 2015

This study estimates future AADT using historical AADT and socio-economic factors in isolated area. Multiple linear regression method by socio-economic factors are lower MAPE and higher R-square than using historical AADT. Analysis of socio-economic factors influence AADT in isolated typical areas, varied socio-economic factors influence on AADT. In isolated coastal areas, oil price influence on AADT. AADT forecasting model in isolated area is excellent when analysising $R^2$ and MAPE. It is assume that estimation of AADT in isolated area using multiple linear regression is accurate because of a little passed traffic volume and traffic volume fluctuation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.5
• /
• pp.1809-1827
• /
• 2013

Recently we need to take various measures to prepare for extreme flood that occur due to climate change. It is important that establish flood forecasting system to prepare flood over non-structure measures. The objective of this study is to develop superior real-time flood forecasting model by comparing the Neuro-fuzzy model and the multiple linear regression model. The Neuro-fuzzy model and the multiple linear regression model are established using same input data and applied for various flood events in Nakdong basin. The results show that the Neuro-fuzzy model can carry out flood forecasting results more accurately than the multiple linear regression model. This study can contribute to the establishment of a high accuracy flood information system that secure lead time in Nakdong basin.

• Journal of Korean Society for Atmospheric Environment
• /
• v.32 no.5
• /
• pp.513-525
• /
• 2016

To propose an effective ensemble methods in predicting $PM_{10}$ concentration, six experiments were designed by different ensemble average methods (e.g., non-weighted, single weighted, and cluster weighted methods). The single weighted method was calculated the weighted value using both multiple regression analysis and singular value decomposition and the cluster weighted method was estimated the weighted value based on temperature, relative humidity, and wind component using multiple regression analysis. The effects of ensemble average methods were significantly better in weighted average than non-weight. The results of ensemble experiments using weighted average methods were distinguished according to methods calculating the weighted value. The single weighted average method using multiple regression analysis showed the highest accuracy for hourly $PM_{10}$ concentration, and the cluster weighted average method based on relative humidity showed the highest accuracy for daily mean $PM_{10}$ concentration. However, the result of ensemble spread analysis showed better reliability in the single weighted average method than the cluster weighted average method based on relative humidity. Thus, the single weighted average method was the most effective method in this study case.

• The Journal of the Korea Contents Association
• /
• v.14 no.2
• /
• pp.319-329
• /
• 2014

Purpose: The purpose of this study was to investigate the effect of adolescent's family function, impulsive behavior, stress on the bullying types. Method: Data were collected from 627 adolescents and analyzed using descriptive statistics, t-test, Pearson correlation coefficients and stepwise multiple regression with the SPSS 18.0. Results: The bullying types (injurer and victim) correlates with family function, impulsive behavior and stress. Stepwise multiple regression analysis showed emotional reactivity, non-planning impulsiveness, friends related stress, experience of drinking (yes), experience of parent depression problem (yes), explained 34.1% of the total variance in bully injurer. Stepwise multiple regression analysis showed communication, motor impulsiveness, friends related stress, gender (male), grade (junior high school), explained 30.9% of the total variance in bully victim. Conclusion: The results of this study are expected to be used as basic data in providing a better understanding of adolescents' bullying, in preventing bullying and in developing an intervention program.

• The Journal of Korean Association of Computer Education
• /
• v.18 no.5
• /
• pp.15-24
• /
• 2015

The purpose of this study is to analyze variables affecting parents' and elementary school students' value of computer science after creative computer science education, through multiple regression. Many researches on Informatics subject have focused on the effect of the subject contents on students but hardly dealt with parents' recognition. Thereupon, this study pays attention to the value of computer science recognized by parents and analyzes variables substantially affecting value variables of computer science related to parents' support for learning Informatics subjects. This paper did not verify the difference in recognition of parents and students but calculated more concrete influence by conducing multiple regression on the variables affecting the value recognized by each group. This is one of the reasons why this study is meaningful. According to the result of the analysis, variables affecting the value of parents on computer science the most are interest and satisfaction, and in students' case, self-efficacy is the variable affecting the value of computer science the most.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.9
• /
• pp.1387-1399
• /
• 2020

Objective: The objective of this study was to estimate the genetic parameters and trends for milk, fat, and protein yields in the first three lactations of Thai dairy cattle using a 3-trait,-3-lactation random regression test-day model. Methods: Data included 168,996, 63,388, and 27,145 test-day records from the first, second, and third lactations, respectively. Records were from 19,068 cows calving from 1993 to 2013 in 124 herds. (Co) variance components were estimated by Bayesian methods. Gibbs sampling was used to obtain posterior distributions. The model included herd-year-month of testing, breed group-season of calving-month in tested milk group, linear and quadratic age at calving as fixed effects, and random regression coefficients for additive genetic and permanent environmental effects, which were defined as modified constant, linear, quadratic, cubic and quartic Legendre coefficients. Results: Average daily heritabilities ranged from 0.36 to 0.48 for milk, 0.33 to 0.44 for fat and 0.37 to 0.48 for protein yields; they were higher in the third lactation for all traits. Heritabilities of test-day milk and protein yields for selected days in milk were higher in the middle than at the beginning or end of lactation, whereas those for test-day fat yields were high at the beginning and end of lactation. Genetics correlations (305-d yield) among production yields within lactations (0.44 to 0.69) were higher than those across lactations (0.36 to 0.68). The largest genetic correlation was observed between the first and second lactation. The genetic trends of 305-d milk, fat and protein yields were 230 to 250, 25 to 29, and 30 to 35 kg per year, respectively. Conclusion: A random regression model seems to be a flexible and reliable procedure for the genetic evaluation of production yields. It can be used to perform breeding value estimation for national genetic evaluation in the Thai dairy cattle population.

• Journal of the Korea Institute of Building Construction
• /
• v.16 no.5
• /
• pp.437-445
• /
• 2016

Since typhoon is a critical meteorological disaster, some advanced countries have developed typhoon damage prediction models. However, although South Korea is vulnerable to typhoons, there is still shortage of study in typhoon damage prediction model reflecting the vulnerability of domestic building and features of disaster. Moreover, many studies have been only focused on the characteristics and typhoon and regional characteristics without various influencing factors. Therefore, the objective of this study is to analyze typhoon damage by path and develop to prediction model for building damage ratio by using multiple regression analysis. This study classifies the building damages by typhoon paths to identify influencing factors then the correlation analysis is conducted between building damage ratio and their factors. In addition, a multiple regression analysis is applied to develop a typhoon damage prediction model. Four categories; typhoon information, geography, construction environment, and socio-economy, are used as the independent variables. The results of this study will be used as fundamental material for the typhoon damage prediction model development of South Korea.