• 한국시스템다이내믹스연구
• /
• 제9권1호
• /
• pp.125-141
• /
• 2008

It is very difficult to predict future demand/supply, price for resources with acceptable accuracy using regression analysis. We try to use system dynamics to forecast the demand/supply and price for nickel. Nickel is very expensive mineral resource used for stainless production or other industrial production like battery, alloy making. Recent nickel price trend showed non-linear pattern and we anticipated the system dynamic method will catch this non-linear pattern better than the regression analysis. Our model has been calibrated for the past 6 year quarterly data (2002-2007) and tested for next 5 year quarterly data(2008-2012). The results were acceptable and showed higher accuracy than the results obtained from the regression analysis. And we ran the simulations for scenarios made by possible future changes in demand or supply related variables. This simulations implied some meaningful price change patterns.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2019년도 추계 학술논문 발표대회
• /
• pp.16-17
• /
• 2019

In order to measure the amount of carbon dioxide emitted from the construction sites, many literature which have been conducted have proposed methodologies for calculating coefficients based on actual data collections for estimating the emission formula. The existing data collected under controlled conditions not on site measurement were too limited to apply in actual sites. The purpose of this study is to conduct analysis based on the data measured in fields and to present predictive models using artificial neural network and nonlinear regression analysis for appropriate predictions and practical applications.

• Communications for Statistical Applications and Methods
• /
• 제26권3호
• /
• pp.273-293
• /
• 2019

We consider the problem of model selection in multiple linear regression with outliers and non-normal error distributions. In this article, the robust model selection criterion is proposed based on the robust estimation method with the least absolute deviation (LAD). The proposed criterion is shown to be consistent. We suggest proposed criterion based algorithms that are suitable for a large number of predictors in the model. These algorithms select only relevant predictor variables with probability one for large sample sizes. An exhaustive simulation study shows that the criterion performs well. However, the proposed criterion is applied to a real data set to examine its applicability. The simulation results show the proficiency of algorithms in the presence of outliers, non-normal distribution, and multicollinearity.

• 한국지능시스템학회논문지
• /
• 제25권5호
• /
• pp.477-482
• /
• 2015

단기풍속 예측을 위한 진화적 선형 및 비선형 회귀분석 기반의 보정 기법을 비교한다. 모델의 체계적 오류를 교정하기 위한 효율적인 MOS(Model Output Statistics)의 개발이 필요하나, 기존의 선형회귀분석 기반의 보정기법은 다양한 기상요소의 복잡한 비선형 특성을 반영하기 힘들다. 이를 개선하기 위해서 유전 프로그래밍을 사용하여 풍속 예측에 대한 비선형 보정 수식을 생성하는 기법을 제안하고 기본 다중선형회귀분석법 및 Ridge, Lasso 회귀분석법과 비교한다. 더불어, 선형회귀분석법과 진화적 비선형회귀분석 기법의 인자 선택의 차이와 유사성을 비교하고 분석한다. 2007년~2013년의 KLAPS(Korea Local Analysis and Prediction System) 재분석자료를 사용하여 제주도와 부산지역의 격자점에 대한 실험을 수행한다.

• 한국환경농학회지
• /
• 제39권3호
• /
• pp.204-213
• /
• 2020

BACKGROUND: Since the number of crops cultivated in reclaimed land is huge, it is very difficult to quantify the total crop production. Therefore, a non-destructive method for predicting crop production is needed. Salt tolerant root vegetables such as red beets and sugar beet are suitable for cultivation in reclaimed land. If their underground biomass can be predicted, it helps to estimate crop productivity. Objectives of this study are to investigate maximum leaf length and weight of red beet, sugar beet, and turnips grown in reclaimed land, and to determine optimal model with regression analysis for linear and allometric growth models. METHODS AND RESULTS: Maximum leaf length, width, and root fresh weight of red beets, sugar beets, and turnips were measured. Ten linear models and six allometric growth models were selected for estimation of root fresh weight and non-linear regression analysis was conducted. The allometric growth model, which have a variable multiplied by square of maximum leaf length and maximum leaf width, showed highest R² values of 0.67, 0.70, and 0.49 for red beets, sugar beets, and turnips, respectively. Validation results of the models for red beets and sugar beets showed the R² values of 0.63 and 0.65, respectively. However, the model for turnips showed the R² value of 0.48. The allometric growth model was suitable for estimating the root fresh weight of red beets and sugar beets, but the accuracy for turnips was relatively low. CONCLUSION: The regression models established in this study may be useful to estimate the total production of root vegetables cultivated in reclaimed land, and it will be used as a non-destructive method for prediction of crop information.

• 한국연초학회지
• /
• 제6권1호
• /
• pp.51-62
• /
• 1984

The chemical components of non-blended and blended cigarettes and their smoke have been analyzed to investigate the correlation between them. Some regression of linear equations were obtained based on the simple correlation data(r), for the various smoke components such as tar, nicotine, nitrogen dioxide, steam volatile phenols, formaldehyde, acetaldehyde, acrolein and hydrogen cyanide. Chi-square tests were carried out to observe the probabilities of the values estimated by the regression of linear equations. The probabilities of the greater values were 0.900-0.999 to tar, nicotine, formaldehyde, acetal dehyde, acrolein, steam volatile phenols, nitrogen dioxide and hydrogen cyanide of the non-blended cigarettes, and 0.900-0.999 to tar, nicotine, nitrogen dioxide, steam volatile phenols and static burning rate (SBR) of the blended cigarettes.

• Communications for Statistical Applications and Methods
• /
• 제24권6호
• /
• pp.673-683
• /
• 2017

The least absolute shrinkage and selection operator (LASSO) has been a popular regression estimator with simultaneous variable selection. However, LASSO does not have the oracle property and its robust version is needed in the case of heavy-tailed errors or serious outliers. We propose a robust penalized regression estimator which provide a simultaneous variable selection and estimator. It is based on the rank regression and the non-convex penalty function, the smoothly clipped absolute deviation (SCAD) function which has the oracle property. The proposed method combines the robustness of the rank regression and the oracle property of the SCAD penalty. We develop an efficient algorithm to compute the proposed estimator that includes a SCAD estimate based on the local linear approximation and the tuning parameter of the penalty function. Our estimate can be obtained by the least absolute deviation method. We used an optimal tuning parameter based on the Bayesian information criterion and the cross validation method. Numerical simulation shows that the proposed estimator is robust and effective to analyze contaminated data.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1525-1525
• /
• 2001

Non-destructive determination of soluble solids(Brix) in harvested fruits using near infrared(hereafter, NIR) spectroscopy has been reported by many researchers. We have just reported on non-destructive estimation of Brix in harvested melons using a NIR Systems Model 6500 spectrophotometer(Ito et al., 2000). There is a melon cultivar that is difficult to judge the harvest time from the external appearance. If we can determine Brix in growing fruits non-destructively in the field, immature fruits will not be harvested. A portable m spectrophotometer for field use has been just developed by Kubota Corporation. The spectral data of growing melons were measured by the portable spectrophotometer. A commercial program was used for multiple linear regression analysis. Brix in growing melons could be estimated by a multiple regression equation calibrated with harvested melons. Absorbances of 906 and 874 nm were included as the independent variables in the multiple regression equation, and these wavelengths are key wavelengths for non-destructive Brix determination.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권2호
• /
• pp.363-370
• /
• 2022

The study aims to probe the impact of foreign ownership on Vietnamese listed firms' capital structure. This study employs panel data of 288 non-financial firms listed on the Ho Chi Minh City stock exchange (HOSE) and Ha Noi stock exchange (HNX) in 2015-2019. In this research, we applied a Bayesian linear regression method to provide probabilistic explanations of the model uncertainty and effect of foreign ownership on the capital structure of non-financial listed enterprises in Vietnam. The findings of experimental analysis by Bayesian linear regression method through Markov chain Monte Carlo (MCMC) technique combined with Gibbs sampler suggest that foreign ownership has substantial adverse effects on the firms' capital structure. Our findings also indicate that a firm's size, age, and growth opportunities all have a strong positive and significant effect on its debt ratio. We found that the firms' profitability, tangible assets, and liquidity negatively and strongly affect firms' capital structure. Meanwhile, there is a low negative impact of dividends and inflation on the debt ratio. This research has ramifications for business managers since it improves a company's financial resources by developing a strong capital structure and considering foreign investment as a source of funding.

• Educational Technology International
• /
• 제15권2호
• /
• pp.71-88
• /
• 2014

A variety of studies to predict students' performance have been conducted since educational data such as web-log files traced from Learning Management System (LMS) are increasingly used to analyze students' learning behaviors. However, it is still challenging to predict students' learning achievement in blended learning environment where online and offline learning are combined. In higher education, diverse cases of blended learning can be formed from simple use of LMS for administrative purposes to full usages of functions in LMS for online distance learning class. As a result, a generalized model to predict students' academic success does not fulfill diverse cases of blended learning. This study compares two blended learning classes with each prediction model. The first blended class which involves online discussion-based learning revealed a linear regression model, which explained 70% of the variance in total score through six variables including total log-in time, log-in frequencies, log-in regularities, visits on boards, visits on repositories, and the number of postings. However, the second case, a lecture-based class providing regular basis online lecture notes in Moodle show weaker results from the same linear regression model mainly due to non-linearity of variables. To investigate the non-linear relations between online activities and total score, RF (Random Forest) was utilized. The results indicate that there are different set of important variables for the two distinctive types of blended learning cases. Results suggest that the prediction models and data-mining technique should be based on the considerations of diverse pedagogical characteristics of blended learning classes.