http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Hohsuk Noh (검색결과 8 건)
- 무료
- 기관 내 무료
- 유료
-
Forecasting Korean Stock Returns with Machine Learning
Noh Hohsuk,Jang Hyuna,Yang Cheol‐Won 한국증권학회 2023 Asia-Pacific Journal of Financial Studies Vol.52 No.2
This paper aims to evaluate the predictive power of financial variables by using various machine learning methods. An analysis is conducted on data for the Korean stock market, which is representative of emerging markets, over 32 years from 1987 to 2018. The study shows that median regression is a more efficient tool than mean regression in the presence of potential heterogeneity of stocks, significantly improving performance in terms of average realized monthly return. This suggests that median regression can have better predictive performance in emerging markets where there are likely to be outliers. Additionally, a gradient boosting machine (GBM) is found to be better than a traditional linear model both in prediction accuracy and portfolio performance. The hedged return from GBM is on average 2.89% per month with an annualized Sharpe ratio of 0.93 in the median regression. The neural network (NN) is also tested and shown to perform best when the number of hidden layers is two or three. Finally, we evaluatea list of predictor variables with various measures of variable importance. Variables of risk, price trend and liquidity are found to serve as important predictors.
-
Component selection in additive quantile regression models
Hohsuk Noh,이은령 한국통계학회 2014 Journal of the Korean Statistical Society Vol.43 No.3
Nonparametric additive models are powerful techniques for multivariate data analysis. Although many procedures have been developed for estimating additive components bothin mean regression and quantile regression, the problem of selecting relevant componentshas not been addressed much especially in quantile regression. We present a doublypenalizedestimation procedure for component selection in additive quantile regressionmodels that combines basis function approximation with a ridge-type penalty and a variantof the smoothly clipped absolute deviation penalty. We show that the proposed estimatoridentifies relevant and irrelevant components consistently and achieves the nonparametricoptimal rate of convergence for the relevant components. We also provide an accurateand efficient computation algorithm to implement the estimator and demonstrate itsperformance through simulation studies. Finally, we illustrate our method via a real dataexample to identify important body measurements to predict percentage of body fat of anindividual.
-
확률프런티어 모형하에서 단조증가하는 매끄러운 프런티어 함수 추정
윤단비,노호석,Yoon, Danbi,Noh, Hohsuk 한국통계학회 2017 응용통계연구 Vol.30 No.5
생산성 평가를 위해서는 주어진 생산 자료를 기반으로 투입 대비 최대산출량을 나타내는 최대산출량을 나타내는 생산 프런티어 곡선에 대한 정보가 필요한 경우가 많다. 이러한 프런티어 함수를 확률프런티어 모형하에서 추정하는 경우에 초기에는 프런티어 함수의 특정한 모수적 형테를 가정하는 경우가 많았다. 그러나 최근에는 프런티어 함수를 프런티어 함수가 기본적으로 만족해야 하는 단조성이나 오목성등을 만족하도록 하면서 비모수적 방법으로 추정하는 방법들이 많이 이루어졌다. 하지만, 이러한 방법들에서 얻어지는 추정량들은 프런티어 함수를 조각적 선형함수 또는 계단함수로 추정하는 특징 때문에 추정의 효율이 떨어지나가 프런티어 함수가 해석이 용이하지 않은 불연속점을 가지는 문제를 가지게 된다. 본 논문에서는 이러한 문제를 해결하기 위해 확률프런티어 모형에서 단조증가하는 매끄러운 프런티어 함수 추정법을 제시하고 제안된 추정방법이 기존의 추정방법에 비해서 가지는 추정 효율의 장점을 시뮬레이션를 통해 예시하였다. When measuring productive efficiency, often it is necessary to have knowledge of the production frontier function that shows the maximum possible output of production units as a function of inputs. Canonical parametric forms of the frontier function were initially considered under the framework of stochastic frontier model; however, several additional nonparametric methods have been developed over the last decade. Efforts have been recently made to impose shape constraints such as monotonicity and concavity on the non-parametric estimation of the frontier function; however, most existing methods along that direction suffer from unnecessary non-smooth points of the frontier function. In this paper, we propose methods to estimate the smooth frontier function with monotonicity for stochastic frontier models and investigate the effect of imposing a monotonicity constraint into the estimation of the frontier function and the finite dimensional parameters of the model. Simulation studies suggest that imposing the constraint provide better performance to estimate the frontier function, especially when the sample size is small or moderate. However, no apparent gain was observed concerning the estimation of the parameters of the error distribution regardless of sample size.
-
-
노호석,송지나,조혜윤,Noh, Hohsuk,Song, Ji Na,Cho, Hyeyoon 한국통계학회 2016 응용통계연구 Vol.29 No.2
It is common to quantify the concept of interest in the social and human sciences to test a research hypothesis. In such a case, it is strongly recommended to investigate if the procedure is appropriately designed and implemented according the research purpose since the quantification procedure highly affects the result of statistical analysis. In this work, we propose a visualization tool which enables us to check the construct validity of a measurement tool (such a questionnaire) in a concise and convenient way based on a penalized factor analysis model. We illustrate our method with numerical simulation and real data analysis. 인문사회학 분야에서와 같이 개념적인 주제에 대한 연구가설을 검정하기 위해서는 연구 대상이 되는 개념을 수량화하여 통계적 분석을 실시하여야 한다. 이러한 경우 연구결과에 대한 해석이 설문조사에 의한 수량화과정에 깊이 의존하기 때문에 연구자가 측정도구인 설문지가 연구목적에 부합하게 제대로 만들어졌는지 검정하는 것은 필수적인 과정이라고 할 수 있다. 본 논문에서는 흔히 사용되는 요인분석에 의한 측정도구 타당도 평가를 개선할 수 있는 시각화 방법을 제시하고 모의실험과 실제사례분석을 통해 그 유용성을 예시하였다.
-
-
-
Nanotopography-based engineering of retroviral DNA integration patterns
Jang, Yoon-ha,Park, Yi-seul,Nam, Jung-soo,Yang, Yeji,Lee, Ji-eun,Lee, Kwang-hee,Kang, Minho,Chialastri, Alex,Noh, Hohsuk,Park, Jungwon,Lee, Jin Seok,Lim, Kwang-il The Royal Society of Chemistry 2019 Nanoscale Vol.11 No.12
<P>Controlling the interactions between cells and viruses is critical for treating infected patients, preventing viral infections, and improving virus-based therapeutics. Chemical methods using small molecules and biological methods using proteins and nucleic acids are employed for achieving this control, albeit with limitations. We found, for the first time, that retroviral DNA integration patterns in the human genome, the result of complicated interactions between cells and viruses, can be engineered by adapting cells to the defined nanotopography of silica bead monolayers. Compared with cells on a flat glass surface, cells on beads with the highest curvature harbored retroviral DNAs at genomic sites near transcriptional start sites and CpG islands during infections at more than 50% higher frequencies. Furthermore, cells on the same type of bead layers contained retroviral DNAs in the genomic regions near cis-regulatory elements at frequencies that were 2.6-fold higher than that of cells on flat glass surfaces. Systems-level genetic network analysis showed that for cells on nanobeads with the highest curvature, the genes that would be affected by cis-regulatory elements near the retroviral integration sites perform biological functions related to chromatin structure and antiviral activities. Our unexpected observations suggest that novel engineering approaches based on materials with specific nanotopography can improve control over viral events.</P>
ScienceON
DBpia연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
