• 한국의류학회지
• /
• 제27권5호
• /
• pp.496-504
• /
• 2003

The purpose of this study was (1) to identify the experimental bias which could appear person perception as results of presentation methods (2) to find out the most desirable method in presentation of stimulus. The research was a quasi experiment and the subjects were 773 male and female undergraduate students. The experimental instruments consisted of a set of stimulus and semantic differential scales of 7- point hi-polar adjectives. The collected data were analyzed by Factor Analysis, ANOVA(analysis of variance), Scheffe＇s multiple range test. The independent variables were presentation orders and presentation time of stimulus. The results were as follows: First, five factors which were potency, sociality, appearance, evaluation, activity impression dimensions emerged to account for the methods of development of stimulus. Second, the presentation order of stimulus in the combination of four stimuli sets had significant effects on the 3 impressional factors(sociality, appearance, evaluation). The presentation order of stimuli in the combination of eight stimuli set had significant effects on the 3 impressional factors(potency, sociality, appearance) and the presentation order of stimuli in the combination of eight stimuli set showed a significant effect on memorization of stimulus and the results support the recency effect. Third, the presentation time of stimuli had significant effects on the 2 impressional factors(potency, activity). 30 seconds presentation as well as free duration time resulted less experimental bias than 3 seconds presentation.

• Quantitative Bio-Science
• /
• 제37권2호
• /
• pp.133-141
• /
• 2018

Graphical lasso is one of the most popular methods to estimate a sparse precision matrix, which is an inverse of a covariance matrix. The objective function of graphical lasso imposes an ${\ell}_1$-penalty on the (vectorized) precision matrix, where a tuning parameter controls the strength of the penalization. The selection of the tuning parameter is practically and theoretically important since the performance of the estimation depends on an appropriate choice of tuning parameter. While information criteria (e.g. AIC, BIC, or extended BIC) have been widely used, they require an asymptotically unbiased estimator to select optimal tuning parameter. Thus, the biasedness of the ${\ell}_1$-regularized estimate in the graphical lasso may lead to a suboptimal tuning. In this paper, we propose a two-staged bias-correction procedure for the graphical lasso, where the first stage runs the usual graphical lasso and the second stage reruns the procedure with an additional constraint that zero estimates at the first stage remain zero. Our simulation and real data example show that the proposed bias correction improved on both edge recovery and estimation error compared to the single-staged graphical lasso.

• 아태비즈니스연구
• /
• 제11권4호
• /
• pp.1-19
• /
• 2020

Purpose - This study analyzes the intertemporal patterns in personnel decisions made between a supervisor and a subordinate to understand potential supervisor bias in the decisions. A correlation between the current and the most recent personnel decisions made for a subordinate by a current supervisor captures certain relationship-embedded and time-invariant factors in effect. The characteristics speak to the nature of a supervisor bias arising from a relationship, or favoritism. Design/methodology/approach - This study manually collects the executive profile data from annual reports of key Samsung Group affiliates and compile a longitudinal sample of 3,675 executive-years. It mainly explores the logistic regression analysis. Findings - The study finds that a supervisor' previous promotion award to a subordinate does not improve but decreases the likelihood of promotions in ensuing years, suggesting the containment of favoritism; and that the time since the last promotion award to a subordinate by the current supervisor increases the likelihood of both promotions and dismissals of the subordinate. Research implications or Originality - The findings are generally consistent with the theory suggesting that incentive schemes that align interests between an individual and an organization will contain the form of a supervisor bias.

• 한국수자원학회논문집
• /
• 제47권12호
• /
• pp.1227-1237
• /
• 2014

이중편파레이더는 강수의 형태를 구분하고 대기 중의 기상 현상뿐만 아니라 비강수에코에 대한 정보를 제공하기 때문에 보다 정확한 강수량 추정을 가능하게 한다. 그러나 수직, 수평으로 진동하는 전파를 송 수신하여 생성되는 이중편파레이더 관측변수들은 레이더 자체가 갖는 시스템적 관측오차를 포함하기 때문에 정량적 강수량 추정을 위해서는 이에 대한 보정이 필수적이다. 본 연구에서는 2차원 영상우적계(2-Dimensional Video Disdrometer, 이하 2DVD) 관측 자료를 이용하여 비슬산 이중편파레이더가 갖는 Z, $Z_{DR}$ 관측오차를 계산한 후, 관측오차 보정에 따라 강수량이 정량적으로 얼마나 개선되는지를 살펴보았다. 총 33강수사례에 대한 분석결과, Z는 약-0.3~5.5 dB, $Z_{DR}$는 -0.1~0.6 dB의 관측오차를 가지며, 대부분의 사례에서 Z와 $Z_{DR}$는 모의된 값보다 낮게 관측하였다. 관측오차를 보정한 전 후 산출된 이중편파레이더 강수량 추정값을 지상관측 강우강도와 비교한 결과, 평균 bias와 RMSE는 각각 1.54 mm/hr, 1.73 mm/hr로 보정 전의 1.69 mm/hr, 2.54 mm/hr 보다 감소함으로써 지상우량계 관측값 대비 레이더 강수량 추정값이 약 7~61% 향상되었다.

• Korean Journal of Acupuncture
• /
• 제37권3호
• /
• pp.131-144
• /
• 2020

Objectives : The aim of this study is to analyze the details of acupuncture treatment methods and the reporting quality of acupuncture on Carpal Tunnel Syndrome (CTS). Methods : Search was conducted in Pubmed, EMBASE, and Cochrane Library for acupuncture studies on CTS. The reporting quality of acupuncture treatment was assessed using the following guidelines: Standards for Reporting Interventions in Clinical Trials of Acupuncture (STRICTA) for analyzing the method of acupuncture treatment, Consolidated Standards of Reporting Trials (CONSORT) for analyzing study design and study process, and Risk of Bias (ROB) for analyzing bias. The number of reported items was calculated and evaluated as a proportion. The reported proportion of each study was classified into three grades: Grade A (% score ≥75), Grade B (50≤ % score <75), and Grade C (% score <50). Results : A total of 9 Randomized Controlled Trials (RCTs) were included in this study. All trials reported 12 items (66.67%) on average in STRICTA guidelines. Five studies were conducted with manual acupuncture and 3 studies were conducted with electroacupuncture. PC7 (Daereung) was most frequently used to treat CTS. In STRICTA guideline evaluation, 3 studies were classified as Grade A, 5 studies were classified as Grade B, and 1 study was classified as Grade C. In the CONSORT statement assessment, all trials reported an average of 20.56 items. Of the 9 RCTs, 6 studies were classified as Grade B and 3 studies were classified as Grade C. In ROB assessment, most studies showed a low (63.49%) or unclear (26.98%) risk of bias. The selective reporting bias and the incomplete outcome data bias were found to have the lowest risk of bias, and the allocation concealment of selection bias was found to have the most unclear risk of bias. Conclusions : Recent acupuncture studies on CTS showed moderate reporting quality. However, more detailed reports on acupuncture are still needed to establish more solid evidence of acupuncture treatment.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권1호
• /
• pp.1-8
• /
• 2021

뉴스 기사의 정치 분야는 보수, 진보와 같이 양극화된 편향적 특성이 존재하며 이를 정치적 편향성이라고 한다. 뉴스 기사로부터 편향성 문제를 분류하기 위해 키워드 기반의 학습 데이터를 구축하였다. 대부분의 임베딩 연구에서는 미등록어로 인한 문제를 완화시키기 위해 형태소 단위로 문장을 구성한다. 본 논문에서는 문장을 언어 모델에 의해 세부적으로 분할하는 부분 단어로 문장을 구성할 경우 미등록어 수가 감소할 것이라 예상하였다. 부분 단어 토큰화 기법을 이용한 문서 임베딩 모델을 제안하며 이를 SVM과 전방향 뉴럴 네트워크 구조에 적용하여 정치적 편향성 분류 실험을 진행하였다. 형태소 토큰화 기법을 이용한 문서 임베딩 모델과 비교 실험한 결과, 부분 단어 토큰화 기법을 이용한 문서 임베딩 모델이 78.22%로 가장 높은 정확도를 보였으며 부분 단어 토큰화를 통해 미등록어 수가 감소되는 것을 확인하였다. 분류 실험에서 가장 성능이 좋은 임베딩 모델을 이용하여 정치적 인물을 기반한 어휘를 추출하였으며 각 성향의 정치적 인물 벡터와의 평균 유사도를 통해 어휘의 편향성을 검증하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2001년도 춘계 학술대회 논문집 통권 4호 Proceedings of the 2001 KSRS Spring Meeting
• /
• pp.104-110
• /
• 2001

Ocean heat fluxes over a wide region are generally estimated by an aerodynamic bulk fromula. Though a remote sensing technique can be expected to estimated global heat flux, it is difficult to obtain air temperature and specific humidity at sea surface by a remote sensor. In this study present a new method with which to determine near-sea surface air temperature from in situ data. Also, These methods compared with other methods. A new method used a linear regression equation between sea surface temperature and air temperature of the buoys data. In this study new method is validated using observed monthly mean data at the Japan Meteorological Agency(JMA), National Data Buoy Center(NDBC) and Tropical Ocean-Global Atmosphere(TOGA)-Tropical Atmosphere Ocean(TAO) buoys. The result that bias and rmse are 0.28, 1.5$0^{\circ}C$ respectively. The correlation coefficient is 0.98. Also, to retrieve near-sea surface specific humidity(Q) from good nonlinear regression relationship between vapor pressure(Ea) of buoy data and air temperature, after obtained the third-order polynomial function, compared with that of estimated from SSM/I empirical equation by Schussel et al(1995). The result that bias and rmse are -1.42 and 1.75(g/kg).

• 한국군사과학기술학회지
• /
• 제13권6호
• /
• pp.982-989
• /
• 2010

This paper shows accuracy comparison results of reliability estimation methods for one-shot systems such as ammunitions. Quantal-response data, following a binomial distribution at each sampling time, characterizes lifetimes of one-shot systems. Various quantal-response data of different sample sizes are simulated using lifetime data randomly sampled from assumed weibull distributions with different shape parameters but the identical scale parameter in this paper. Then, reliability estimation methods in open literature are applied to the simulated quantal-response data to estimate true reliability over time. Rankings in estimation accuracy for different sample sizes are determined using t-test of SSE. Furthermore, MSE at each time, including both bias and variance of estimated reliability metrics for each method are analyzed to investigate how much both bias and variance contribute the SSE. From the MSE analysis, MSE provides reliability estimation trend for each method. Parametric estimation method provides more accurate reliability estimation results than the other methods for most of sample sizes.

• 한국수자원학회논문집
• /
• 제50권1호
• /
• pp.1-15
• /
• 2017

최근 기후변화로 인하여 발생하는 기상재해 및 위험기상 현상의 대비를 위하여 조밀한 시공간적 해상도를 갖는 레이더 강우가 활용되고 있지만 널리 사용되는 Marshall-Palmer의 Z-R 관계식으로 추정된 레이더 강우는 과소추정의 문제점이 있다. 본 연구는 이러한 문제점을 해결하기 위하여 분위회귀 분석기법을 통한 레이더 강우자료 편의보정 기법과 Copula 함수를 연계한 강우자료 확충기법을 개발하였다. 본 연구에서 개발된 모형을 통하여 편의가 보정된 시계열 레이더 강우자료 효율을 통계적으로 분석한 결과 우수한 모형성능을 확인하였으며 Copula 기법을 이용하여 지상강우 및 레이더 강우자료를 확충한 결과 기존의 강우특성을 현실적으로 재현하는 것을 확인하였다. Copula 기법을 통한 강우자료 확충기법은 레이더 강우의 오차분포를 평가하는데 유용하게 활용될 것으로 판단된다.

• 대기
• /
• 제29권3호
• /
• pp.241-255
• /
• 2019

Bias correction (BC) and quality control (QC) are essential steps for the proper use of satellite observations in data assimilation (DA) system. BC should be calculated over quality controlled observation. And also QC should be performed for bias corrected observation. In the Korea Institute of Atmospheric Prediction Systems (KIAPS) Package for Observation Processing (KPOP), we adopted an adaptive BC method that calculates the BC coefficients with background at the analysis time rather than using static BC coefficients. In this study, we have developed an iterative QC-BC method for Advanced Microwave Sounding Unit-A (AMSU-A) to reduce the negative feedback from the interaction between BC and QC. The new iterative QC-BC is evaluated in the KIAPS 3-dimensional variational (3DVAR) DA cycle for January 2016. The iterative QC-BC method for AMSU-A shows globally significant benefits for error reduction of the temperature. The positive impacts for the temperature were predominant at latitudes of $30^{\circ}{\sim}90^{\circ}$ of both hemispheres. Moreover, the background warm bias across the troposphere is decreased. Even though AMSU-A is mainly designed for atmospheric temperature sounding, the improvement of AMSU-A pre-processing module has a positive impact on the wind component over latitudes of $30^{\circ}S$ near upper-troposphere, respectively. Consequently, the 3-day-forecast-accuracy is improved about 1% for temperature and zonal wind in the troposphere.