• Communications for Statistical Applications and Methods
• /
• 제30권6호
• /
• pp.605-629
• /
• 2023

This paper proposes some diagnostics procedures for the skew-t linear regression model with censored response. The skew-t distribution is an attractive family of asymmetrical heavy-tailed densities that includes the normal, skew-normal and student's-t distributions as special cases. Inspired by the power and wide applicability of the EM-type algorithm, local and global influence analysis, based on the conditional expectation of the complete-data log-likelihood function are developed, following Zhu and Lee's approach. For the local influence analysis, four specific perturbation schemes are discussed. Two real data sets, from education and economics, which are right and left censoring, respectively, are analyzed in order to illustrate the usefulness of the proposed methodology.

• 한국환경과학회지
• /
• 제26권4호
• /
• pp.421-432
• /
• 2017

In this study, we examined the suitability of ten disinfection models for predicting the inactivation of Artemia sp. via single or combined physical and chemical treatments. The effect of Hydraulic Retention Time (HRT) on the inactivation of Artemia sp. was examined experimentally. Disinfection models were fitted to the experimental data by using the GInaFiT plug-in for Microsoft Excel. The inactivation model were evaluated on the basis of RMSE (Root Mean Square Error), SSE (mean Sum Square Error) and $r^2$. An inactivation model with the lowest RMSE, SSE and $r^2$ close to 1 was considered the best. The Weibull+Tail model was found to be the most appropriate for predicting the inactivation of Artemia sp. via electrolytic treatment and electrolytic-ultrasonic combined treatment. The Log-linear+Tail model was the most appropriate for modeling inactivation via homogenization and combined electrolytic-homogenization treatment. The double Weibull disinfection model was the most suitable for the predicting inactivation via ultrasonic treatment.

• 한국정보전자통신기술학회논문지
• /
• 제8권6호
• /
• pp.445-452
• /
• 2015

소프트웨어 개발 과정에서 소프트웨어 신뢰성은 매우 중요한 이슈이다. 소프트웨어 고장분석을 위한 무한고장 비동질적인 포아송과정에서 결함당 고장발생률이 상수이거나, 단조 증가 또는 단조 감소하는 패턴을 가질 수 있다. 본 논문에서는 소프트웨어 신뢰성에 대한 적용 효율을 나타내는 로그 및 지수파우어 강도함수(로그 선형, 로그 파우어와 지수 파우어)로 신뢰성 모형을 제안한다. 효율적인 모형을 위해 평균제곱에러(MSE), 결정계수($R^2$)에 근거한 모델선택, 최우추정법, 이분법에 사용된 파라미터를 평가하기 위한 알고리즘이 적용되였다. 제안하는 로그 및 지수파우어 강도함수를 위해 실제 데이터을 사용한 고장분석이 적용되였다. 고장데이터 분석은 로그 및 지수파우어 강도함수와 비교하였다. 데이터 신뢰성을 보장하기 위하여 라플라스 추세검정(Laplace trend test)을 사용하였다. 본 연구에 제안된 로그선형과 로그파우어 및 지수파우어 신뢰성모형도 신뢰성 측면에서 효율적이기 때문에 (결정계수가 70% 이상) 이 분야에서 기존 모형의 하나의 대안으로 사용할 수 있음을 확인 할 수 있었다. 이 연구를 통하여 소프트웨어 개발자들은 다양한 강도함수를 고려함으로서 소프트웨어 고장형태에 대한 사전지식을 파악하는데 도움을 줄 수 있으리라 사료 된다.

• 한국사회복지학회:학술대회논문집
• /
• 한국사회복지학회 2004년도 추계공동학술대회 자료집
• /
• pp.461-492
• /
• 2004

This study examined the effects of gender, parental support and treatment type on the treatment outcome of adolescent substance abusers. Outcome variable was the successful graduation (or drop) from an Intensive Adolescent Outpatient Program. Adolescents with their parents' support were treated in one of three treatment models (2-weeks Inpatient plus 6 week Intensive Croup-Oriented Outpatient, 8-weeks Intensive Croup-Oriented Outpatient, and 8-weeks Individual-Family Therapy) within a private hospital-affiliated treatment center by managed care practice allowing their own choice (non-random natural assignments). Several hypotheses were tested for main effects by the Log-Linear Analyses for a multi-dimensional contingency table with 440 adolescents (284 boys and 156 girls treated during 1992-l997) from middle-class families with private health insurances. The following results were found. Odds of graduating versus dropping out of the treatment program among : (1) girls were 1.7 times higher than those among boys; (2) adolescents with two-parent were 2.2 times higher than those among adolescents with one-parent ; (3) adolescents with Inpatient plus Outpatient was 1.7 times higher than that of those with Outpatient; (4) adolescents with Individual-Family Therapy was 2.3 times higher than that of those with Outpatient Model. There was no statistically significant outcome difference between the Individual-Family Therapy and the Inpatient plus Outpatient. Implications from the results were discussed. Suggestions were made to improve the treatment components in the areas of gender sensitivity, securing more parental support, alternatives for separation from peer group and integrating new peer groups, and flexibility for the unique needs of individual family. Also, some research questions for future studies were suggested.

• 한국산림과학회지
• /
• 제97권5호
• /
• pp.485-491
• /
• 2008

This study was performed in 14 unthinned Mongolian pine (Pinus sylvestris L. var. mongolica Litvin) plantations in northeast China. Data were collected on 70 sample trees of different canopy position with diameter at breast height (DBH) ranging from 6.9 cm to 34.5 cm. Diameter and length of knots per whorl below the living crown were studied by different vertical levels divided by relative knot height (RHK) in this paper. Models taking DBH and height to the crown base (HCB) as independent variables were developed to predict knot diameter (KD) in a sample whorl. According to the vertical distribution tendency and range of sound knot length (KLsound), KLsound was modeled as multiple linear function of DBH, KD and relative knot height (RHK). The loose knot length (KLloose) was described as a function of DBH, KD and height above the ground for knots (HK) in a mixed log-linear model. Results from this study can provide abundant knot information so as to describe the knot size and vertical distribution tendency of Mongolian pine plantation.

• 대한산업공학회지
• /
• 제34권1호
• /
• pp.23-31
• /
• 2008

This paper presents accelerated degradation test plans considering adoption of tightened critical values. Under arandom coefficient degradation rate and log-linear acceleration models, the asymptotic variance of an estimatorfor a lifetime quantile at the use condition as the optimization criterion is derived where the degradation ratefollows a lognormal and Reciprocal Weibull distributions, respectively and then the low stress level andproportions ofunits allocated to each stress level are determined. We also show that the developed test plans canbe applied to the multiplicative model with measurement error.

• 응용통계연구
• /
• 제13권1호
• /
• pp.197-206
• /
• 2000

반복비율적합 방법을 확장하여 준독립성모형하에서 불완전한 다차원 분할표에 포함된 결측칸의 최우추정값을 얻기 위한 추정방법을 제안하였다. 제안된 방법은 주변합이 영이 아닌 모든 불완전한 분할표에 적용할 수 있으며 주어진 준로그선형모형의 구조를 해치지 않는다. 또한 결측칸의 위치와 수에 영향을 받지 않고 항상 수렴한다는 것을 확인하였다.

• 접착 및 계면
• /
• 제21권1호
• /
• pp.6-13
• /
• 2020

The objective of the current study is to characterize the long-term stability and efficacy of a structural adhesive assembly under static load. An apparatus was designed to be used in the Instron tensile test machine that would allow for real time modeling of the failure characteristics of an assembly utilizing a moisture- cure adhesive which was bonded to concrete. A regression model was developed that followed a linear - natural log function which was used to predict the expected life of the assembly. Evaluations at different curing times confirmed the structure was more robust with longer cure durations prior to loading. Finally, the results show that under the conditions the assembly was tested, there was only a small amount of inelastic creep and the regression models demonstrated the potential for a stable structure lasting several decades.

• Communications for Statistical Applications and Methods
• /
• 제25권6호
• /
• pp.591-604
• /
• 2018

The accelerated failure time (AFT) model is a linear model under the log-transformation of survival time that has been introduced as a useful alternative to the proportional hazards (PH) model. In this paper we propose variable-selection procedures of fixed effects in a parametric AFT model using penalized likelihood approaches. We use three popular penalty functions, least absolute shrinkage and selection operator (LASSO), adaptive LASSO and smoothly clipped absolute deviation (SCAD). With these procedures we can select important variables and estimate the fixed effects at the same time. The performance of the proposed method is evaluated using simulation studies, including the investigation of impact of misspecifying the assumed distribution. The proposed method is illustrated with a primary biliary cirrhosis (PBC) data set.

• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.203-212
• /
• 2021

To eliminate ambiguities in the existing methods to simplify Chinese pronunciation learning, we propose a model that can predict the pronunciation of Chinese characters automatically. The proposed model relies on a statistical machine translation (SMT) framework. In particular, we consider the components of Chinese characters as the basic unit and consider the pronunciation prediction as a machine translation procedure (the component sequence as a source sentence, the pronunciation, pinyin, as a target sentence). In addition to traditional features such as the bidirectional word translation and the n-gram language model, we also implement a component similarity feature to overcome some typos during practical use. We incorporate these features into a log-linear model. The experimental results show that our approach significantly outperforms other baseline models.