• Journal of the Korean Statistical Society
• /
• v.8 no.1
• /
• pp.15-21
• /
• 1979

A zone of sensitivity is developed to investigate the effect of nonnormality on the Bayes decision function for testing mean of a normal population when either parent or prior belongs to Edgeworthian family of moderately nonnormal probability density functions.

• Communications for Statistical Applications and Methods
• /
• v.4 no.3
• /
• pp.787-793
• /
• 1997

It is well known that the assumption of independence is ofter not valid for real data. This phenomenon has been observed empirically by many prominent scientists. In this article the sensitivity of dependence on Bayes test of a sharp null hypothesis is considered. The robustness is considered with respect to the significant level and the prior probability on the null hypothesis.

• Korean Journal of Construction Engineering and Management
• /
• v.17 no.5
• /
• pp.13-21
• /
• 2016

Insolvency of construction companies that play the role of main contractors can lead to clients' losses due to non-fulfillment of construction contracts, and it can have negative effects on the financial soundness of construction companies and suppliers. The construction industry has the cash flow financial characteristic of receiving a project and getting payment based on the progress of the construction. As such, insolvency during project progress can lead to financial losses, which is why the prediction of construction companies is so important. The prediction of insolvency of Korean construction companies are often made through the KMV model from the KMV (Kealhofer McQuown and Vasicek) Company developed in the U.S. during the early 90s, but this model is insufficient in predicting construction companies because it was developed based on credit risk assessment of general companies and banks. In addition, the predictive performance of KMV value's insolvency probability is continuously being questioned due to lack of number of analyzed companies and data. Therefore, in order to resolve such issues, the Bayesian Probabilistic Approach is to be combined with the existing insolvency predictive probability model. This is because if the Prior Probability of Bayesian statistics can be appropriately predicted, reliable Posterior Probability can be predicted through ensured conditionality on the evidence despite the lack of data. Thus, this study is to measure the Expected Default Frequency (EDF) by utilizing the Bayesian Probabilistic Approach with the existing insolvency predictive probability model and predict the accuracy by comparing the result with the EDF of the existing model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.593-594
• /
• 2015

In wireless sensor networks (WSNs), due to the very low data rate, the sleeping schedule is usually used to save consumed energy and prolong the lifetime of nodes. However, duty-cycled approach can cause a high end-to-end (E2E) delay. In this paper, we study a node scheduling algorithm in WSNs such that E2E delay meets bounded delay with a given probability. We have applied the probability theory to spot the relationship between E2E delay and node interval. Simulation result illustrates that we can create the network to achieve given delay with prior probability and high energy use efficient as well.

• ETRI Journal
• /
• v.27 no.4
• /
• pp.461-464
• /
• 2005

Recently, a variety of confidence measures for utterance verification has been studied to improve speech recognition performance by rejecting out-of-vocabulary inputs. Most of the conventional confidence measures for utterance verification are based primarily on hypothesis testing or an approximated posterior probability, and their performances depend on the robustness of an alternative hypothesis or the prior probability. We introduce a novel confidence measure called a search confusion rate (SCR), which does not require an alternative hypothesis or the approximation of posterior probability. Our confusion-based approach shows better performance in additive noise-corrupted speech as well as in clean speech.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.5095-5111
• /
• 2016

The Probability Hypothesis Density (PHD) filter is a suboptimal approximation and tractable alternative to the multi-target Bayesian filter based on random finite sets. However, the PHD filter fails to track newborn targets when the target birth intensity is unknown prior to tracking. In this paper, a dual detection-guided newborn target intensity PHD algorithm is developed to solve the problem, where two schemes, namely, a newborn target intensity estimation scheme and improved measurement-driven scheme, are proposed. First, the newborn target intensity estimation scheme, consisting of the Dirichlet distribution with the negative exponent parameter and target velocity feature, is used to recursively estimate the target birth intensity. Then, an improved measurement-driven scheme is introduced to reduce the errors of the estimated number of targets and computational load. Simulation results demonstrate that the proposed algorithm can achieve good performance in terms of target states, target number and computational load when the newborn target intensity is not predefined in multi-target tracking systems.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.111-116
• /
• 2004

It is essential to know the information about the prior model for wavelet coefficients, the probability distribution of noise, and the variance of wavelet coefficients for noise reduction using Bayesian estimation in wavelet domain. In general denoising methods, the signal variance is estimated from the proper prior model for wavelet coefficients. In this paper, we propose a variable window size decision algorithm to estimate signal variance according to image region. Simulation results shows the proposed method have better PSNRs than those of the state of art denoising methods.

• Korean Journal of Clinical Pharmacy
• /
• v.25 no.1
• /
• pp.9-17
• /
• 2015

Background: Biologic disease-modifying antirheumatic drugs (bDMARDs) extend the treatment choices for rheumatoid arthritis patients with insufficient response or intolerance to conventional DMARDs (cDMARDs). These agents have considerable efficacy compared with conventional DMARDs, but only a few head-to-head comparisons among these agents have been performed. The objective of this systematic review and network meta-analysis (NMA) was to compare the relative efficacy of Certolizumab with conventional DMARD to licensed bDMARD with cDMARD therapy for patients who failed to prior cDMARD treatment under the condition of the reimbursement coverage criteria in Korea. Methods: A systematic review was conducted using MEDLINE and Cochrane library. Key endpoints were the American College of Rheumatology (ACR) responses of 20/50/70 at six months. Bayesian outcomes were calculated as median of treatment effect, probability of the best, Odds Ratio (OR) and probability that OR was greater than one. Results: Compared with other bDMARDs, Certolizumab were associated with higher or comparable ACR response rates; in ACR20, the OR (probability of OR>1) was 2.08 (92.6%) for Adalimumab, 1.86 (85.7%) for Etanercept, 1.89 (79.5%) for Golimumab, 2.36 (92.1%) for Infliximab, 1.79 (87.0%) for Abatacept, 1.74 (80.8%) for Rituximab and 1.82 (86.8%) for Tocilizaumab. In ACR50 and ACR70, the ORs did not present significant differences. Conclusion: Certolizaumab with cDMARD was more effective or comparable than other bDMARDs in patients who failed prior cDMARD treatment.

• Korean Journal of Social Welfare
• /
• v.62 no.4
• /
• pp.249-274
• /
• 2010

This study examines a casaul relationship between depression and welfare transitions of the National Basic Likelihood Protection Program. From a social selection perspective, prior high levels of depression are likely to select people into welfare or serve as a barrier to leaving welfare. From a social causation perspective, entering or exiting welfare can change the levels of depression. These hypotheses were tested using KOWEPS(Korean Welfare Panel study) 2005~2007. The results are as follows. First, entering welfare clearly increases the levels of depression. The increased economic stress resulting from falling into poverty seems to play a major role in the negative effect of welfare entry. Second, exiting welfare does not decrease the levels of depression. However, when welfare exits are classified into distinctive categories, welfare exit combined with concurrent poverty exit is likely to decrease the levels of depression. Third, high levels of depression clearly increase the probability of entering welfare regardless of the prior poverty status. Fourth, high levels of depression do not decrease the probability of exiting welfare, but rather increase the probability of an administrative disentitlement which leads to even worse economic conditions after exiting welfare. One implication of these findings is that negative policies such as time limit and strengthening sanctions can increase the number of welfare cyclers who are able-bodied but mentally weak.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.49 no.3
• /
• pp.11-20
• /
• 2007

Estimation of crop consumptive use is a key term of agricultural water resource systems design and operation. The 10-year return period drought has special aspects as a reference period in design process of irrigation systems in terms of agricultural water demand analysis so that crop evapotranspiration (ETc) about the return period also has to be analyzed to assist understanding of crop water requirement of paddy rice. In this study, The ETc of 10-year return period drought was computed using frequency analysis by 54 meteorological stations. To find an optimal probability distribution, 8 types of probability distribution function were tested by three the goodness of fit tests including ${\chi}^2$(Chi-Square), K-S (Kolmogorov-Smirnov) and PPCC (Probability Plot Correlation Coefficient). Optimal probability distribution function was selected the 2-parameter Log-Normal (LN2) distribution function among 8 distribution functions. Using the two selected distribution functions, the ETc of 10-year return period drought was estimated for 54 meteorological stations and compared with prior study results suggested by other researchers.