• Communications for Statistical Applications and Methods
• /
• v.24 no.6
• /
• pp.561-581
• /
• 2017

Bayesian statistics can play a key role in the design and analysis of clinical trials and this has been demonstrated for medical device trials. By 1995 Bayesian statistics had been well developed and the revolution in computing powers and Markov chain Monte Carlo development made calculation of posterior distributions within computational reach. The Food and Drug Administration (FDA) initiative of Bayesian statistics in medical device clinical trials, which began almost 20 years ago, is reviewed in detail along with some of the key decisions that were made along the way. Both Bayesian hierarchical modeling using data from previous studies and Bayesian adaptive designs, usually with a non-informative prior, are discussed. The leveraging of prior study data has been accomplished through Bayesian hierarchical modeling. An enormous advantage of Bayesian adaptive designs is achieved when it is accompanied by modeling of the primary endpoint to produce the predictive posterior distribution. Simulations are crucial to providing the operating characteristics of the Bayesian design, especially for a complex adaptive design. The 2010 FDA Bayesian guidance for medical device trials addressed both approaches as well as exchangeability, Type I error, and sample size. Treatment response adaptive randomization using the famous extracorporeal membrane oxygenation example is discussed. An interesting real example of a Bayesian analysis using a failed trial with an interesting subgroup as prior information is presented. The implications of the likelihood principle are considered. A recent exciting area using Bayesian hierarchical modeling has been the pediatric extrapolation using adult data in clinical trials. Historical control information from previous trials is an underused area that lends itself easily to Bayesian methods. The future including recent trends, decision theoretic trials, Bayesian benefit-risk, virtual patients, and the appalling lack of penetration of Bayesian clinical trials in the medical literature are discussed.

• Fisheries and Aquatic Sciences
• /
• v.24 no.6
• /
• pp.207-218
• /
• 2021

This study evaluated the risk of foodborne illness from highly pathogenic Vibrio spp. (Vibrio vulnificus and V. cholerae) by raw whip-arm octopus (Octopus minor) consumption. In total 180 samples of raw whip-arm octopus were collected from markets and examined for the prevalence of V. vulnificus and V. cholerae. Predictive models describing the kinetic behavior of Vibrio spp. in raw whip-arm octopus were developed, and the data on amounts and frequency of raw whip-arm octopus consumption were collected. Using the collected data, a risk assessment simulation was conducted to estimate the probability of foodborne illness raw whip-arm octopus consumption using @RISK. Initial contamination levels of Vibrio spp. in raw whip-arm octopus were -3.9 Log colony-forming unit/g, as estimated by beta distribution fitting. The developed predictive models were appropriate to describe Vibrio spp. in raw whip-arm octopus during distribution and storage with R² values of 0.946-0.964. The consumption frequency and daily consumption amounts of raw whip-arm octopus per person were 0.47% and 57.65 g, respectively. The probability of foodborne illness from raw whip-arm octopus consumption was estimated to be 8.71 × 10^-15 for V. vulnificus and 7.08 × 10^-13 for V. cholerae. These results suggest that the risk of Vibrio spp. infection from raw whip-arm octopus consumption is low in South Korea.

• The Korean Journal of Applied Statistics
• /
• v.21 no.5
• /
• pp.835-843
• /
• 2008

In this paper, we investigate a Bayesian inference for software reliability models based on mean value functions which take the form of the mixture of beta distribution functions. The posterior simulation via the Markov chain Monte Carlo approach is used to produce estimates of posterior properties. Its applicability is illustrated with two real data sets. We compute the predictive distribution and the marginal likelihood of various models to compare the performance of them. The model comparison results show that the model based on the beta-mixture performs better than other models.

• Journal of Distribution Science
• /
• v.18 no.11
• /
• pp.69-77
• /
• 2020

Purpose: This research aims to verify the role of mobile shopping attributes, trustworthiness, and cultural dimensions on mobile shopping intentions in Saudi Arabia. The originality of the model stems from the verification of the moderating impact of cultural variables, namely collectivism and masculinity, and from the integration of trustworthiness as a variable depending on mobile shopping attributes. Research design, data and methodology: A survey was distributed to 233 consumers with different nationalities living in the Kingdom of Saudi Arabia. Structural equation modeling and multi-group analysis were carried out to verify the conceptual model and the moderating variables. Results: The findings support the influence of several innovation attributes, namely complexity and trialability on behavioral intentions, while relative advantage has a direct impact on trustworthiness. A few paths are moderated by masculinity and collectivism. Conclusions: Culture and mobile commerce attributes need to be thought out by managers as factors influencing mobile commerce segmentation for expatriates and locals. Trustworthiness is also a key factor of mobile shopping adoption. Limitations and future research ideas are presented to enrich the proposed model and improve its predictive validity.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.1
• /
• pp.51-57
• /
• 2012

This paper provides a safety guideline for DC supplied home appliances through the comparative analysis of existing safety guideline for AC supplied home appliances. For this purpose, a predictive DC home appliance model is suggested and in special international safety standards of AC appliances are also analyzed. Moreover, a DC distribution system is built to verify the validity of the proposed safety guideline. The detailed analyzing process is explained with help of informative experimental results.

• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.269-279
• /
• 2015

This paper considers inferences of random effects. We show that the proposed confidence distribution (CD) performs well in logistic regression for random intercepts with small samples. Real data analyses are also done to identify the subject effects clearly.

• Proceedings of the Korean Geotechical Society Conference
• /
• 1992.12a
• /
• pp.19-32
• /
• 1992

Objectives of this study are : 1) to utilize capillary theory and obtain pore-size distribution profiles from moisture-suction relationships using Laplace theory. 2) to investigate the behavior of Light Non-Aqueous Phase Liquids(LNAPLs) in the subsurface environment and to develop several predictive relationships which can be used to assess the effectiveness of various LNAPLs remediation technologies. The relationship to predict pore-size distribution function expressed in differencial equation is found by using capillary theory. Also, experiments are conducted to : the various LNAPLs subjected to vadose zone drainage, groundwater table drainage, waterflooding with surfactants. The experiments are performed with #2 heating oil, jet fuel. and kerosene. Several relationships have been derived describing the effect of various properties and process parameters on the LNAPL residual saturation.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.37-53
• /
• 2024

In this study, flood records from 79 sites across Thailand were analyzed to estimate flood indices using the regional frequency analysis based on the L-moments method. Observation sites were grouped into homogeneous regions using k-means and Ward's clustering techniques. Among various distributions evaluated, the generalized extreme value distribution emerged as the most appropriate for certain regions. Regional growth curves were subsequently established for each delineated region. Furthermore, 20- and 100-year return values were derived to illustrate the recurrence intervals of maximum rainfall across Thailand. The predicted return values tend to increase at each site, which is associated with growth curves that could describe an increasing long-term predictive pattern. The findings of this study hold significant implications for water management strategies and the design of flood mitigation structures in the country.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.56 no.4
• /
• pp.384-394
• /
• 2020

This paper proposes an outlier detection model based on machine learning that can diagnose the presence or absence of major engine parts through unsupervised learning analysis of main engine big data of a ship. Engine big data of the ship was collected for more than seven months, and expert knowledge and correlation analysis were performed to select features that are closely related to the operation of the main engine. For unsupervised learning analysis, ensemble model wherein many predictive models are strategically combined to increase the model performance, is used for anomaly detection. As a result, the proposed model successfully detected the anomalous engine status from the normal status. To validate our approach, clustering analysis was conducted to find out the different patterns of anomalies the anomalous point. By examining distribution of each cluster, we could successfully find the patterns of anomalies.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.9
• /
• pp.4989-4992
• /
• 2013

Aim: To compare p16INK4a immunocytochemistry with the HPV polymerase chain reaction in predicting high grade cervical squamous intraepithelial lesions. Materials and Methods: This diagnostic case-control study was conducted from January 2010 until December 2010. We obtained 30 samples, classified according to the degree of cervical intraepithelial neoplasia (CIN): 11 samples for CIN 1, 9 samples for CIN 2, and 10 samples for CIN 3. HPV PCR, p16INK4a immunocytochemistry, and histopathological examination were performed on all samples. Statistical analysis was conducted using SPSS 20.0. Results: In predicting CIN 2-3, we found p16INK4a to have similar specificity and positive predictive value as HPV PCR (95%, 97.2% vs 96.7%), but better sensitivity (87.5% vs 72.5%) and negative predictive value (82.1% vs 67.6%). The most prevalent types of high-risk HPV in our study were HPV 33, 35, 58, 52, and 16. Conclusions: p16INK4a has better diagnostic values than HPV PCR and may be incorporated in the triage of ASCUS and LSIL to replace HPV PCR. Genotype distribution of HPV differs in each region, providing a challenge to develop HPV vaccines based on the epidemiology of HPV in that particular region.