Joungyoun Kim

A Burner-Type Trap for Particulate Matter From a Diesel Engine

Work on the reduction of particulate matter from a Diesel engine has led to a new trap and a method of controlling the combustion rate of the particulate matter filtered in the trap. Ceramic cordierite is a major component of the trap and is susceptible to thermal shock. Thus, techniques were tried to reduce the peak temperature and temperature gradients in the ceramic filter because these were assumed to be the main factors causing thermal shock of the ceramic filter during regeneration. Temperatures were measured inside the filter during regeneration; the oxygen concentration at the outlet of the filter was also measured, to investigate the combustion characteristics of the particulate matter. The temperature distributions and temperature gradients in the filter during regeneration varied widely according to the regeneration control scheme. It was found that intermittent combustion of the particulate matter assured relatively desirable temperature characteristics for durability of the ceramic filter. In addition, modification of the technique resulted in efficient regeneration of the trap.

An EM algorithm for the proportional hazards model with doubly censored data

In this paper, we consider a new procedure for estimating parameters in the proportional hazards model with doubly censored data. Computing the maximum likelihood estimator with doubly censored data is often nontrivial and requires a certain constraint optimization procedure, which is computationally unstable and sometimes fails to converge. We propose an approximated likelihood and study the maximum approximated likelihood estimator, which is obtained by maximizing the approximated likelihood. In comparison to the maximum likelihood estimator, this new estimator is stable and always converges with an efficient EM algorithm we develop. The stability of the new estimator even with moderate sample sizes is amply demonstrated through simulated and real data. For theoretical justification of the approximated likelihood, we show the consistency of the maximum approximated likelihood estimator.

Detection of gene-environment interactions in a family-based population using SCAD: G. KIM ET AL.

Gene-environment interaction (GxE) is emphasized as one potential source of missing genetic variation on disease traits, and the ultimate goal of GxE research is prediction of individual risk and prevention of complex diseases. However, there are various challenges in statistical analysis of GxE. In this paper, we focus on the three methodological challenges: (i) the high dimensions of genes; (ii) the hierarchical structure between interaction effects and their corresponding main effects; and (iii) the correlation among subjects from family-based population studies. In this paper, we propose an algorithm that approaches all three challenges simultaneously. This is the first penalized method focusing on an interaction search based on a linear mixed effect model. For verification, we compare the empirical performance of our new method with other existing methods in simulation study. The results demonstrate the superiority of our method under overall simulation setup. In particular, the outperformance obviously becomes greater as the correlation among subjects increases. In addition, the new method provides a robust estimate for the correlation among subjects. We also apply the new method on Genetics of Lipid Lowering Drugs and Diet Network study data. Copyright

Randomized trial of subfascial infusion of ropivacaine for early recovery in laparoscopic colorectal cancer surgery

Background There is a need for investigating the analgesic method as part of early recovery after surgery tailored for laparoscopic colorectal cancer (LCRC) surgery. In this randomized trial, we aimed to investigate the analgesic efficacy of an inverse ‘v’ shaped bilateral, subfascial ropivacaine continuous infusion in LCRC surgery. Methods Forty two patients undergoing elective LCRC surgery were randomly allocated to one of two groups to receive either 0.5% ropivacaine continuous infusion at the subfascial plane (n = 20, R group) or fentanyl intravenous patient controlled analgesia (IV PCA) (n = 22, F group) for postoperative 72 hours. The primary endpoint was the visual analogue scores (VAS) when coughing at postoperative 24 hours. Secondary end points were the VAS at 1, 6, 48, and 72 hours, time to first flatus, time to first rescue meperidine requirement, rescue meperidine consumption, length of hospital stay, postoperative nausea and vomiting, sedation, hypotension, dizziness, headache, and wound complications. Results The VAS at rest and when coughing were similar between the groups throughout the study. The time to first gas passage and time to first rescue meperidine at ward were significantly shorter in the R group compared to the F group (P = 0.010). Rescue meperidine was administered less in the R group; however, without statistical significance. Other study parameters were not different between the groups. Conclusions Ropivacaine continuous infusion with an inverse ‘v ’ shaped bilateral, subfascial catheter placement showed significantly enhanced bowel recovery and analgesic efficacy was not different from IV PCA in LCRC surgery.

Detection of gene–environment interactions in a family‐based population using SCAD

Gene–environment interaction (GxE) is emphasized as one potential source of missing genetic variation on disease traits, and the ultimate goal of GxE research is prediction of individual risk and prevention of complex diseases. However, there are various challenges in statistical analysis of GxE. In this paper, we focus on the three methodological challenges: (i) the high dimensions of genes; (ii) the hierarchical structure between interaction effects and their corresponding main effects; and (iii) the correlation among subjects from family-based population studies. In this paper, we propose an algorithm that approaches all three challenges simultaneously. This is the first penalized method focusing on an interaction search based on a linear mixed effect model. For verification, we compare the empirical performance of our new method with other existing methods in simulation study. The results demonstrate the superiority of our method under overall simulation setup. In particular, the outperformance obviously becomes greater as the correlation among subjects increases. In addition, the new method provides a robust estimate for the correlation among subjects. We also apply the new method on Genetics of Lipid Lowering Drugs and Diet Network study data. Copyright

ROC Estimation from Clustered Data with an Application to Liver Cancer Data

In this article, we propose a regression model to compare the performances of different diagnostic methods having clustered ordinal test outcomes. The proposed model treats ordinal test outcomes (an ordinal categorical variable) as grouped-survival time data and uses random effects to explain correlation among outcomes from the same cluster. To compare different diagnostic methods, we introduce a set of covariates indicating diagnostic methods and compare their coefficients. We find that the proposed model defines a Lehmann family and can also introduce a location-scale family of a receiver operating characteristic (ROC) curve. The proposed model can easily be estimated using standard statistical software such as SAS and SPSS. We illustrate its practical usefulness by applying it to testing different magnetic resonance imaging (MRI) methods to detect abnormal lesions in a liver.