http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
On Adaptation to Sparse Design in Bivariate Local Linear Regression
Hall, Peter,Seifert, Burkhardt,Turlach, Berwin A. The Korean Statistical Society 2001 Journal of the Korean Statistical Society Vol.30 No.2
Local linear smoothing enjoys several excellent theoretical and numerical properties, an in a range of applications is the method most frequently chosen for fitting curves to noisy data. Nevertheless, it suffers numerical problems in places where the distribution of design points(often called predictors, or explanatory variables) is spares. In the case of univariate design, several remedies have been proposed for overcoming this problem, of which one involves adding additional ″pseudo″ design points in places where the orignal design points were too widely separated. This approach is particularly well suited to treating sparse bivariate design problem, and in fact attractive, elegant geometric analogues of unvariate imputation and interpolation rules are appropriate for that case. In the present paper we introduce and develop pseudo dta rules for bivariate design, and apply them to real data.
Lukas Hefermehl,Karolin Bossert,Venkat M. Ramakrishnan,Burkhardt Seifert,Kurt Lehmann 대한배뇨장애요실금학회 2018 International Neurourology Journal Vol.22 No.2
Purpose: This study aims to objectively characterize the effect of successful nerve sparing (NS) during radical prostatectomy (RP) on postoperative urinary continence (UC) using International Index of Erectile Function (IIEF)-scores and a previously described Expanded Prostate Cancer Index Composite (EPIC) score cutoff value (COV) for UC. Several notable studies on this topic present conflicting outcomes. This is largely due to a lack of clear definitions and consensus regarding preserved erectile function (EF) and UC. Methods: This study is comprised of all patients who underwent RP at the Kantonsspital Baden, Switzerland, between 2004 and 2013. Patients completed self-assessment questionnaires for UC (EPIC) and EF (IIEF) pre- and postoperatively (3, 6, 9, 12, 18, and 24 months; yearly thereafter). We used a previously described EPIC subscore COV, with “satisfactory continence” signified by a score >85. Statistical analysis was performed using Kaplan-Meier and Cox regression analyses for “surgeon-” and “IIEF-defined” NS definitions. Results: Of 236 men with a median age of 63 years (interquartile range [IQR], 59–66 years) and median follow-up time of 48 months (IQR, 30–78 months), 176 underwent unilateral (n=33) or bilateral (n=143) NS RP. Fifty-four underwent non-NS (NNS) RP. Kaplan-Meier analyses identified the following risk factors for UC: age, prostate volume, cancer risk group, and NS status. In surgeon-defined NS RP cases, multivariate analysis for regaining continence demonstrated no significant difference (hazard ratio [HR], 0.78; 95% confidence interval [CI], 0.48–1.25; P=0.3). With successful IIEF-defined NS RPs, regression analysis demonstrated no significant difference (HR, 0.89; 95% CI, 0.59–1.35; P=0.58). Conclusions: In our population, analysis and comparison of surgeon- and IIEF-defined NS and NNS cohorts revealed that NS RP did not improve postoperative UC. The conservation of UC alone should not motivate surgeons or patients to pursue NS RP.
Karolin Bossert,Venkat M. Ramakrishnan,Burkhardt Seifert,Kurt Lehmann,Lukas J. Hefermehl 대한배뇨장애요실금학회 2017 International Neurourology Journal Vol.21 No.4
Purpose: To determine an objective cutoff value (COV) for urinary incontinence (UI) using the Expanded Prostate Cancer Composite (EPIC) score after radical prostatectomy (RP). Methods: From 2004–2013, all RP patients at our institution completed the EPIC urinary domain (EPIC-UD) questionnaire preoperatively and 6 weeks; 3, 6, 9, 12, and 18 months postoperatively; and yearly thereafter. The EPIC-UD is composed of several questions, 4 of which address UI qualitatively (EPIC-UI). Furthermore, patients were asked to complete a global quality of life (QoL) questionnaire regarding continence. The EPIC COV was calculated using receiver operating characteristic (ROC) analysis. Correlations between the EPIC-UI and quantitative QoL were evaluated using the Kendall-Tau test. Results: We analyzed 239 patients with a median age of 63 years (interquartile range [IQR], 59–66 years), a median follow-up of 48 months (IQR, 30–78 months) and a median preoperative EPIC-UI score of 100 (IQR, 91.75–100). The ROC analysis for the distinction between EPIC-UI and the use of ≤1 pad/day yielded an EPIC-UI COV of >85, which we termed the UI-85, with an area under the curve of 0.857 (P<0.0001). A stronger correlation was seen between QoL scores and the UI-85 (1 year postoperatively: correlation coefficient [CC], 0.592; P<0.0001) than between QoL and not using a pad (CC, 0.512; P<0.0001). Conclusions: The calculated COV of the EPIC-UI for continence was 85. UI is a multidimensional condition that cannot be adequately characterized by a single piece of information, such as pad usage only. Hence, the UI-85 represents a nuanced and straightforward tool for monitoring and comparing continence between different time points and cohorts in a multidimensional and objective manner.