Fixed-Width Output Analysis for Markov Chain Monte Carlo

Markov chain Monte Carlo is a method of producing a correlated sample in order to estimate features of a complicated target distribution via simple ergodic averages. A fundamental question in MCMC applications is when should the sampling stop? That is, when are the ergodic averages good estimates of the desired quantities? We consider a method that stops the MCMC sampling the first time the width of a confidence interval based on the ergodic averages is less than a user-specified value. Hence calculating Monte Carlo standard errors is a critical step in assessing the output of the simulation. In particular, we consider the regenerative simulation and batch means methods of estimating the variance of the asymptotic normal distribution. We describe sufficient conditions for the strong consistency and asymptotic normality of both methods and investigate their finite sample properties in a variety of examples.

Rock fracture mean trace length estimation and confidence interval calculation using maximum likelihood methods

There has been a resurgence of interest in the mean trace length estimator of Pahl for window sampling of traces. The estimator has been dealt with by Mauldon and Zhang and Einstein in recent publications. The estimator is a very useful one in that it is non-parametric. However, despite some discussion regarding the statistical distribution of the estimator, none of the recent works or the original work by Pahl provide a rigorous basis for the determination a confidence interval for the estimator or a confidence region for the estimator and the corresponding estimator of trace spatial intensity in the sampling window. This paper shows, by consideration of a simplified version of the problem but without loss of generality, that the estimator is in fact the maximum likelihood estimator (MLE) and that it can be considered essentially unbiased. As the MLE, it possesses the least variance of all estimators and confidence intervals or regions should therefore be available through application of classical ML theory. It is shown that valid confidence intervals can in fact be determined. The results of the work and the calculations of the confidence intervals are illustrated by example. (C) 2003 Elsevier Science Ltd. All rights reserved.

Point-wise confidence interval estimation by neural networks: A comparative study based on automotive engine calibration.

In developing neural network techniques for real world applications it is still very rare to see estimates of confidence placed on the neural network predictions. This is a major deficiency, especially in safety-critical systems. In this paper we explore three distinct methods of producing point-wise confidence intervals using neural networks. We compare and contrast Bayesian, Gaussian Process and Predictive error bars evaluated on real data. The problem domain is concerned with the calibration of a real automotive engine management system for both air-fuel ratio determination and on-line ignition timing. This problem requires real-time control and is a good candidate for exploring the use of confidence predictions due to its safety-critical nature.

Conditional Confidence Interval for the Scale Parameter of a Weibull Distribution

2000 Mathematics Subject Classification: 62F25, 62F03.

Test of four colon cancer risk-scores in formalin fixed paraffin embedded microarray gene expression data.

BACKGROUND: Prognosis prediction for resected primary colon cancer is based on the T-stage Node Metastasis (TNM) staging system. We investigated if four well-documented gene expression risk scores can improve patient stratification. METHODS: Microarray-based versions of risk-scores were applied to a large independent cohort of 688 stage II/III tumors from the PETACC-3 trial. Prognostic value for relapse-free survival (RFS), survival after relapse (SAR), and overall survival (OS) was assessed by regression analysis. To assess improvement over a reference, prognostic model was assessed with the area under curve (AUC) of receiver operating characteristic (ROC) curves. All statistical tests were two-sided, except the AUC increase. RESULTS: All four risk scores (RSs) showed a statistically significant association (single-test, P < .0167) with OS or RFS in univariate models, but with HRs below 1.38 per interquartile range. Three scores were predictors of shorter RFS, one of shorter SAR. Each RS could only marginally improve an RFS or OS model with the known factors T-stage, N-stage, and microsatellite instability (MSI) status (AUC gains < 0.025 units). The pairwise interscore discordance was never high (maximal Spearman correlation = 0.563) A combined score showed a trend to higher prognostic value and higher AUC increase for OS (HR = 1.74, 95% confidence interval [CI] = 1.44 to 2.10, P < .001, AUC from 0.6918 to 0.7321) and RFS (HR = 1.56, 95% CI = 1.33 to 1.84, P < .001, AUC from 0.6723 to 0.6945) than any single score. CONCLUSIONS: The four tested gene expression-based risk scores provide prognostic information but contribute only marginally to improving models based on established risk factors. A combination of the risk scores might provide more robust information. Predictors of RFS and SAR might need to be different.

A systematic review of the performance of ceramic and metal implant abutments supporting fixed implant reconstructions

OBJECTIVES: The objective of this systematic review was to assess the 5-year survival rates and incidences of complications associated with ceramic abutments and to compare them with those of metal abutments. METHODS: An electronic Medline search complemented by manual searching was conducted to identify randomized-controlled clinical trials, and prospective and retrospective studies providing information on ceramic and metal abutments with a mean follow-up time of at least 3 years. Patients had to have been examined clinically at the follow-up visit. Assessment of the identified studies and data abstraction was performed independently by three reviewers. Failure rates were analyzed using standard and random-effects Poisson regression models to obtain summary estimates of 5-year survival proportions. RESULTS: Twenty-nine clinical and 22 laboratory studies were selected from an initial yield of 7136 titles and data were extracted. The estimated 5-year survival rate of ceramic abutments was 99.1% [95% confidence interval (CI): 93.8-99.9%] and 97.4% (95% CI: 96-98.3%) for metal abutments. The estimated cumulative incidence of technical complications after 5 years was 6.9% (95% CI: 3.5-13.4%) for ceramic abutments and 15.9% (95% CI: 11.6-21.5%) for metal abutments. Abutment screw loosening was the most frequent technical problem, occurring at an estimated cumulative incidence after 5 years of 5.1% (95% CI: 3.3-7.7%). All-ceramic crowns supported by ceramic abutments exhibited similar annual fracture rates as metal-ceramic crowns supported by metal abutments. The cumulative incidence of biological complications after 5 years was estimated at 5.2% (95% CI: 0.4-52%) for ceramic and 7.7% (95% CI: 4.7-12.5%) for metal abutments. Esthetic complications tended to be more frequent at metal abutments. A meta-analysis of the laboratory data was impossible due to the non-standardized test methods of the studies included. CONCLUSION: The 5-year survival rates estimated from annual failure rates appeared to be similar for ceramic and metal abutments. The information included in this review did not provide evidence for differences of the technical and biological outcomes of ceramic and metal abutments. However, the information for ceramic abutments was limited in the number of studies and abutments analyzed as well as the accrued follow-up time. Standardized methods for the analysis of abutment strength are needed.

A systematic review of the survival and complication rates of implant supported fixed dental prostheses with cantilever extensions after an observation period of at least 5 years

OBJECTIVE: The aim of this systematic review was to assess the survival rates of short-span implant-supported cantilever fixed dental prostheses (ICFDPs) and the incidence of technical and biological complications after an observation period of at least 5 years. MATERIAL AND METHODS: An electronic MEDLINE search supplemented by manual searching was conducted to identify prospective or retrospective cohort studies reporting data of at least 5 years on ICFDPs. Five- and 10-year estimates for failure and complication rates were calculated using standard or random-effect Poisson regression analysis. RESULTS: The five studies eligible for the meta-analysis yielded an estimated 5- and 10-year ICFDP cumulative survival rate of 94.3% [95 percent confidence interval (95% CI): 84.1-98%] and 88.9% (95% CI: 70.8-96.1%), respectively. Five-year estimates for peri-implantitis were 5.4% (95% CI: 2-14.2%) and 9.4% (95% CI: 3.3-25.4%) at implant and prosthesis levels, respectively. Veneer fracture (5-year estimate: 10.3%; 95% CI: 3.9-26.6%) and screw loosening (5-year estimate: 8.2%; 95% CI: 3.9-17%) represented the most common complications, followed by loss of retention (5-year estimate: 5.7%; 95% CI: 1.9-16.5%) and abutment/screw fracture (5-year estimate: 2.1%; 95% CI: 0.9-5.1%). Implant fracture was rare (5-year estimate: 1.3%; 95% CI: 0.2-8.3%); no framework fracture was reported. Radiographic bone level changes did not yield statistically significant differences either at the prosthesis or at the implant levels when comparing ICFDPs with short-span implant-supported end-abutment fixed dental prostheses. CONCLUSIONS: ICFDPs represent a valid treatment modality; no detrimental effects can be expected on bone levels due to the presence of a cantilever extension per se.

Fixed low-dose ultrasound-assisted catheter-directed thrombolysis for intermediate- and high-risk pulmonary embolism

AIMS No standardized local thrombolysis regimen exists for the treatment of pulmonary embolism (PE). We retrospectively investigated efficacy and safety of fixed low-dose ultrasound-assisted catheter-directed thrombolysis (USAT) for intermediate- and high-risk PE. METHODS AND RESULTS Fifty-two patients (65 ± 14 years) of whom 14 had high-risk PE (troponin positive in all) and 38 intermediate-risk PE (troponin positive in 91%) were treated with intravenous unfractionated heparin and USAT using 10 mg of recombinant tissue plasminogen activator per device over the course of 15 h. Bilateral USAT was performed in 83% of patients. During 3-month follow-up, two [3.8%; 95% confidence interval (CI) 0.5-13%] patients died (one from cardiogenic shock and one from recurrent PE). Major non-fatal bleeding occurred in two (3.8%; 95% CI, 0.5-13%) patients: one intrathoracic bleeding after cardiopulmonary resuscitation requiring transfusion, one intrapulmonary bleeding requiring lobectomy. Mean pulmonary artery pressure decreased from 37 ± 9 mmHg at baseline to 25 ± 8 mmHg at 15 h (P < 0.001) and cardiac index increased from 2.0 ± 0.7 to 2.7 ± 0.9 L/min/m(2) (P < 0.001). Echocardiographic right-to-left ventricular end-diastolic dimension ratio decreased from 1.42 ± 0.21 at baseline to 1.06 ± 0.23 at 24 h (n = 21; P < 0.001). The greatest haemodynamic benefit from USAT was found in patients with high-risk PE and in those with symptom duration < 14 days. CONCLUSION A standardized catheter intervention approach using fixed low-dose USAT for the treatment of intermediate- and high-risk PE was associated with rapid improvement in haemodynamic parameters and low rates of bleeding complications and mortality.

Systematic review of the survival rate and incidence of biologic, technical, and esthetic complications of single implant abutments supporting fixed prostheses

Purpose: To assess the 5-year survival rate and number of technical, biologic, and esthetic complications involving implant abutments. Materials and Methods: Electronic (Medline) and hand searches were performed to assess studies on metal and ceramic implant abutments. Relevant data from a previous review were included. Two reviewers independently extracted the data. Failure and complication rates were analyzed, and estimates of 5-year survival proportions were calculated from the relationship between event rate and survival function. Multivariable robust Poisson regression was used to compare abutment characteristics. Results: The search yielded 1,558 titles and 274 abstracts. Twenty-four studies were selected for data analysis. The survival rate for ceramic abutments was 97.5% (95% confidence interval [CI]): 89.6% to 99.4%) and 97.6% (95% CI: 96.2% to 98.5%) for metal abutments. The overall 5-year rate for technical complications was 11.8% (95% CI: 8.5% to 16.3%), 8.9% (95% CI: 4.3% to 17.7%) for ceramic and 12.0% (95% CI: 8.5% to 16.8%) for metal abutments. Biologic complications occurred with an overall rate of 6.4% (95% CI: 3.3% to 12.0%), 10.4% (95% CI: 1.9% to 46.7%) for ceramic, and 6.1% (95% CI: 3.1% to 12.0%) for metal abutments. Conclusions: The present meta-analysis on single-implant prostheses presents high survival rates of single implants, abutments, and prostheses after 5 years of function. No differences were found for the survival and failure rates of ceramic and metal abutments. No significant differences were found for technical, biologic, and esthetic complications of internally and externally connected abutments.

Clinical Performance of Screw- Versus Cement-Retained Fixed Implant-Supported Reconstructions- A Systematic Review.

PURPOSE To assess the survival outcomes and reported complications of screw- and cement-retained fixed reconstructions supported on dental implants. MATERIALS AND METHODS A Medline (PubMed), Embase, and Cochrane electronic database search from 2000 to September 2012 using MeSH and free-text terms was conducted. Selected inclusion and exclusion criteria guided the search. All studies were first reviewed by abstract and subsequently by full-text reading by two examiners independently. Data were extracted by two examiners and statistically analyzed using a random effects Poisson regression. RESULTS From 4,324 abstracts, 321 full-text articles were reviewed. Seventy-three articles were found to qualify for inclusion. Five-year survival rates of 96.03% (95% confidence interval [CI]: 93.85% to 97.43%) and 95.55% (95% CI: 92.96% to 97.19%) were calculated for cemented and screw-retained reconstructions, respectively (P = .69). Comparison of cement and screw retention showed no difference when grouped as single crowns (I-SC) (P = .10) or fixed partial dentures (I-FDP) (P = .49). The 5-year survival rate for screw-retained full-arch reconstructions was 96.71% (95% CI: 93.66% to 98.31). All-ceramic reconstruction material exhibited a significantly higher failure rate than porcelain-fused-to-metal (PFM) in cemented reconstructions (P = .01) but not when comparing screw-retained reconstructions (P = .66). Technical and biologic complications demonstrating a statistically significant difference included loss of retention (P ≤ .01), abutment loosening (P ≤ .01), porcelain fracture and/or chipping (P = .02), presence of fistula/suppuration (P ≤ .001), total technical events (P = .03), and total biologic events (P = .02). CONCLUSIONS Although no statistical difference was found between cement- and screw-retained reconstructions for survival or failure rates, screw-retained reconstructions exhibited fewer technical and biologic complications overall. There were no statistically significant differences between the failure rates of the different reconstruction types (I-SCs, I-FDPs, full-arch I-FDPs) or abutment materials (titanium, gold, ceramic). The failure rate of cemented reconstructions was not influenced by the choice of a specific cement, though cement type did influence loss of retention.

Small sample confidence intervals for the mean of a positively skewed distribution

This thesis proposes some confidence intervals for the mean of a positively skewed distribution. The following confidence intervals are considered: Student-t, Johnson-t, median-t, mad-t, bootstrap-t, BCA, T1 , T3 and six new confidence intervals, the median bootstrap-t, mad bootstrap-t, median T1, mad T1 , median T3 and the mad T3. A simulation study has been conducted and average widths, coefficient of variation of widths, and coverage probabilities were recorded and compared across confidence intervals. To compare confidence intervals, the width and coverage probabilities were compared so that smaller widths indicated a better confidence interval when coverage probabilities were the same. Results showed that the median T1 and median T3 outperformed other confidence intervals in terms of coverage probability and the mad bootstrap-t, mad-t, and mad T3 outperformed others in terms of width. Some real life data are considered to illustrate the findings of the thesis.

Sibilância em crianças e adolescentes vizinhos a uma indústria petroquímica no Rio Grande do Norte, Brasil

OBJETIVO: Verificar a associação entre relato de sibilância em crianças e adolescentes e o local de residência em relação à dispersão dos poluentes atmosféricos emitidos pelo Pólo Petroquímico (PPQ) de Guamaré (RN). MÉTODOS: Estudo transversal de relato de sibilância em crianças e adolescentes de 0 a 14 anos de idade, residentes no entorno do PPQ de Guamaré, em 2006. Foi utilizado o questionário padronizado do International Study of Asthma and Allergies in Childhood, acrescido de questões relativas ao tabagismo, renda, moradia e escolaridade. Concentrações diárias de PM10, PM2,5, carbono grafítico, SO2, NO2, O3, benzeno, tolueno e xilenos foram medidas em uma estação de monitoramento fixa. As comunidades residentes na área de influência das emissões do PPQ foram classificadas, segundo a direção preferencial dos ventos, em expostas e de referência. RESULTADOS: Participaram do estudo 209 crianças e adolescentes. As concentrações médias diárias dos poluentes monitorados mantiveram-se abaixo dos limites estabelecidos nos padrões de qualidade do ar. A prevalência de sibilos nos últimos 12 meses foi de 27,3%. Associações estatisticamente significantes com sibilos nos últimos 12 meses foram verificadas mesmo após ajustamentos para comunidades expostas [razão de chances (odds ratio, ORajust) = 2,01; intervalo de confiança de 95% (IC95%) 1,01-4,01], gênero masculino (ORajust = 2,50; IC95% 1,21-5,18) e idade de 0 a 6 anos (ORajust = 5,00; IC95% 2,41-10,39). CONCLUSÃO: Mesmo em baixas concentrações de poluentes atmosféricos, a ocorrência de sintomas respiratórios em crianças e adolescentes nas comunidades no entorno de um PPQ esteve associada a residência na direção preferencial dos ventos, mostrando-se mais vulnerável o grupo de pré-escolares do gênero masculino.

Interval breast cancers in an Australian mammographic screening program

Objective: To determine the incidence of interval cancers which occurred in the first 12 months after mammographic screening at a mammographic screening service. Design: Retrospective analysis of data obtained by crossmatching the screening Service and the New South Wales Central Cancer Registry databases. Setting: The Central & Eastern Sydney Service of BreastScreen NSW. Participants: Women aged 40-69 years at first screen, who attended for their first or second screen between 1 March 1988 and 31 December 1992. Main outcome measures: Interval-cancer rates per 10 000 screens and as a proportion of the underlying incidence of breast cancer (as estimated by the underlying rate in the total NSW population). Results: The 12-month interval-cancer incidence per 10 000 screens was 4.17 for the 40-49 years age group (95% confidence interval [CI], 1.35-9.73) and 4.64 for the 50-69 years age group (95% CI, 2.47-7.94). Proportional incidence rates were 30.1% for the 40-49 years age group (95% CI, 9.8-70.3) and 22% for the 50-69 years age group (95% CI, 11.7-37.7). There was no significant difference between the proportional incidence rate for the 50-69 years age group for the Central & Eastern Sydney Service and those of major successful overseas screening trials. Conclusion: Screening quality was acceptable and should result in a significant mortality reduction in the screened population. Given the small number of cancers involved, comparison of interval-cancer statistics of mammographic screening programs with trials requires age-specific or age-adjusted data, and consideration of confidence intervals of both program and trial data.

Prognostic Value of Dobutamine Stress Echocardiography With Early Injection of Atropine With Versus Without Chronic Beta-Blocker Therapy in Patients With Known or Suspected Coronary Heart Disease

Although a new protocol of dobutamine stress echocardiography with the early injection of atropine (EA-DSE) has been demonstrated to be useful in reducing adverse effects and increasing the number of effective tests and to have similar accuracy for detecting coronary artery disease (CAD) compared with conventional protocols, no data exist regarding its ability to predict long-term events. The aim of this study was to determine the prognostic value of EA-DSE and the effects of the long-term use of beta blockers on it. A retrospective evaluation of 844 patients who underwent EA-DSE for known or suspected CAD was performed; 309 (37%) were receiving beta blockers. During a median follow-up period of 24 months, 102 events (12%) occurred. On univariate analysis, predictors of events were the ejection fraction (p <0.001), male gender (p <0.001), previous myocardial infarction (p <0.001), angiotensin-converting enzyme inhibitor therapy (p = 0.021), calcium channel blocker therapy (p = 0.034), and abnormal results on EA-DSE (p <0.001). On multivariate analysis, the independent predictors of events were male gender (relative risk [RR] 1.78, 95% confidence interval [CI] 1.13 to 2.81, p = 0.013) and abnormal results on EA-DSE (RR 4.45, 95% CI 2.84 to 7.01, p <0.0001). Normal results on EA-DSE with P blockers were associated with a nonsignificant higher incidence of events than normal results on EA-DSE without beta blockers (RR 1.29, 95% CI 0.58 to 2.87, p = 0.54). Abnormal results on EA-DSE with beta blockers had an RR of 4.97 (95% CI 2.79 to 8.87, p <0.001) compared with normal results, while abnormal results on EA-DSE without beta blockers had an RR of 5.96 (95% CI 3.41 to 10.44, p <0.001) for events, with no difference between groups (p = 0.36). In conclusion, the detection of fixed or inducible wall motion abnormalities during EA-DSE was an independent predictor of long-term events in patients with known or suspected CAD. The prognostic value of EA-DSE was not affected by the long-term use of beta blockers. (C) 2008 Elsevier Inc. All rights reserved. (Am J Cardiol 2008;102:1291-1295)

Family history of cancer: Pooled analysis in the International Head and Neck Cancer Epidemiology consortium

Alcohol and tobacco consumption are well-recognized risk factors for head and neck cancer (HNC). Evidence suggests that genetic predisposition may also play a role. Only a few epidemiologic studies, however, have considered the relation between HNC risk and family history of HNC and other cancers. We pooled individual-level data across 12 case-control studies including 8,967 HNC cases and 13,627 controls. We obtained pooled odds ratios (OR) using fixed and random effect models and adjusting for potential confounding factors. All statistical tests were two-sided. A family history of HNC in first-degree relatives increased the risk of HNC (OR = 1.7, 95% confidence interval, CI, 1.2-2.3). The risk was higher when the affected relative was a sibling (OR = 2.2, 95% CI 1.6-3.1) rather than a parent (OR = 1.5, 95% CI 1.1-1.8) and for more distal HNC anatomic sites (hypopharynx and larynx). The risk was also higher, or limited to, in subjects exposed to tobacco. The OR rose to 7.2 (95% CI 5.5-9.5) among subjects with family history, who were alcohol and tobacco users. A weak but significant association (OR = 1.1, 95% CI 1.0-1.2) emerged for family history of other tobacco-related neoplasms, particularly with laryngeal cancer (OR = 1.3, 95% CI 1.1-1.5). No association was observed for family history of nontobacco-related neoplasms and the risk of HNC (OR = 1.0, 95% CI 0.9-1.1). Familial factors play a role in the etiology of HNC. In both subjects with and without family history of HNC, avoidance of tobacco and alcohol exposure may be the best way to avoid HNC. (C) 2008 Wiley-Liss, Inc,