Two-sided confidence intervals for the single proportion: comparison of seven methods by Robert G. Newcombe,Statistics in Medicine 1998;17:857–872

Statistics in Medicine (Impact Factor: 2.04). 11/2005; 24(21):3383-4. DOI: 10.1002/sim.2164
Source: PubMed
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The aim was to determine the prevalence of tuberculosis in adolescents in Western Kenya. We conducted a cohort study of 5004 adolescents aged 12-18 years. Adolescents were screened for prevalent tuberculosis using clinical criteria, history of TB contact, and a mantoux test. TB suspects were investigated through 2 sputum examinations (microscopy and liquid culture), and chest radiography. Out of 5004 adolescents enrolled, 1960 (39.2%) were identified as a TB suspect including 1544 with a positive mantoux (prevalence 1544/4808 32.1%), 515 having symptoms suggestive of TB (10.3%) and 144 (2.9%) with household TB contact. Sixteen culture-confirmed (definite) and 18 probable pulmonary TB (PTB) cases were identified reflecting a prevalence estimate of 3.2/1,000 (definite) and 6.8/1,000 all PTB respectively. Only one smear-positive case was detected. The case notification rate among 12-18 year old adolescents for all TB was 101/100,000 yielding a patient diagnostic rate of 0.13 (95% CI 0.03,3.7) cases detected per person-year for all TB. The prevalence of PTB among adolescents is high with the majority of cases not detected routinely. Innovative active case finding including wider use of Xpert MTB/RIF is needed, to detect smear-negative TB among adolescents. Copyright © 2015. Published by Elsevier Ltd.
    International Journal of Infectious Diseases 03/2015; 35. DOI:10.1016/j.ijid.2015.03.008 · 2.33 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Confidence intervals for a binomial parameter or for the ratio of Poisson means are commonly desired in high energy physics (HEP) applications such as measuring a detection efficiency or branching ratio. Due to the discreteness of the data, in both of these problems the frequentist coverage probability unfortunately depends on the unknown parameter. Trade-offs among desiderata have led to numerous sets of intervals in the statistics literature, while in HEP one typically encounters only the classic intervals of Clopper–Pearson (central intervals with no undercoverage but substantial over-coverage) or a few approximate methods which perform rather poorly. If strict coverage is relaxed, some sort of averaging is needed to compare intervals. In most of the statistics literature, this averaging is over different values of the unknown parameter, which is conceptually problematic from the frequentist point of view in which the unknown parameter is typically fixed. In contrast, we perform an (unconditional) average over observed data in the ratio-of-Poisson-means problem. If strict conditional coverage is desired, we recommend Clopper–Pearson intervals and intervals from inverting the likelihood ratio test (for central and non-central intervals, respectively). Lancaster's mid-P modification to either provides excellent unconditional average coverage in the ratio-of-Poisson-means problem.
    Nuclear Instruments and Methods in Physics Research Section A Accelerators Spectrometers Detectors and Associated Equipment 01/2010; 612(2-612):388-398. DOI:10.1016/j.nima.2009.10.156 · 1.32 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Middle cerebral artery (MCA) aneurysms are often considered unsuitable for endovascular coiling because of unfavorable morphological features. With improvements in endovascular techniques, several series have detailed the results and complications of endovascular treatment of MCA aneurysms. We performed a systematic review of published series on endovascular treatment of MCA aneurysms including our experience. We conducted a computerized MEDLINE search of the literature on endovascular treatment of MCA aneurysms. Only studies examining a consecutive case series of MCA aneurysms were included. We then extracted information regarding intraprocedural complications, procedural mortality and morbidity, immediate and long-term angiographic outcomes, and re-treatment rate. Analysis was done including 40 MCA aneurysms treated at our institution. Twelve studies including our institution's consecutive case series were included. Approximately 50% of the aneurysms presented as ruptured. Intraprocedural rupture rate in unruptured aneurysms was 1.7% (95% confidence interval [CI] = 0.7%-3.6%) compared with 4.8% (95% CI = 3.1%-7.4%) for ruptured aneurysms (P = .02). The risk of early postprocedural hemorrhage was 1.1% (95% CI = 0.5%-2.5%) for ruptured aneurysms. Overall procedure-related permanent morbidity and mortality were 5.1% and 6.0% for unruptured and ruptured aneurysms, respectively. The overall rate of complete or near-complete obliteration at angiographic follow-up was 82.4%. Endovascular treatment of MCA aneurysms is feasible and effective in selected cases. The combined periprocedural mortality and morbidity is not negligible (5.1%) and the overall rate of complete or near-complete angiographic obliteration at follow-up approaches 82%.
    Neurosurgery 11/2010; 68(2):397-402; discussion 402. DOI:10.1227/NEU.0b013e318201d7f4 · 3.03 Impact Factor