Robust Confidence Intervals for the Bernoulli Parameter

Song, Wheyming Tina; Chang, Chia‐Jung; Liu, Sin-Long

doi:10.1080/03610920802602958

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) p o = n pos n pos + n neg which gives an upper and lower limit in which p lies, given p o and the number n of tests performed. Out of various confidence estimations for the Bernoulli process, we have chosen a 95% Wilson interval (Wilson 1927), which provides particularly robust confidence intervals for a small number of trials (Song et al 2009). Wilson intervals were calculated using the statsmodels module in Python (Seabold and Perktold 2010).…”

Section: Discussionmentioning

confidence: 99%

“…Statistically, this represents a Bernoulli process with only two outcomes (1) or (0). This discreteness of results makes the analysis of any Bernoulli process deceptively tricky (Song et al 2009 ). We assume the true contamination rate of chips p depends only on the geometry of the tested chips by keeping all the background variables constant.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Self-sealing MEMS spray-nozzles to prevent bacterial contamination of portable inhalers for aqueous drug delivery

Last

Winkler

Stemme

et al. 2022

Biomed Microdevices

View full text Add to dashboard Cite

Pulmonary drug delivery by portable inhalers is the gold standard in lung disease therapy. An increasing focus on environmentally friendly inhalation currently spurs the development of propellant-free devices. However, the absence of propellants in the drug creates a need for suitable sealing systems that can ensure the pathogenic safety of devices. Traditionally, liquid drug inhalers incorporate a spray nozzle and a separate check valve. Here we show a fully integrated MEMS-based spray system for aqueous drug solutions and demonstrate its bacterial safety. The device comprises a thin silicon membrane with spray orifices, which self-seal against a compliant parylene valve seat underneath. This sealing system prevents bacterial ingrowth in its default closed state, while actuation lifts the membrane from the valve seat upon pressurization and sprays an inhalable aerosol from the nozzles. To seal against bacterial contamination effectively, we found that a contact force between the valve seat and the membrane (featuring the spray nozzles) is needed. In our testing, both self-sealing and an otherwise identical unvalved version of the spray chip can be bacterially safe in continued use when thoroughly cleaned of excess fluids and subjected to low bacterial loads for brief periods. However, when directly exposed to $$10^{7}$$ 10 7 CFU/ml of our test organism Citrobacter rodentium for 24 h, unvalved systems become contaminated in nearly 90% of cases. In contrast, self-sealing spray chips reduced contamination probability by 70%. This development may enable preservative-free drug formulations in portable inhalers that use propellant-free aqueous drug solutions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Self-sealing MEMS spray-nozzles to prevent bacterial contamination of portable inhalers for aqueous drug delivery

Last

Winkler

Stemme

et al. 2022

Biomed Microdevices

View full text Add to dashboard Cite

show abstract

“…We can consider the outcome of each trial as a Bernoulli random variable with parameter x (the probability of a subject selecting the label given by a human). For a given excerpt for which the human label is selected h times by N independent subjects, we can estimate the Bernoulli parameter x using the minimum mean-squared error estimator, assuming x is distributed uniform in [0, 1]:x(h) = (h + 1)/(N + 2) (Song et al 2009). The variance of this estimate is given bŷ…”

Section: Artistmentioning

confidence: 99%

Classification accuracy is not enough

Sturm

2013

J Intell Inf Syst

View full text Add to dashboard Cite

We argue that an evaluation of system behavior at the level of the music is required to usefully address the fundamental problems of music genre recognition (MGR), and indeed other tasks of music information retrieval, such as autotagging. A recent review of works in MGR since 1995 shows that most (82 %) measure the capacity of a system to recognize genre by its classification accuracy. After reviewing evaluation in MGR, we show that neither classification accuracy, nor recall and precision, nor confusion tables, necessarily reflect the capacity of a system to recognize genre in musical signals. Hence, such figures of merit cannot be used to reliably rank, promote or discount the genre recognition performance of MGR systems if genre recognition (rather than identification by irrelevant confounding factors) is the objective. This motivates the development of a richer experimental toolbox for evaluating any system designed to intelligently extract information from music signals.

show abstract

Binomial and Poisson Confidence Intervals and Its Variants: A Bibliography

Khurshid¹

2010

Pak.j.stat.oper.res.

View full text Add to dashboard Cite

show abstract

Robust Confidence Intervals for the Bernoulli Parameter

Cited by 3 publications

References 7 publications

Self-sealing MEMS spray-nozzles to prevent bacterial contamination of portable inhalers for aqueous drug delivery

Self-sealing MEMS spray-nozzles to prevent bacterial contamination of portable inhalers for aqueous drug delivery

Classification accuracy is not enough

Binomial and Poisson Confidence Intervals and Its Variants: A Bibliography

Contact Info

Product

Resources

About