Article
Multidisciplinary Sciences
Lorentz Jantschi
Summary: This paper discusses the challenge of mathematically evaluating the exact confidence interval for sampled outcomes, which follow a binomial distribution. It proposes three alternative methods for calculating confidence intervals and provides descriptions and examples for each.
Article
Multidisciplinary Sciences
Shu-Fei Wu
Summary: This paper presents interval estimation methods for the scale parameter of two-parameter exponential distribution, and proposes two methods for the joint confidence region. The optimal method of the confidence region is determined by simulation comparison based on confidence region area. The proposed methods are validated through a biometrical example.
Article
Engineering, Industrial
Zahra Saberzadeh, Mostafa Razmkhah
Summary: The reliability of complex systems consisting of n independent elements, each with two dependent components, is investigated based on degradation data. A copula-based model is used to describe the dependence structure of the components. The reliability of a complex system is derived for different copula functions, considering gamma, Wiener, and inverse Gaussian processes for the degradation of each component. Reliability bounds are obtained by assuming positive association of components for special cases of series and parallel systems. A two-step method is proposed for estimating maximum likelihood estimators when model parameters are unknown. The performance of the estimators is evaluated through a simulation study, and the sensitivity of system reliability is analyzed using simulation. The results of the paper are illustrated using two real examples.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Pharmacology & Pharmacy
Kaifeng Lu, Hua Guo
Summary: This passage explores the application of multiple imputation techniques in parameter estimation, comparing the MN method with the LMB method. Through simulation studies, it is found that the proposed method produces slightly shorter confidence intervals compared to the LMB method, while also being evaluable for all datasets.
PHARMACEUTICAL STATISTICS
(2022)
Article
Mathematics
Felix Almendra-Arao, Hortensia Reyes-Cervantes, Marcos Morales-Cortes
Summary: Confidence intervals are important tools for estimating binomial proportions in statistics, with the most well-known being the Wald and Clopper-Pearson intervals. However, these intervals are known to have shortcomings in terms of coverage probability and expected mean length, leading to the proposal of alternative intervals. In this study, we investigate the performance of several of these confidence intervals using a parametric family to estimate the parameter p. Instead of using the confidence intervals approach, our analysis is done through hypothesis tests. Our main goal is to identify values of c that yield better-performing tests and establish an optimal procedure.
Article
Mathematics
Lorentz Jantschi
Summary: Medical studies often compare two outcomes from samples, with the importance placed on the probability and confidence in the findings. Current guidelines recommend reporting both relative and absolute measures of association, but the exact confidence interval for these measures poses a mathematical challenge due to the discrete distribution. In order to address this issue, algorithms implementing a strategy for providing exact p-values and confidence intervals have been proposed.
Article
Statistics & Probability
Angkana Kokaew, Winai Bodhisuwan, Su-Fen Yang, Andrei Volodin
Summary: This article investigates the logarithmic interval estimation of a ratio of two binomial proportions in dependent samples. The study finds that closed-form solutions to confidence intervals for the difference and ratio of correlated proportions are typically not available and the computation process is complex. Through a Monte Carlo simulation, we demonstrate the reliability of using a normal approximation for the estimation of the ratio and provide recommendations for the asymptotic logarithmic interval.
JOURNAL OF APPLIED STATISTICS
(2023)
Article
Mathematical & Computational Biology
Lonnie Turpin, Jeanne-Claire Patin, William Jens, Morgan Turpin
Summary: This study develops two functions (one for each level) that provide approximations of the exact lower-bound L within a/a3 when considering the one-sided binomial confidence interval (L , 1) containing the unknown parameter p. The exponential and logarithmic functions are found to outperform the standard rule of three L ? 1- 3/n over their respective ranges, covering all sample sizes n = 1. Specifically, the exponential function with exp(-3/n) is a better lower bound when a = 0.05 and n < 1054, while exp(-4.6569/n) is a better bound when a = 0.01 and n < 209.
INTERNATIONAL JOURNAL OF BIOSTATISTICS
(2023)
Article
Multidisciplinary Sciences
Wasana Chankham, Sa-Aat Niwitpong, Suparat Niwitpong
Summary: This study proposed confidence intervals for the coefficient of variation (CV) of an inverse Gaussian (IG) distribution to calculate PM2.5 concentrations. The performance of these intervals was evaluated through simulation experiments and it was found that the fiducial confidence interval (FCI) performed the best, especially for small sample sizes.
Article
Engineering, Industrial
Piao Chen, Kilian Buis, Xiujie Zhao
Summary: This paper develops a comprehensive R package for handling the gamma distribution, covering the state-of-the-art methods of this distribution. The package allows for generating gamma random variables, estimating model parameters, and constructing statistical limits, facilitating practical applications.
JOURNAL OF QUALITY TECHNOLOGY
(2023)
Article
Pharmacology & Pharmacy
Hassan Lakkis, Andrew Lakkis
Summary: In this article, the authors propose an approximate exact score (AES) test for noninferiority comparisons and derive its test-based confidence interval for the difference between two independent binomial proportions. The AES method has important advantages over popular asymptotic methods for noninferiority comparisons, especially when the sample sizes of the compared groups are unbalanced. The empirical comparisons show that the AES method has a true type I error rate closer to the nominal level than other methods.
PHARMACEUTICAL STATISTICS
(2023)
Article
Pharmacology & Pharmacy
Carl Peck, Gregory Campbell, Isaac Yoo, Kairui Feng, Meng Hu, Liang Zhao
Summary: In this study, the performance of TOST and BEST methods in evaluating bioequivalence was compared using simulated datasets. The results showed that there was no significant difference between the two methods when the data followed a lognormal distribution. However, when the data followed a normal distribution or included extreme values, the BEST method was more accurate and required fewer subjects.
Article
Engineering, Multidisciplinary
Xiaofei Wang, Bing Xing Wang, Xin Pan, Yunkai Hu, Yingpei Chen, Junxing Zhou
Summary: This paper discusses interval estimation for the inverse Gaussian distribution, deriving generalized confidence intervals and prediction intervals. Through simulation, it is shown that the proposed intervals have higher coverage probabilities compared to traditional methods like Wald CIs and bootstrap-p CIs. Additionally, the proposed procedures are illustrated using two examples.
QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL
(2021)
Article
Mathematics
Jose Antonio Roldan-Nofuentes, Saad Bouh Regad
Summary: This manuscript focuses on comparing the positive (negative) predictive values of two binary diagnostic tests through confidence intervals in a paired design. Simulation experiments have been conducted to study the behavior of the confidence intervals asymptotically, providing general rules for application. The manuscript also discusses a method for calculating sample size for comparing parameters using confidence intervals, with results applied to the diagnosis of colorectal cancer.
Article
Mathematical & Computational Biology
Yongqiang Tang
Summary: In this study, new methods have been proposed for evaluating treatment effects and inferring parameter confidence intervals in survival trials, with excellent performance.
STATISTICS IN MEDICINE
(2021)