scholarly journals Insights in Hypothesis Testing and Making Decisions in Biomedical Research

2016 ◽  
Vol 10 (1) ◽  
pp. 196-200 ◽  
Author(s):  
Varin Sacha ◽  
Demosthenes B. Panagiotakos
Keyword(s):  
Confidence Interval ◽  
Hypothesis Testing ◽  
Confidence Intervals ◽  
Biomedical Research ◽  
Bootstrap Method ◽  
Resampling Methods ◽  
Effect Measure ◽  
Social Fields ◽  
The Bootstrap Method

It is a fact that p values are commonly used for inference in biomedical and other social fields of research. Unfortunately, the role of p value is very often misused and misinterpreted; that is why it has been recommended the use of resampling methods, like the bootstrap method, to calculate the confidence interval, which provides more robust results for inference than does p value. In this review a discussion is made about the use of p values through hypothesis testing and its alternatives using resampling methods to develop confidence intervals of the tested statistic or effect measure.

Application of the bootstrap method to quantify uncertainty in seismic hazard estimates

1992 ◽  
Vol 82 (1) ◽  
pp. 104-119
Author(s):  
Michéle Lamarre ◽  
Brent Townshend ◽  
Haresh C. Shah
Keyword(s):  
Confidence Interval ◽  
Seismic Hazard ◽  
Statistical Method ◽  
Bootstrap Method ◽  
Earthquake Magnitude ◽  
Earthquake Catalog ◽  
Uncertainty Measure ◽  
Attenuation Models ◽  
The Bootstrap Method

Abstract This paper describes a methodology to assess the uncertainty in seismic hazard estimates at particular sites. A variant of the bootstrap statistical method is used to combine the uncertainty due to earthquake catalog incompleteness, earthquake magnitude, and recurrence and attenuation models used. The uncertainty measure is provided in the form of a confidence interval. Comparisons of this method applied to various sites in California with previous studies are used to confirm the validity of the method.

Random Weighting Estimation of One-Sided Confidence Intervals in Discrete Distributions

2013 ◽  
pp. 92-102
Author(s):  
Yalin Jiao ◽  
Yongmin Zhong ◽  
Shesheng Gao ◽  
Bijan Shirinzadeh
Keyword(s):  
Confidence Intervals ◽  
Coverage Probability ◽  
Bootstrap Method ◽  
Experimental Results ◽  
Discrete Distributions ◽  
Estimation Accuracy ◽  
Weighting Method ◽  
Random Weighting Method ◽  
Random Weighting ◽  
The Bootstrap Method

This paper presents a new random weighting method for estimation of one-sided confidence intervals in discrete distributions. It establishes random weighting estimations for the Wald and Score intervals. Based on this, a theorem of coverage probability is rigorously proved by using the Edgeworth expansion for random weighting estimation of the Wald interval. Experimental results demonstrate that the proposed random weighting method can effectively estimate one-sided confidence intervals, and the estimation accuracy is much higher than that of the bootstrap method.

Computation of Exact Bootstrap Confidence Intervals: Complexity and Deterministic Algorithms

2020 ◽  
Vol 68 (3) ◽  
pp. 949-964
Author(s):  
Dimitris Bertsimas ◽  
Bradley Sturt
Keyword(s):  
Confidence Intervals ◽  
Bootstrap Method ◽  
Synthetic Data ◽  
Randomized Algorithm ◽  
Data Sets ◽  
Bootstrap Confidence Intervals ◽  
Integer Points ◽  
Deterministic Algorithms ◽  
New Perspective ◽  
The Bootstrap Method

The bootstrap method is one of the major developments in statistics in the 20th century for computing confidence intervals directly from data. However, the bootstrap method is traditionally approximated with a randomized algorithm, which can sometimes produce inaccurate confidence intervals. In “Computation of Exact Bootstrap Confidence Intervals: Complexity and Deterministic Algorithms,” Bertsimas and Sturt present a new perspective of the bootstrap method through the lens of counting integer points in a polyhedron. Through this perspective, the authors develop the first computational complexity results and efficient deterministic approximation algorithm (fully polynomial time approximation scheme) for bootstrap confidence intervals, which unlike traditional methods, has guaranteed bounds on its error. In experiments on real and synthetic data sets from clinical trials, the proposed deterministic algorithms quickly produce reliable confidence intervals, which are significantly more accurate than those from randomization.

Confidence Intervals for Weibull Fast-Fracture Parameters

2002 ◽  
Author(s):  
Mandar Chati ◽  
Curtis Johnson ◽  
Ahmet Kaya ◽  
Bjoern Schenk
Keyword(s):  
Confidence Interval ◽  
Confidence Intervals ◽  
Likelihood Ratio ◽  
Failure Modes ◽  
Bootstrap Method ◽  
Parametric Bootstrap ◽  
Nonparametric Bootstrap ◽  
Weibull Parameters ◽  
Fracture Data ◽  
Fast Fracture

Practical limits on number of specimens that can be tested lead to uncertainty in the estimated Weibull parameters. This paper presents an evaluation of four techniques for estimating confidence intervals for size-scaled Weibull parameters of monolithic ceramics. The techniques include normal approximation method, likelihood ratio technique, nonparametric bootstrap, and parametric bootstrap methods. For uncensored fast-fracture data, the confidence intervals for Weibull parameters are compared to the method used in ASTM Standard C1239. A simulation fracture experiment is conducted to evaluate the statistical characteristics, in particular coverage probability, of the four methods. For fast-fracture data with multiple failure modes, the statistical assessment of the confidence interval techniques for size-scaled Weibull parameters complement the existing literature. Overall, it was observed that the likelihood ratio technique and parametric bootstrap method perform very well. These techniques can also be extended for confidence interval estimation using fast-fracture data obtained from various geometry’s of test specimens and/or loading conditions (pooled data).

scholarly journals Beyond Psychology: Prevalence of p-value and confidence interval misinterpretation across different fields

2019 ◽  
Author(s):  
Xiaokang Lyu ◽  
Yuepei Xu ◽  
Xiaofan Zhao ◽  
Xi-Nian Zuo ◽  
Hu Chuan-Peng
Keyword(s):  
Confidence Interval ◽  
Confidence Intervals ◽  
Biomedical Research ◽  
Scientific Community ◽  
Scientific Literature ◽  
P Value ◽  
Raw Data ◽  
Research Fields ◽  
Research Gap ◽  
Two Indices

P-value and confidence intervals (CIs) are the most widely used statistical indices in scientific literature. Several surveys revealed that these two indices are generally misunderstood. However, existing surveys on this subject fall under psychology and biomedical research, and data from other disciplines are rare. Moreover, the confidence of researchers when constructing judgments remains unclear. To fill this research gap, we survey 1,479 researchers and students from different fields in China. Results reveal that for significant (p < .05, CI doesn’t include 0) and non-significant (p > .05, CI includes 0) conditions, most respondents, regardless of academic degrees, research fields, and stages of career, could not interpret p-value and CI accurately. Moreover, the majority of them are confident about their (inaccurate) judgments (see osf.io/mcu9q/ for raw data, materials, and supplementary analyses). Therefore, misinterpretations of p-value and CIs prevail in the whole scientific community, thus the need for statistical training in science.

scholarly journals The Cost of Capital for Investment in the Warsaw Stock Exchange Indexes – Versus Djia

2021 ◽  
Vol 21 (1) ◽  
pp. 122-143
Author(s):  
Stanisław Urbański
Keyword(s):  
Confidence Interval ◽  
Cost Of Capital ◽  
Stock Exchange ◽  
Bootstrap Method ◽  
Market Returns ◽  
Investment Projects ◽  
Warsaw Stock Exchange ◽  
The Cost ◽  
Stock Indexes ◽  
The Bootstrap Method

Abstract Research background and purpose: The CAPM, Fama-French and modified Fama-French models were used to estimate the cost of the capital of the DJIA and selected Polish stock indexes were used. The estimated cost of capital was the cost of the portfolio of corporate investment projects estimated by market returns. Research methodology: The model tests were run on 276 monthly returns of stocks listed on the markets in the years 1995–2019. The bootstrap method to estimate the confidence interval of the cost of capital was used. Results: The highest and positive cost of capital median was found for the DJIA index, about 0.85% monthly, and for the WIG20 and WIGDIV indexes, about 0.25% monthly. The cost of capital median for the mWIG80, WIGBANK and WIGCHEMIA indexes were found to be negative. This was due to large errors in the estimated cost of capital. Novelty: Minor errors in the estimation of the cost of capital of index DJIA may result from a more rational policy for the implementation of investment projects by companies included in the index.

scholarly journals Bootstrap Statistical Inference for the Variance Based on Fuzzy Data

2016 ◽  
Vol 38 (2) ◽  
Author(s):  
Mohammad Ghasem Akbari ◽  
Abdolhamid Rezaei
Keyword(s):  
Hypothesis Testing ◽  
Statistical Inference ◽  
Confidence Intervals ◽  
Nonparametric Estimation ◽  
Bootstrap Method ◽  
Estimation Problem ◽  
Fuzzy Data ◽  
Signed Distance ◽  
Straightforward Method ◽  
Statistical Hypotheses

The bootstrap is a simple and straightforward method for calculating approximated biases, standard deviations, confidence intervals, testing statistical hypotheses, and so forth, in almost any nonparametric estimation problem. In this paper we describe a bootstrap method for variance that is designed directly for hypothesis testing in case of fuzzy data based on Yao-Wu signed distance.

Sign in / Sign up

Export Citation Format

Share Document