Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 6

confidence interval Related Abstracts

6 Approximate Confidence Interval for Effect Size Base on Bootstrap Resampling Method

Authors: S. Phanyaem

Abstract:

This paper presents the confidence intervals for the effect size base on bootstrap resampling method. The meta-analytic confidence interval for effect size is proposed that are easy to compute. A Monte Carlo simulation study was conducted to compare the performance of the proposed confidence intervals with the existing confidence intervals. The best confidence interval method will have a coverage probability close to 0.95. Simulation results have shown that our proposed confidence intervals perform well in terms of coverage probability and expected length.

Keywords: Resampling, effect size, confidence interval, bootstrap method

Procedia PDF Downloads 474
5 On Coverage Probability of Confidence Intervals for the Normal Mean with Known Coefficient of Variation

Authors: Sa-aat Niwitpong, Suparat Niwitpong

Abstract:

Statistical inference of normal mean with known coefficient of variation has been investigated recently. This phenomenon occurs normally in environment and agriculture experiments when the scientist knows the coefficient of variation of their experiments. In this paper, we constructed new confidence intervals for the normal population mean with known coefficient of variation. We also derived analytic expressions for the coverage probability of each confidence interval. To confirm our theoretical results, Monte Carlo simulation will be used to assess the performance of these intervals based on their coverage probabilities.

Keywords: confidence interval, coverage probability, expected length, known coefficient of variation

Procedia PDF Downloads 235
4 Asymptotic Confidence Intervals for the Difference of Coefficients of Variation in Gamma Distributions

Authors: Sa-aat Niwitpong, Patarawan Sangnawakij

Abstract:

In this paper, we proposed two new confidence intervals for the difference of coefficients of variation, CIw and CIs, in two independent gamma distributions. These proposed confidence intervals using the close form method of variance estimation which was presented by Donner and Zou (2010) based on concept of Wald and Score confidence interval, respectively. Monte Carlo simulation study is used to evaluate the performance, coverage probability and expected length, of these confidence intervals. The results indicate that values of coverage probabilities of the new confidence interval based on Wald and Score are satisfied the nominal coverage and close to nominal level 0.95 in various situations, particularly, the former proposed confidence interval is better when sample sizes are small. Moreover, the expected lengths of the proposed confidence intervals are nearly difference when sample sizes are moderate to large. Therefore, in this study, the confidence interval for the difference of coefficients of variation which based on Wald is preferable than the other one confidence interval.

Keywords: coefficient of variation, confidence interval, simulation study, score’s interval, wald’s interval, gamma distribution

Procedia PDF Downloads 259
3 Using the Bootstrap for Problems Statistics

Authors: Brahim Boukabcha, Amar Rebbouh

Abstract:

The bootstrap method based on the idea of exploiting all the information provided by the initial sample, allows us to study the properties of estimators. In this article we will present a theoretical study on the different methods of bootstrapping and using the technique of re-sampling in statistics inference to calculate the standard error of means of an estimator and determining a confidence interval for an estimated parameter. We apply these methods tested in the regression models and Pareto model, giving the best approximations.

Keywords: Regression Models, bias, bootstrap, mean, confidence interval, Median, variance, error standard, jackknife

Procedia PDF Downloads 227
2 An Insite to the Probabilistic Assessment of Reserves in Conventional Reservoirs

Authors: Sai Sudarshan, Harsh Vyas, Riddhiman Sherlekar

Abstract:

The oil and gas industry has been unwilling to adopt stochastic definition of reserves. Nevertheless, Monte Carlo simulation methods have gained acceptance by engineers, geoscientists and other professionals who want to evaluate prospects or otherwise analyze problems that involve uncertainty. One of the common applications of Monte Carlo simulation is the estimation of recoverable hydrocarbon from a reservoir.Monte Carlo Simulation makes use of random samples of parameters or inputs to explore the behavior of a complex system or process. It finds application whenever one needs to make an estimate, forecast or decision where there is significant uncertainty. First, the project focuses on performing Monte-Carlo Simulation on a given data set using U. S Department of Energy’s MonteCarlo Software, which is a freeware e&p tool. Further, an algorithm for simulation has been developed for MATLAB and program performs simulation by prompting user for input distributions and parameters associated with each distribution (i.e. mean, st.dev, min., max., most likely, etc.). It also prompts user for desired probability for which reserves are to be calculated. The algorithm so developed and tested in MATLAB further finds implementation in Python where existing libraries on statistics and graph plotting have been imported to generate better outcome. With PyQt designer, codes for a simple graphical user interface have also been written. The graph so plotted is then validated with already available results from U.S DOE MonteCarlo Software.

Keywords: Simulation, Probability, Sensitivity Analysis, confidence interval

Procedia PDF Downloads 169
1 The Reproducibility and Repeatability of Modified Likelihood Ratio for Forensic Handwriting Examination

Authors: Adeyinka O. Abiodun, Adesesan B. Adeyemo

Abstract:

The forensic use of handwriting depends on the analysis, comparison, and evaluation decisions made by forensic document examiners. When using biometric technology in forensic applications, it is necessary to compute Likelihood Ratio (LR) for quantifying strength of evidence under two competing hypotheses, namely the prosecution and the defense hypotheses, wherein a set of assumptions and methods for a given data set will be made. It is, therefore, important to know how repeatable and reproducible our estimated LR is. This paper evaluated the accuracy and reproducibility of examiners' decisions. Confidence interval for the estimated LR was presented so as not get an incorrect estimate that will be used to deliver wrong judgment in the court of law. The estimate of LR is fundamentally a Bayesian concept, and we used two LR estimators, namely Logistic Regression (LoR) and Kernel Density Estimator (KDE), for this paper. The repeatability evaluation was carried out by retesting the initial experiment after an interval of six months to observe whether examiners would repeat their decisions for the estimated LR. The experimental results, which are based on handwriting dataset, show that LR does have different confidence interval, which therefore implies that LR cannot be estimated with the same certainty everywhere. Though the logistics regression (LoR) performed better than the kernel density estimator (KDE) when tested using the same dataset, the two LR estimators investigated showed a consistent region in which LR value can be estimated confidently. These two findings advance our understanding of LR when used in computing the strength of evidence in handwriting using forensics.

Keywords: Reproducibility, KDE, confidence interval, handwriting, repeatability, kernel density estimator, logistic regression LoR

Procedia PDF Downloads 1