• Communications for Statistical Applications and Methods
• /
• 제31권5호
• /
• pp.497-519
• /
• 2024

In reliability analysis, the probability P(Y < X) is significant because it denotes availability and dependability in a stress-strength model where Y and X are the stress and strength variables, respectively. In reliability theory, the inverse Lomax distribution is a well-established lifetime model, and the literature is developing inference techniques for its reliability attributes. In this article, we are interested in estimating the stress-strength reliability R = P(Y < X), where X and Y have an unknown common scale parameter and follow the inverse Lomax distribution. Using Bayesian and non-Bayesian approaches, we discuss this issue when both stress and strength are expressed in terms of lower record values. The parametric bootstrapping techniques of R are taken into consideration. The stress-strength reliability estimator is investigated using uniform and gamma priors with several loss functions. Based on the proposed loss functions, the reliability R is estimated using Bayesian analyses with Gibbs and Metropolis-Hasting samplers. Monte Carlo simulation studies and real-data-based examples are also performed to analyze the behavior of the proposed estimators. We analyze electrical insulating fluids, particularly those used in transformers, for data sets using the stress-strength model. In conclusion, as expected, the study's results showed that the mean squared error values decreased as the record number increased. In most cases, Bayesian estimates under the precautionary loss function are more suitable in terms of simulation conclusions than other specified loss functions.

• Asian Journal of Business Environment
• /
• 제12권3호
• /
• pp.1-12
• /
• 2022

Purpose: This study aims to investigate whether AIS data can be used as a supporting indicator or as an initial signal to describe Indonesia's export-import conditions in real-time. Research design, data, and methodology: This study performs several stages of data selection to obtain indicators from AIS that truly reflect export-import activities in Indonesia. Also, investigate the potential of AIS indicators in producing forecasts of the value and volume of Indonesian export-import using conventional statistical methods and machine learning techniques. Results: The six preprocessing stages defined in this study filtered AIS data from 661.8 million messages to 73.5 million messages. Seven predictors were formed from the selected AIS data. The AIS indicator can be used to provide an initial signal about Indonesia's import-export activities. Each export or import activity has its own predictor. Conventional statistical methods and machine learning techniques have the same ability both in forecasting Indonesia's exports and imports. Conclusions: Big data AIS can be used as a supporting indicator as a signal of the condition of export-import values in Indonesia. The right method of building indicators can make the data valuable for the performance of the forecasting model.

• Korean Journal of Acupuncture
• /
• 제29권4호
• /
• pp.573-580
• /
• 2012

Objectives : This study was to investigate statistical validities and trends of previously reported papers that used various statistical techniques such as t-test and analysis of variance. Methods : To analyze the statistical procedures, 54 original articles using those statistical methods were selected from The Korean Journal of Acupuncture published from 2007 to 2011. Results : T-test and analysis of variance were used in 23(25.27%), and 18 papers(19.78%) out of 54 papers, respectively. Seven articles(12.96%) did not report alpha values and 26(48.15%) out of 54 studies were not tested for normal distribution. One paper(1.85%) misused t-test and 7 papers(38.89%) did not carry out the multiple comparison. Conclusions : To improve the quality of KJA, statistician involvement in research design would be necessary to reduce errors in statistical methods and interpretation of the results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1348-1375
• /
• 2018

Support Vector Machine (SVM) is a well-known machine learning classification algorithm, which has been widely applied to many data mining problems, with good accuracy. However, SVM classification speed decreases with increase in dataset size. Some applications, like video surveillance and intrusion detection, requires a classifier to be trained very quickly, and on large datasets. Hence, this paper introduces two filter-based instance selection techniques for optimizing SVM training speed. Fast classification is often achieved at the expense of classification accuracy, and some applications, such as phishing and spam email classifiers, are very sensitive to slight drop in classification accuracy. Hence, this paper also introduces two wrapper-based instance selection techniques for improving SVM predictive accuracy and training speed. The wrapper and filter based techniques are inspired by Cuckoo Search Algorithm and Bat Algorithm. The proposed techniques are validated on three popular e-fraud types: credit card fraud, spam email and phishing email. In addition, the proposed techniques are validated on 20 other datasets provided by UCI data repository. Moreover, statistical analysis is performed and experimental results reveals that the filter-based and wrapper-based techniques significantly improved SVM classification speed. Also, results reveal that the wrapper-based techniques improved SVM predictive accuracy in most cases.

• 한국한의학연구원논문집
• /
• 제18권3호
• /
• pp.127-132
• /
• 2012

Background and Purpose : This study was to investigate statistical validities and trends of previously reported papers that used various statistical techniques such as t-test and analysis of variance. Methods : To analyze the statistical procedures, 38 original articles using those statistical methods were selected from Journal of Korea Institute of Oriental Medicine(JKIOM) published from 2010 to 2012. Results : Analysis of variance and t-test were used in 20 papers (38.5%), 16 papers (30.8%) of 52 papers. Four articles(10.5%) did not report ${\alpha}$ values and nineteen papers(50.0%) of 38 ones were not tested for normal distribution. Five papers (13.2%) misused t-test and 3 papers (7.9%) did not carry out the multiple comparison. Conclusions : To improve the quality of JKIOM, The participation of statisticians in research design will reduce the significant errors in statistical interpretation of the results.

• 한국한의학연구원논문집
• /
• 제14권2호
• /
• pp.87-91
• /
• 2008

Background and Purpose: The purpose of this study was investigate statistical validities of previously reported articles that used various statistical techniques such as t-test and analysis of variance. Methods: To analyze the statistical procedures, 66 original articles using those statistical methods were selected from "Korean Journal of Oriental Medicine(KJOM)" published from 1995 to 2007. Results: Twenty-one articles(32%) did not report correct p-values, 33 articles(50%) used mean${\pm}$standard error(mean${\pm}$SE) and 11 articles(l7%) used mean${\pm}$standard deviation(mean${\pm}$SD). Fifty-two articles(95%) of 55 ones which were tested for normal distribution made an error in describing normal distribution. Seventeen articles misused t-test and 12 articles did not carry out the multiple comparison. Conclusions: The training of researchers with clinical statistics or the participation of statisticians in research design will reduce the significant errors in statistical interpretation of the results.

• 대한수의학회지
• /
• 제39권6호
• /
• pp.1187-1196
• /
• 1999

The purpose of this study is to assess the suitability of the statistical techniques employed in papers published in the Korean Journal of Veterinary Research from March 1997 to March 1999 and it is hoped that the critical assessment may be of help to other researchers preparing their works for publication. Of the 246 original papers 94 were included in the analysis. Of 62 papers with the measure of central location and dispersion of data 34 (54.8%) used them correctly : 9 (39.1%) of 23 for t-test ; 1 (33.3%) of 3 for correlation analysis ; 7 (43.8%) of 16 for analysis of variance (ANOVA) ; 5 (62.5%) of 8 for chi-square test ; 44 (71%) of 62 for description of p-value. A number of papers employed ANOVA did not perform subsequent analysis of multiple comparison. Compared to the results of others, relatively higher proportion of papers in the present study was evaluated as appropriate analysis. The reason is that papers described insufficiently on the study design were not included, and evaluation items were restricted to the cases violated seriously inherent assumptions for each statistical technique. Statistical misuse or abuse appeared in the study is due to lack of knowledge on statistics and short of its importance for improvement the quality of paper. Because an inappropriate analysis can lead the readers to misunderstand on findings, observed statistical analyses must be valid, and correctly undertaken. It is suggested that more intensive statistical refereeing are needed, and the communication should be allowed for the controversial points.

• 한국통신학회논문지
• /
• 제11권1호
• /
• pp.73-84
• /
• 1986

화상이해의 기본적인 특성중의 하나인 edge를 추정하는 statistical 한 방법을 제안하였다. 종래의 edge검출기법은 주로 deterministic한 신호에는 잘 적용되었지만 statistical한 신호에는 만족스러운 결과를 얻을 수 없었다. 본 논문에서는 신호의 statistical 한 성질을 고려한 likelihood함수를 이용하여 결정함수를 구하고, 이것을 최대로 하는 위치를 edge로 선정하는 maximum likelihood edge 검출기법에 대하여 논하였다. 이 기법을 random number generator에 의하여 발생된 통계적인 성질을 갖는 신호에 적용하여 edge가 잘 검출됨을 보였다. 또 이 방법을 통계적인 성질을 갖는 이차원의 화상으로 확장하였을 때에도 정확하게 edge가 검출됨을 알 수 있었다.

• 사상체질의학회지
• /
• 제22권4호
• /
• pp.49-55
• /
• 2010

1. Objectives The purpose of this study is to assess the statistical methods used in the Journal of Sasang Constitutional Medicine and to identify the types of errors in the statistical analysis. 2. Methods We have reviewed quantitative articles published in the Journal of Sasang Constitutional Medicine from 2000 to 2009. Except for the case report, a total of 505 articles was reviewed by year. We focused on the methods of statistics in these articles. We have analysed the number of thesis used the statistical methods, the number of the statistical methods, the types of the statistical methods, and the errors of the statistical methods with the object of 202 thesis used the statistical method. 3. Results 1. Of the 370 articles, 202 used inferential statistics. 2. The most dominant was the thesis with one type of the statistical method forming 61.9% (125 thesis) of the total. 3. The ANOVA was the statistic of choice overall (40.1%), followed by the t-test (35.6%). 4. By examining the errors of the statistical methods, there were 49 thesis with errors among 81 thesis using ANOVA, 25 thesis among 72 thesis using t-test, and 18 over 62 thesis using chi-squared test. 4. Conclusions We have found various mistakes or misuses in the applications of statistical methodologies in the articles published in the Journal of Sasang Constitutional Medicine. It is necessary to present the cases of inappropriate statistical methods in order to improve the quality of academic researches. So long as Sasang constitutional medicine uses the statistical methods, researchers should fully examine and be aware of the statistical methods which they wish to use through other research articles, and statistic publications.

• Communications for Statistical Applications and Methods
• /
• 제19권3호
• /
• pp.303-313
• /
• 2012

By using the techniques of a Malliavin calculus, we study the asymptotic behavior of the weighted cross-variation of a fractional Brownian sheet with a Hurst parameter $H=(H_1,H_2)$ such that 0 < $H_1$ < 1/2 and 0 < $H_1$ < 1/2.