In this review article, we revisit derivation of the cumulative density function (CDF) of the test statistic of the one-sample Kolmogorov-Smirnov test. Even though several such proofs already exist, they often leave o...In this review article, we revisit derivation of the cumulative density function (CDF) of the test statistic of the one-sample Kolmogorov-Smirnov test. Even though several such proofs already exist, they often leave out essential details necessary for proper understanding of the individual steps. Our goal is filling in these gaps, to make our presentation accessible to advanced undergraduates. We also propose a simple formula capable of approximating the exact distribution to a sufficient accuracy for any practical sample size.展开更多
In this article, we study the Kolmogorov-Smirnov type goodness-of-fit test for the inhomogeneous Poisson process with the unknown translation parameter as multidimensional parameter. The basic hypothesis and the alter...In this article, we study the Kolmogorov-Smirnov type goodness-of-fit test for the inhomogeneous Poisson process with the unknown translation parameter as multidimensional parameter. The basic hypothesis and the alternative are composite and carry to the intensity measure of inhomogeneous Poisson process and the intensity function is regular. For this model of shift parameter, we propose test which is asymptotically partially distribution free and consistent. We show that under null hypothesis the limit distribution of this statistic does not depend on unknown parameter.展开更多
This paper presents a framework that can be used to formalize the specification-based single-class test generation process. Object-Z is used to describe both software requirements and the proposed framework. Using thi...This paper presents a framework that can be used to formalize the specification-based single-class test generation process. Object-Z is used to describe both software requirements and the proposed framework. Using this framework, test engineers can automatically get the testing process model during the test generation process. With this model, properties of test cases （ such as relationship between test cases and methods can easily be captured. Furthermore, with the framework, the test process model can be updated automatically with the test generation process. The properties of test cases can then be updated correspondingly. It will greatly facilitate the regression testing. The main contribution of this paper is that it provides an approach to formalizing testing process by extending existing framework to class testing, and a way to represent test cases as multi-part, multi-step, multi-level artifacts.展开更多
With the redesigned jigs for the Thermecmastor-Z thermal simulator,the feasibility of using 3 kinds of Gleeble specimens in the Thermecmastor-Z simulator was investigated. Results show that Gleeble specimens can be us...With the redesigned jigs for the Thermecmastor-Z thermal simulator,the feasibility of using 3 kinds of Gleeble specimens in the Thermecmastor-Z simulator was investigated. Results show that Gleeble specimens can be used in the Thermecmastor-Z simulator. The tension tests in the Gleeble and Thermecmastor-Z simulators produced results with the same trend,which proves that the high temperature ductility of Gleeble specimens can be reflected by the Thermecmastor- Z simulator. In addition,as the Thermecmastor-Z simulator offers a wider heating zone,better cross-section shrinkage and elongation of specimens can be achieved under the same test conditions.展开更多
Objective: To improve the detecting accuracy of chromosomal aneuploidy of fetus by non-invasive prenatal testing (NIPT) using next generation sequencing data of pregnant women’s cell-free DNA. Methods: We proposed th...Objective: To improve the detecting accuracy of chromosomal aneuploidy of fetus by non-invasive prenatal testing (NIPT) using next generation sequencing data of pregnant women’s cell-free DNA. Methods: We proposed the multi-Z method which uses 21 z-scores for each autosomal chromosome to detect aneuploidy of the chromosome, while the conventional NIPT method uses only one z-score. To do this, mapped read numbers of a certain chromosome were normalized by those of the other 21 chromosomes. Average and standard deviation (SD), which are used for calculating z-score of each sample, were obtained with normalized values between all autosomal chromosomes of control samples. In this way, multiple z-scores can be calculated for 21 autosomal chromosomes except oneself. Results: Multi-Z method showed 100% sensitivity and specificity for 187 samples sequenced to 3 M reads while the conventional NIPT method showed 95.1% specificity. Similarly, for 216 samples sequenced to 1 M reads, Multi-Z method showed 100% sensitivity and 95.6% specificity and the conventional NIPT method showed a result of 75.1% specificity. Conclusion: Multi-Z method showed higher accuracy and robust results than the conventional method even at low coverage reads.展开更多
In this article we improve a goodness-of-fit test, of the Kolmogorov-Smirnov type, for equally distributed- but not stationary-strongly dependent data. The test is based on the asymptotic behavior of the empirical pro...In this article we improve a goodness-of-fit test, of the Kolmogorov-Smirnov type, for equally distributed- but not stationary-strongly dependent data. The test is based on the asymptotic behavior of the empirical process, which is much more complex than in the classical case. Applications to simulated data and discussion of the obtained results are provided. This is, to the best of our knowledge, the first result providing a general goodness of fit test for non-weakly dependent data.展开更多
文摘In this review article, we revisit derivation of the cumulative density function (CDF) of the test statistic of the one-sample Kolmogorov-Smirnov test. Even though several such proofs already exist, they often leave out essential details necessary for proper understanding of the individual steps. Our goal is filling in these gaps, to make our presentation accessible to advanced undergraduates. We also propose a simple formula capable of approximating the exact distribution to a sufficient accuracy for any practical sample size.
文摘In this article, we study the Kolmogorov-Smirnov type goodness-of-fit test for the inhomogeneous Poisson process with the unknown translation parameter as multidimensional parameter. The basic hypothesis and the alternative are composite and carry to the intensity measure of inhomogeneous Poisson process and the intensity function is regular. For this model of shift parameter, we propose test which is asymptotically partially distribution free and consistent. We show that under null hypothesis the limit distribution of this statistic does not depend on unknown parameter.
文摘This paper presents a framework that can be used to formalize the specification-based single-class test generation process. Object-Z is used to describe both software requirements and the proposed framework. Using this framework, test engineers can automatically get the testing process model during the test generation process. With this model, properties of test cases （ such as relationship between test cases and methods can easily be captured. Furthermore, with the framework, the test process model can be updated automatically with the test generation process. The properties of test cases can then be updated correspondingly. It will greatly facilitate the regression testing. The main contribution of this paper is that it provides an approach to formalizing testing process by extending existing framework to class testing, and a way to represent test cases as multi-part, multi-step, multi-level artifacts.
文摘With the redesigned jigs for the Thermecmastor-Z thermal simulator,the feasibility of using 3 kinds of Gleeble specimens in the Thermecmastor-Z simulator was investigated. Results show that Gleeble specimens can be used in the Thermecmastor-Z simulator. The tension tests in the Gleeble and Thermecmastor-Z simulators produced results with the same trend,which proves that the high temperature ductility of Gleeble specimens can be reflected by the Thermecmastor- Z simulator. In addition,as the Thermecmastor-Z simulator offers a wider heating zone,better cross-section shrinkage and elongation of specimens can be achieved under the same test conditions.
文摘Objective: To improve the detecting accuracy of chromosomal aneuploidy of fetus by non-invasive prenatal testing (NIPT) using next generation sequencing data of pregnant women’s cell-free DNA. Methods: We proposed the multi-Z method which uses 21 z-scores for each autosomal chromosome to detect aneuploidy of the chromosome, while the conventional NIPT method uses only one z-score. To do this, mapped read numbers of a certain chromosome were normalized by those of the other 21 chromosomes. Average and standard deviation (SD), which are used for calculating z-score of each sample, were obtained with normalized values between all autosomal chromosomes of control samples. In this way, multiple z-scores can be calculated for 21 autosomal chromosomes except oneself. Results: Multi-Z method showed 100% sensitivity and specificity for 187 samples sequenced to 3 M reads while the conventional NIPT method showed 95.1% specificity. Similarly, for 216 samples sequenced to 1 M reads, Multi-Z method showed 100% sensitivity and 95.6% specificity and the conventional NIPT method showed a result of 75.1% specificity. Conclusion: Multi-Z method showed higher accuracy and robust results than the conventional method even at low coverage reads.
文摘In this article we improve a goodness-of-fit test, of the Kolmogorov-Smirnov type, for equally distributed- but not stationary-strongly dependent data. The test is based on the asymptotic behavior of the empirical process, which is much more complex than in the classical case. Applications to simulated data and discussion of the obtained results are provided. This is, to the best of our knowledge, the first result providing a general goodness of fit test for non-weakly dependent data.
