A comparative study of the reliability of nine statistical software packages

The reliabilities of nine software packages commonly used in performing statistical analysis are assessed and compared. The (American) National Institute of Standards and Technology (NIST) data sets are used to evaluate the performance of these software packages with regard to univariate summary statistics, one-way ANOVA, linear regression, and nonlinear regression. Previous research has examined various versions of these software packages using the NIST data sets, but typically with fewer software packages than used in this study. This study provides insight into a relative comparison of a wide variety of software packages including two free statistical software packages, basic and advanced statistical software packages, and the popular Excel package. Substantive improvements from previous software reliability assessments are noted. Plots of principal components of a measure of the correct number of significant digits reveal how these packages tend to cluster for ANOVA and nonlinear regression.     

Logical operators of some statistical computing packages and missing values

When using statistical computer packages in general, we rely on the results they produce. We are aware that numerical approximations are made and trust that the best algorithms are chosen to do them. Most manuals give us instructions about precision of calculations and some report how missing values are administered. What we are unaware of is that some packages can invent results when creating atomic formulas and compounding complex formulas out of atomic ones, what inflates sample sizes, and possibly leads us to incorrect statistical decisions. Two simple indicator variables, with missing values positioned so the results are always missing values, were tested as numerical, as logical and as character variables, by compounding them through connective ‘and’ (&) and ‘or’ (|) to form new indicator variables. The results show that one of the three very known packages does not, statistically, correctly handle missing values, and the three make atomic formulas out of character variables assigning the value false (0) for missing value, what can be said an statistical error. The conclusion is that statisticians and users of statistics must be aware of the capabilities of logically operating missing values of the statistical packages they use, otherwise wrong statistical decisions can be made. And that programmers of statistical packages should correct their algorithms in order to not permit their packages invent non-existing values.     

Swat: A system for detecting salient Wikipedia entities in texts

We study the problem of entity salience by proposing the design and implementation of Swat , a system that identifies the salient Wikipedia entities occurring in an input document. Swat consists of several modules that are able to detect and classify on‐the‐fly Wikipedia entities as salient or not, based on a large number of syntactic, semantic, and latent features properly extracted via a supervised process, which has been trained over millions of examples drawn from the New York Times corpus. The validation process is performed through a large experimental assessment, eventually showing that Swat improves known solutions over all publicly available datasets. We release Swat via an API that we describe and comment in the paper to ease its use in other software.     

一种针对可信计算平台的分布式可信验证机制

可信计算技术在提高系统安全性的同时,也给用户使用计算机带来了诸多限制。为了解决自由软件等未授权程序的可信验证问题,提出了一种基于可信计算的分布式可信验证机制（DTVMTC）。该机制以庞大的Internet用户群为基础,通过网络数据统计的方法,实现对应用程序的可信验证,从而解决了对无可信来源但实际可信的应用程序进行可信验证的问题,保障了用户使用可信计算平台的自由。在Windows平台实现了DTVMTC的原型,实验结果表明DTVMTC能够实现预定目标且具有良好的性能。     

Evaluation of statistical packages for suitability for use by clinical investigators in medicine

With the increased availability of personal computers and statistical software packages, it is inevitable that there will be increasing attempts by clinical investigators to perform data management and statistical analysis. Reviews of statistical packages are abundant in computer and statistical journals. However the majority of them were not written for clinical investigators in medicine. This paper presents an analytic approach to evaluate the suitability of statistical packages for use by clinical investigators for data-management and preliminary statistical-analysis purposes. The evaluation scheme addresses five areas of concern: availability of data-management features; availability of basic statistical-analysis features; ease of use; documentation; and quality of programs. Among six statistical packages reviewed by this process, CRISP is recommended as the most suitable package for clinical investigators to use for data-management and preliminary statistical-analysis purposes.     

Early estimation of software size in object-oriented environments a case study in a CMM level 3 software firm

Early estimation of the size of a software product is extremely important. In this paper we analyze two software packages developed by a CMM level 3 software firm. We study if any property of analysis objects can be used to infer the size of the final code in an object-oriented environment. In both cases we find the number of methods well correlated with software size, in the sense that the correlation with the final size is high (r > 0.77) and significant at the level 0.05. Inferential statistics guarantee that the results of this study are also applicable outside the scope of the two projects.     

A decision rules approach for improvement of airport service quality

The passenger’s perception of the airport’s level of service (LOS) may have a significant impact on promoting or discouraging future tourism and business activities. In this study, we take a look at this problem, but unlike in traditional statistical analysis, we apply a new method, the dominance-based rough set approach (DRSA), to an airport service survey. A set of “if … then … ” decision rules is used in the preference model. The passengers indicate their perception of airport LOS by rating a set of criteria/attributes. The proposed method provides practical information that should be of help to airport planners, designers, operators, and managers to develop LOS improvement strategies. The model was implemented using survey data from a large sample of customers from an international airport in Taiwan.     

Software quality analysis by combining multiple projects and learners

When building software quality models, the approach often consists of training data mining learners on a single fit dataset. Typically, this fit dataset contains software metrics collected during a past release of the software project that we want to predict the quality of. In order to improve the predictive accuracy of such quality models, it is common practice to combine the predictive results of multiple learners to take advantage of their respective biases. Although multi-learner classifiers have been proven to be successful in some cases, the improvement is not always significant because the information in the fit dataset sometimes can be insufficient. We present an innovative method to build software quality models using majority voting to combine the predictions of multiple learners induced on multiple training datasets. To our knowledge, no previous study in software quality has attempted to take advantage of multiple software project data repositories which are generally spread across the organization. In a large scale empirical study involving seven real-world datasets and seventeen learners, we show that, on average, combining the predictions of one learner trained on multiple datasets significantly improves the predictive performance compared to one learner induced on a single fit dataset. We also demonstrate empirically that combining multiple learners trained on a single training dataset does not significantly improve the average predictive accuracy compared to the use of a single learner induced on a single fit dataset.

The reasons why people continue editing Wikipedia content – task value confirmation perspective

Recently, Wikipedia has garnered increasing public attention. However, few studies have examined the intentions of individuals who edit Wikipedia content. Furthermore, previous studies ascribed a ‘knowledge sharing’ label to Wikipedia content editors. However, in this work, Wikipedia can be viewed as a platform that allows individuals to show their expertise. This study investigates the underlying reasons that drive individuals to edit Wikipedia content. Based on expectation-confirmation theory and expectancy-value theory for achievement motivations, we propose an integrated model that incorporates psychological and contextual perspectives. Wikipedians from the English-language Wikipedia site were invited to survey. Partial least square was applied to test our proposed model. Analytical results indicated and confirmed that subjective task value, commitment, and procedural justice were significant to satisfaction of Wikipedians; and satisfaction significantly influenced continuance intention to edit Wikipedia content.     

Presenting software engineering results using structured abstracts: a randomised experiment

When conducting a systematic literature review, researchers usually determine the relevance of primary studies on the basis of the title and abstract. However, experience indicates that the abstracts for many software engineering papers are of too poor a quality to be used for this purpose. A solution adopted in other domains is to employ structured abstracts to improve the quality of information provided. This study consists of a formal experiment to investigate whether structured abstracts are more complete and easier to understand than non-structured abstracts for papers that describe software engineering experiments. We constructed structured versions of the abstracts for a random selection of 25 papers describing software engineering experiments. The 64 participants were each presented with one abstract in its original unstructured form and one in a structured form, and for each one were asked to assess its clarity (measured on a scale of 1 to 10) and completeness (measured with a questionnaire that used 18 items). Based on a regression analysis that adjusted for participant, abstract, type of abstract seen first, knowledge of structured abstracts, software engineering role, and preference for conventional or structured abstracts, the use of structured abstracts increased the completeness score by 6.65 (SE 0.37, p < 0.001) and the clarity score by 2.98 (SE 0.23, p < 0.001). 57 participants reported their preferences regarding structured abstracts: 13 (23%) had no preference; 40 (70%) preferred structured abstracts; four preferred conventional abstracts. Many conventional software engineering abstracts omit important information. Our study is consistent with studies from other disciplines and confirms that structured abstracts can improve both information content and readability. Although care must be taken to develop appropriate structures for different types of article, we recommend that Software Engineering journals and conferences adopt structured abstracts.

Statgraphics : Neil W. Polhemus and the Statistical Graphics Corporation. Rockville, MD: STSC. Release No. 2.0, $795.00

Several statistical software packages are now commercially available for microcomputers. The quality and usability of these software packages vary dramatically. The purpose of this paper is to review the package STATGRAPHICS utilizing the statistical software model developed by Ansorge, Wise, and Plake (1985). The paper will address quality and usability dimensions of STATGRAPHICS from the vantage point and needs of an educational researcher.     

New Products

In this issue, editors Keith Farkas and Guerney Hunt look at several software packages that could enable ubiquitous system software, present a reader-submitted review of the OQO pocket computer, and examine a promising display and a device that connects the various telephone technologies.     

On the power transformation of kernel-based tests for serial correlation in vector time series: Some finite sample results and a comparison with the bootstrap

Portmanteau test statistics represent useful diagnostic tools for checking the adequacy of multivariate time series models. For stationary and partially non-stationary vector time series models, Duchesne and Roy [Duchesne, P., Roy, R., 2004. On consistent testing for serial correlation of unknown form in vector time series models. Journal of Multivariate Analysis 89, 148-180] and Duchesne [Duchesne, P., 2005a. Testing for serial correlation of unknown form in cointegrated time series models. Annals of the Institute of Statistical Mathematics 57, 575-595] have proposed kernel-based test statistics, obtained by comparing the spectral density of the errors under the null hypothesis of non-correlation with a kernel-based spectral density estimator; these test statistics are asymptotically standard normal under the null hypothesis of non-correlation in the error term of the model. Following the method of Chen and Deo [Chen, W.W., Deo, R.S., 2004a. Power transformations to induce normality and their applications. Journal of the Royal Statistical Society, Ser. B 66, 117-130], we determine an appropriate power transformation to improve the normal approximation in small samples. Additional corrections for the mean and variance of the distance measures intervening in these test statistics are obtained. An alternative procedure to estimate the finite distribution of the test statistics is to use the bootstrap method; we introduce bootstrap-based versions of the original spectral test statistics. In a Monte Carlo study, comparisons are made under various alternatives between: the original spectral test statistics, the new corrected test statistics, the bootstrap-based versions, and finally the classical Hosking portmanteau test statistic.     

Application Briefs

When one sensory input, hearing, is blocked altogether or reduced to some degree, a greater load of communications is placed on vision. Not surprisingly, the deaf and hearingimpaired have long relied on two visual substitutes for speech: lip reading and sign language. To make these skills easier to learn, two contestants in the Johns Hopkins University Search for Applications of Personal Computing to Aid the Handicapped have devised ways of simulating lip positions and hand signs on a display. In both cases the main intent of the software packages is to train not only the deaf and hearing-impaired, but also those who want to communicate with them.     

The Contemporary Software Security Landscape

Microsoft's release of Windows Vista marks the arrival of a new era for software security. Fundamental changes have gradually occurred, bringing us to a point now where the threat landscape no longer resembles what it was just a few years ago. Vista's release is ideal to consider as a culmination point; it's from here that software attack strategies will move into new directions. In this article, the author examines some of these new directions, as well as some of the changes related to Vista that most encapsulate the current threat landscape for software security. Eight characterirstics most strongly define the new software security threat landscape. Let's take a look at them: actualization of Web vulnerability threats; advances in code analysis; more advanced techniques; client-side vulnerabilities; remote exploitation; targeted attacks; sale of vulnerability information; and anti-exploitation technology.     

利用SAR图像识别海面油膜的方法介绍

利用SAR图像可以有效地识别海上油膜。通过对南海及渤海地区的80多景ASAR数据进行暗区域分析,利用海面烃类油膜雷达遥感图像监测系统(System for Oil Spill Detection 1.0,简称SOSD 1.0)提取出油膜及低风速区等暗目标的特征参数,包括油膜的后向散射系数、均一度、梯度值、面积、复杂度等。通过对这些参数进行统计分析并结合人工解译,找出规律,形成根据这些规律以及其它的经验知识来区分油膜及非油膜的过程,并结合实例进行说明。     

A user-friendly tool for comprehensive evaluation of the geographical origins of atmospheric pollution: Wind and trajectory analyses

Various receptor methodologies have been developed in the last decades to investigate the geographical origins of atmospheric pollution, based either on wind data or on backtrajectory analyses. To date, only few software packages exist to make use of one or the other approach. We present here ZeFir, an Igor-based package specifically designed to achieve a comprehensive geographical origin analysis using a single statistical tool. ZeFir puts the emphasis on a user-friendly experience in order to facilitate and speed up working time. Key parameters can be easily controlled, and unique innovative features bring geographical origins work to another level.     

Online engagement during COVID-19: Role of agency on collaborative learning orientation and learning expectations

During the COVID-19 outbreak, students had to cope with succeeding in video-conferencing classes susceptible to technical problems like choppy audio, frozen screens and poor Internet connection, leading to interrupted delivery of facial expressions and eye-contact. For these reasons, agentic engagement during video-conferencing became critical for successful learning outcomes. This study explores the mediating effect agentic engagement has on collaborative language learning orientations (CLLO) within an EFL video-conferencing course to understand better how interactions influence academic learning expectations. A total of 329 (Male = 132, Female = 197) students were recruited from four South Korean universities to participate in this questionnaire study. Data analysis was carried out using the statistical software packages SPSS, and a series of data screening procedures were carried out. Findings revealed that collaborative language learning orientations were a statistically significant predictor of academic learning expectations, but this relationship was fully mediated when agentic engagement was added to the model. Students with a propensity for social language learning strategies believe they will succeed; however, this relationship is explained by their propensity to interact with the instructor when video-conferencing. An assortment of learning activities should be provided to support both collaborative and individual learning orientations for academic success. Students with collaborative learning tendencies and a propensity to actively engage the instructor during video conference classes are active participants in the eLearning context, possibly leading to positive course expectations.