Resampling Methods for Testing a Semiparametric Random Censorship Model

This paper presents a goodness-of-fit test for a semiparametric random censorship model proposed by Dikta (1998 ). The test statistic is derived from a model-based process which is asymptotically Gaussian. In addition to test consistency, the proposed test can detect local alternatives distinct n ^-1/2 from the null hypothesis. Due to the intractability of the asymptotic null distribution of the test statistic, we turn to two resampling approximations. We first use the well-known bootstrap method to approximate critical values of the test. We then introduce a so-called random symmetrization method for carrying out the test. Both methods perform very well with a sample of moderate size. A simulation study shows that the latter possesses better empirical powers and sizes for small samples.     

Estimating the total number of distinct species using quadrat sampling and under-dependence structure

To estimate the total number of distinct species in a given region, Bayesian methods along with quadrat sampling procedures have been used by several authors. A key underlying assumption relies on the independence among the species. In this note, we analyse these estimates allowing a generalized binomial dependence between species.     

A comparison of tests for trend with historical controls in carcinogen bioassay

ABSTRACT Tests for trend in tumour response rates with increasing dose in long-term laboratory studies of carcinogenicity that take into account historical control information are discussed. The theoretical basis for these tests is described, and their small-sample properties evaluated using computer simulation. The performance of these tests is also evaluated using data from carcinogenicity experiments conducted under the U.S. National Toxicology Program. Based on these results, recommendations are made as to the most appropriate tests in practice. When the assumptions underlying these tests are satisfied, the use of historical control information is shown to result in an increase in power relative to the classical Cochran-Armitage test that is widely used without historical controls.     

The relationship between double-exponential families and extended quasi-likelihood families, with application to modelling Geissler's human sex ratio data

The human sex ratio data, collected in Saxony in the 19th century by Geissler, are reanalysed by joint modelling of the mean and dispersion. Extended quasi-likelihood and the unnormalized double-exponential family are shown to lead to identical inference. The use of the unnormalized form is discussed. The relationship between multinomial and Poisson models is studied for overdispersed data.     

Validation of the Chinese Version of Differentiation of Self Inventory (C‐DSI)

Although the need to develop objective assessment tools in different cultures is well‐recognized, there is a severe lack of objective measures about emotional functioning in the Chinese context. This project conducted three studies to validate the Chinese version of the Differentiation of Self Inventory (DSI). Study 1 looked at the factor structure, internal consistency, concurrent validity, and construct validity of the C‐DSI. Study 2 examined the test–retest reliability of the C‐DSI. Study 3 tested the discriminant validity of the C‐DSI in a clinical sample and in a nonclinical sample and examined its correlations with the General Contentment Scale (GCS). The study results suggested that the C‐DSI possesses good psychometric properties. Findings also indicated implications of divergent cultures and hinted at treatment implications—taking the familistic orientation and the Chinese meaning of self into consideration to understand the differentiation of self in the Chinese culture context.     

Media and information praxis of young activists in the Umbrella Movement

Young people were key participants in the Umbrella Movement in Hong Kong and the media also played an important role in this protest. This study examines how Hong Kong’s young activists developed communication strategies and media practices to mobilize this social movement. A framework termed “media and information praxis of social movements” is proposed for the analysis. The findings showed that in their praxis, the young activists used their media and information literacy skills to initiate, organize, and mobilize collective actions. They not only used social media and mobile networks but also traditional mass media and street booths in a holistic and integrated approach to receive and disseminate information. Hence, these young activists served as agents of mediatization. The results also indicated that the young activists moved away from the traditional movement mode which just tried to motivate a large number of people to protest in the streets. They actively engaged in the new movement mode, which emphasizes the media and information power game. Their praxis in the Umbrella Movement reflects the trend toward the mediatization of social movements in Hong Kong.     

Social media and Umbrella Movement: insurgent public sphere in formation

The study examines the role of social media during the Umbrella Movement in Hong Kong that lasted from September to December 2014. By interviewing a random sample of 1011 respondents over the telephone before the end of the Umbrella Movement, it was found that social media had become an insurgent public sphere (IPS) in the protest movement. Data showed that acquisition of political news through social media was related positively to support for the Umbrella Movement and adversely with satisfaction and trust of established political authorities, including the Hong Kong Special Administrative Region government, the Hong Kong police, and the Chinese central government. The insurgent public sphere role of social media, its implications, and likely development vis-à-vis the state and the market are discussed.     

Unbalanced data classification using support vector machines with active learning on scleroderma lung disease patterns

Unbalanced data classification has been a long-standing issue in the field of medical vision science. We introduced the methods of support vector machines (SVM) with active learning (AL) to improve prediction of unbalanced classes in the medical imaging field. A standard SVM algorithm with four different AL approaches are proposed: (1) The first one uses random sampling to select the initial pool with AL algorithm; (2) the second doubles the training instances of the rare category to reduce the unbalanced ratio before the AL algorithm; (3) the third uses a balanced pool with equal number from each category; and (4) the fourth uses a balanced pool and implements balanced sampling throughout the AL algorithm. Grid pixel data of two scleroderma lung disease patterns, lung fibrosis (LF), and honeycomb (HC) were extracted from computed tomography images of 71 patients to produce a training set of 348 HC and 3009 LF instances and a test set of 291 HC and 2665 LF. From our research, SVM with AL using balanced sampling compared to random sampling increased the test sensitivity of HC by 56% (17.5% vs. 73.5%) and 47% (23% vs. 70%) for the original and denoised dataset, respectively. SVM with AL with balanced sampling can improve the classification performances of unbalanced data.