The two-sample Winsorized t

This paper extends the single-sample Winsorized t to the case of two independent samples. Statistics are defined for both the cases of equal and unequal population variances. Monte Carlo techniques were used to find the approximate distributions of these statistics as well as to evaluate their performances in comparison to the trimmed t . It was found that as far as the power is concerned, the differences between the Winsorized t and the trimmed t are so small that the choice is immaterial for practical purposes.     

Postcolonial Hong Kong identity: hybridising the local and the national

This paper investigates the changing contour of Hong Kong's cultural identity. This is an empirical longitudinal study which conceptualises Hong Kong identity as the cultural affect of the local from the national — a spatial distance between ‘us’ and ‘others’. While the citizenship of Hong Kong is a closed issue after China resumed Hong Kong's sovereignty in 1997, the question of cultural identity is open to negotiation. The transition marked the apex of the identification. After 1997, however, Hong Kong people might not have the strong identification with China as appeared during the political transition in the high intensity of media coverage of the re‐nationalisation. Yet, what is evident is that Hong Kong people no longer strongly oppose the Chinese authorities. More importantly, people started to face the reality of appropriating a new dual Hong Kong‐China identity, and hence there is a clear trend of increasing identification with the Hong Kong as well as the Chinese authorities; the legitimacy of the two are more likely perceived to be aligned. Hong Kong people manifested an identity which has become increasingly hybridised between the local and national identity.     

Perpetuating Old Exclusions and Producing New Ones: Digital Exclusion in an Information Society

This article presents a study that measures the degree of digital exclusion—or, conversely, the degree of digital inclusion—in Hong Kong, a developed city in East Asia. Governments in the region are among the most active in the developed world in pushing ahead in developing knowledge economies and information societies. The major concern is to improve/maintain their competitiveness in the new knowledge economy created by the process of globalization and the advancement in information technology. Many countries in the region have established themselves in the top ranks of a number of indexes and measurements comparing digital readiness, digital access, information and communication technology penetration, and others. However, not all the citizens in the region share the benefits and promises of the information society. People who are traditionally disadvantaged, such as the elderly and those on a low income, are further excluded from the information society. Such exclusion affects other social groups as well. This study creates a new digital inclusion index to measures the degree of inclusion of various disadvantaged groups in an information society. Data regarding seven disadvantaged groups were collected through a household survey (N = 2,312). The index captures information about access, knowledge, usage, and affordability ininformation and communication technology of the disadvantaged in comparison with mainstream society (N = 284).     

A quasi-Bayesian analysis of regression outliers using Akaike's predictive likelihood

The Bayesian analysis of outliers using a non-informative prior for the parameters is non-trivial because models with different numbers of outliers have different dimensions. A quasi-Bayesian approach based on the Akaike's predictive likelihood is proposed for the analysis of regression outliers. It overcomes the dimensionality problem in Bayesian outlier analysis in which the likelihood of the outlier model is compensated by a correction factor adjusted for the number of outliers. The stack loss data set is analysed with satisfactory results.     

Sustainable planning strategies in supply chain systems: proposal and applications with a real case study in fashion

Abstract

Pollution generated by the fashion industry drives people to pay attention to fashion companies’ sustainability practice. This increase in attention has induced vast literature studying the related area. Since the fashion apparel supply chain is complicated which involves a lot of interrelated steps and decisions, how fashion companies can identify the demand in sustainable fashion and make the right decision in resource allocation throughout the supply chain becomes a critical issue. As a result, this paper examines how a fashion company can develop a successful sustainable planning strategy throughout the sustainable fashion supply chain. The sustainability attributes and the sustainable planning strategy mechanism are also discussed. Based on the institutional theory and resource-based theory, we first analyse the external pressure and internal motivations for companies to adopt a sustainable planning strategy in the fashion supply chain. We then identify the core stakeholders related to the sustainable planning strategy and propose how the decision-making theory can help develop the sustainable supply chain management mechanism. Next, we establish a sustainable planning strategy framework. Finally, via a case study with public data on the fashion giant brand Nike, we explore the application of our proposed sustainable planning strategy framework. The finding suggests that the strategic planning of fashion companies on sustainability can improve the performance of the stakeholders throughout the whole sustainable fashion supply chain.     

Doubly robust estimation of partially linear models for longitudinal data with dropouts and measurement error in covariates

In longitudinal studies, missing responses and mismeasured covariates are commonly seen due to the data collection process. Without cautiousness in data analysis, inferences from the standard statistical approaches may lead to wrong conclusions. In order to improve the estimation for longitudinal data analysis, a doubly robust estimation method for partially linear models, which can simultaneously account for the missing responses and mismeasured covariates, is proposed. Imprecisions of covariates are corrected by taking advantage of the independence between replicate measurement errors, and missing responses are handled by the doubly robust estimation under the mechanism of missing at random. The asymptotic properties of the proposed estimators are established under regularity conditions, and simulation studies demonstrate desired properties. Finally, the proposed method is applied to data from the Lifestyle Education for Activity and Nutrition study.     

Structural identification and variable selection in high-dimensional varying-coefficient models

Varying-coefficient models have been widely used to investigate the possible time-dependent effects of covariates when the response variable comes from normal distribution. Much progress has been made for inference and variable selection in the framework of such models. However, the identification of model structure, that is how to identify which covariates have time-varying effects and which have fixed effects, remains a challenging and unsolved problem especially when the dimension of covariates is much larger than the sample size. In this article, we consider the structural identification and variable selection problems in varying-coefficient models for high-dimensional data. Using a modified basis expansion approach and group variable selection methods, we propose a unified procedure to simultaneously identify the model structure, select important variables and estimate the coefficient curves. The unique feature of the proposed approach is that we do not have to specify the model structure in advance, therefore, it is more realistic and appropriate for real data analysis. Asymptotic properties of the proposed estimators have been derived under regular conditions. Furthermore, we evaluate the finite sample performance of the proposed methods with Monte Carlo simulation studies and a real data analysis.     

An exploratory study of different approaches between social work practice and correctional services in Hong Kong Special Administrative Region

This paper tries to explore the differences between social work and correctional services from the aspects of professional boundaries, concept, content, construct, context, approach, function, professional identity and relationship with service users. Through these, social workers will be informed what are the limitations of their service in a correctional environment, whilst for correctional officers, a better understanding of the philosophical stance of social services which may be helpful for them in discharging their dual role of law enforcer and social worker under the contemporary correctional policy stressing rehabilitation and reintegration of offenders.     

Bayesian semiparametric reproductive dispersion mixed models for non-normal longitudinal data: estimation and case influence analysis

Semiparametric reproductive dispersion mixed model (SPRDMM) is a natural extension of the reproductive dispersion model and the semiparametric mixed model. In this paper, we relax the normality assumption of random effects in SPRDMM and use a truncated and centred Dirichlet process prior to specify random effects, and present the Bayesian P-spline to approximate the smoothing unknown function. A hybrid algorithm combining the block Gibbs sampler and the Metropolis–Hastings algorithm is implemented to sample observations from the posterior distribution. Also, we develop Bayesian case deletion influence measure for SPRDMM based on the φ-divergence and present those computationally feasible formulas. Several simulation studies and a real example are presented to illustrate the proposed methodologies.