Robust Bayesian model selection for variable clustering with the Gaussian graphical model

Statistics and Computing - Variable clustering is important for explanatory analysis. However, only few dedicated methods for variable clustering with the Gaussian graphical model have been...     

Unveiling the Canvas Ceiling: A Multidisciplinary Literature Review of Refugee Employment and Workforce Integration

Increasing levels of displacement and the need to integrate refugees in the workforce pose new challenges to organizations and societies. Extant research on refugee employment and workforce integration currently resides across various disconnected disciplines, posing a significant challenge for management scholars to contribute to timely and relevant solutions. In this paper, we endeavour to address this challenge by reviewing and synthesizing multidisciplinary literature on refugee employment and workforce integration. Using a relational framework, we organize our findings around three levels of analysis – institutional, organizational and individual – to outline the complexity of factors affecting refugees’ employment outcomes. Based on our analysis, we introduce and elaborate on the phenomenon of the canvas ceiling ? a systemic, multilevel barrier to refugee workforce integration and professional advancement. The primary contributions of this paper are twofold. First, we map and integrate the multidisciplinary findings on the challenges of refugee workforce integration. Second, we provide management scholarship with a future research agenda to address the knowledge gap identified in this review and advance practical developments in this domain.     

Linear Increments with Non‐monotone Missing Data and Measurement Error

Linear increments (LI) are used to analyse repeated outcome data with missing values. Previously, two LI methods have been proposed, one allowing non‐monotone missingness but not independent measurement error and one allowing independent measurement error but only monotone missingness. In both, it was suggested that the expected increment could depend on current outcome. We show that LI can allow non‐monotone missingness and either independent measurement error of unknown variance or dependence of expected increment on current outcome but not both. A popular alternative to LI is a multivariate normal model ignoring the missingness pattern. This gives consistent estimation when data are normally distributed and missing at random (MAR). We clarify the relation between MAR and the assumptions of LI and show that for continuous outcomes multivariate normal estimators are also consistent under (non‐MAR and non‐normal) assumptions not much stronger than those of LI. Moreover, when missingness is non‐monotone, they are typically more efficient.     

Semiparametric Estimation of a Change-point for Recurrent Events Data

One particular recurrent events data scenario involves patients experiencing events according to a common intensity rate, and then a treatment may be applied. The treatment might be effective for a limited amount of time, so that the intensity rate would be expected to change abruptly when the effect of the treatment wears out. In particular, we allow models for the intensity rate, post-treatment, to be at first decreasing and then change to increasing (and vice versa). Two estimators of the location of this change are proposed.     

Collective versus Individual Effects in Survival Analysis of Multiple Failures

In survival analysis, we sometimes encounter data with multiple censored outcomes. Under certain scenarios, partial or even all covariates have ‘similar’ relative risks on the multiple outcomes in the Cox regression analysis. The similarity in covariate effects can be quantified using the proportionality of regression coefficients. Identifying the proportionality structure, or equivalently whether covariates have individual or collective effects, may have important scientific implications. In addition, it can lead to a smaller set of unknown parameters, which in turn results in more accurate estimation. In this article, we develop a novel approach for identifying the proportionality structure. Simulation shows the satisfactory performance of the proposed approach and its advantage over estimation under no assumed structure. We analyse three datasets to demonstrate the practical application of the proposed approach.     

Dealing with the Initial Observation in the LM Unit Root Test

This article proposes a linearly weighted unit root test with a new weighting scheme which reflects the trade-off in power between the ADF and LM tests regarding the initial value of a time series. Simulation results indicate that the proposed test has better power performance and works better than other available tests in the literature for a range of initial conditions.     

Measuring Social Tension from Income Class Segregation

We develop an index that effectively measures the level of social tension generated by income class segregation. We adopt the basic concepts of between-group difference (or alienation) and within-group similarity (or identification) from the income [bi]polarization literature; but we allow for asymmetric degrees of between-group antagonism in the alienation function, and construct a more effective identification function using both the relative degree of within-group clustering and the group size. To facilitate statistical inference, we derive the asymptotic distribution of the proposed measure using results from U-statistics. As the new measure is general enough to include existing income polarization indices as well as the Gini index as special cases, the asymptotic result can be readily applied to these popular indices. Evidence from the Panel Study of Income Dynamics data suggests that, while the level of social tension shows an upward trend over the sample period of 1981 to 2005, government’s taxes and transfers have been effective in reducing the level of social tension significantly.     

Finie mixures of canonical fundamenal skew $$$$-disribuions

This paper introduces a finite mixture of canonical fundamental skew \(t\) (CFUST) distributions for a model-based approach to clustering where the clusters are asymmetric and possibly long-tailed (in: Lee and McLachlan, arXiv:1401.8182 [statME], 2014b). The family of CFUST distributions includes the restricted multivariate skew \(t\) and unrestricted multivariate skew \(t\) distributions as special cases. In recent years, a few versions of the multivariate skew \(t\) (MST) mixture model have been put forward, together with various EM-type algorithms for parameter estimation. These formulations adopted either a restricted or unrestricted characterization for their MST densities. In this paper, we examine a natural generalization of these developments, employing the CFUST distribution as the parametric family for the component distributions, and point out that the restricted and unrestricted characterizations can be unified under this general formulation. We show that an exact implementation of the EM algorithm can be achieved for the CFUST distribution and mixtures of this distribution, and present some new analytical results for a conditional expectation involved in the E-step.     

Stochastically optimal bootstrap sample size for shrinkage-type statistics

In nonregular problems where the conventional \(n\) out of \(n\) bootstrap is inconsistent, the \(m\) out of \(n\) bootstrap provides a useful remedy to restore consistency. Conventionally, optimal choice of the bootstrap sample size \(m\) is taken to be the minimiser of a frequentist error measure, estimation of which has posed a major difficulty hindering practical application of the \(m\) out of \(n\) bootstrap method. Relatively little attention has been paid to a stronger, stochastic, version of the optimal bootstrap sample size, defined as the minimiser of an error measure calculated directly from the observed sample. Motivated by this stronger notion of optimality, we develop procedures for calculating the stochastically optimal value of \(m\). Our procedures are shown to work under special forms of Edgeworth-type expansions which are typically satisfied by statistics of the shrinkage type. Theoretical and empirical properties of our methods are illustrated with three examples, namely the James–Stein estimator, the ridge regression estimator and the post-model-selection regression estimator.