A Discrete Time Parametric Model for the Analysis of Failure Time Data

This paper introduces a parametric discrete failure time model which allows a variety of smooth hazard function shapes, including shapes which are not readily available with continuous failure time models. The model is easy to fit, and statistical inference is simple. Further, it is readily extended to allow for differences between subjects while retaining the ease of fit and simplicity of statistical inference. The performance of the discrete time analysis is demonstrated by application to several data sets.     

The post-80s generation: exploring the attitudes toward family and housing

ABSTRACT

Previous literature has paid attention to housing pathways and cohort features of young people, but studies connecting the two themes are lacking. This paper offers a perspective on the cohort analysis of young people based on their housing choices and aspirations. With empirical evidence from a two-round social survey, this study explores the ‘not leaving home’ pattern of the housing choices of young people in Hong Kong. With some supplementary subgroup analysis, the cohort label of a ‘post-80s generation’ in Hong Kong is challenged. Contradictions are revealed in the views of our young people about housing and family life, and further analysis is conducted to examine the impacts of economic and sociocultural factors in the local context of Hong Kong. This study argues that we need to look beyond the shared features and subgroup differences and consider how sociocultural factors, particularly gender, marriage, education, and social norms, interact with economic factors to shape housing choices, aspirations and apparent contradictions in the viewpoints of young people regarding their personal development and housing futures. In doing so, the paper also engages with debates around intra and intergenerational dynamics and inequalities. The paper focuses on Hong Kong but these debates have international resonance.     

An Extension of a Measure of Polarization, with an application to the income distribution of five OECD countries

We introduce an extension of the Esteban and Ray [Econometrica, 62:819–851 1994] measure of polarization that can be applied to density functions. As a by-product we also derive the Wolfson [Am. Econ. Rev., 84:353–358 1994] measure as a special case. This derivation has the virtue of casting both measures in the context of a (statistically) unified framework. We study the polarization of the distribution of household income for five OECD countries (LIS database): US, UK, Canada, Germany and Sweden. The present paper is essentially based on Esteban, Gradín and Ray [9], published as #218 in the working papers series of the Luxembourg Income Study. Changes have been kept to a minimum. We have provided a brief reference to the literature on polarization measurement that has appeared since then and have updated the data of our application.