"第五媒体"大潮暗涌

手机作为"第五媒体"呈迅速发展态势冲击传统媒体,随着3G牌照发放日期的临近,手机报的前景和市场越来越为业内关注.如何在手机报的内容设置、读者定位和广告拓展上寻求突破,是本文思考的一个重点.     

Assessing the stability of classification trees using Florida birth data

Using 1998 and 1999 singleton birth data of the State of Florida, we study the stability of classification trees. Tree stability depends on both the learning algorithm and the specific data set. In this study, test samples are used in statistical learning to evaluate both stability and predictive performance. We also use the resampling technique bootstrap, which can be regarded as data self-perturbation, to evaluate the sensitivity of the modeling algorithm with respect to the specific data set. We demonstrate that the selection of the cost function plays an important role in stability. In particular, classifiers with equal misclassification costs and equal priors are less stable compared to those with unequal misclassification costs and equal priors.     

On the uth geometric conditional quantile

Motivated by Chaudhuri's work [1996. On a geometric notion of quantiles for multivariate data. J. Amer. Statist. Assoc. 91, 862–872] on unconditional geometric quantiles, we explore the asymptotic properties of sample geometric conditional quantiles, defined through kernel functions, in high-dimensional spaces. We establish a Bahadur-type linear representation for the geometric conditional quantile estimator and obtain the convergence rate for the corresponding remainder term. From this, asymptotic normality including bias on the estimated geometric conditional quantile is derived. Based on these results, we propose confidence ellipsoids for multivariate conditional quantiles. The methodology is illustrated via data analysis and a Monte Carlo study.     

Autoregressive distributed lag models and cointegration

Summary This paper considers cointegration analysis within an autoregressive distributed lag (ADL) framework. First, different reparameterizations and interpretations are reviewed. Then we show that the estimation of a cointegrating vector from an ADL specification is equivalent to that from an error-correction (EC) model. Therefore, asymptotic normality available in the ADL model under exogeneity carries over to the EC estimator. Next, we review cointegration tests based on EC regressions. Special attention is paid to the effect of linear time trends in case of regressions without detrending. Finally, the relevance of our asymptotic results in finite samples is investigated by means of computer experiments. In particular, it turns out that the conditional EC model is superior to the unconditional one. We thank Vladimir Kuzin for excellent research assistance and Surayyo Kabilova for skillful word processing. Moreover, we are grateful to an anonymous referee for clarifying comments.     

“Living in sin” and marriage: A matching model

This paper develops a two sided matching model of premarital cohabitation and marriage in which premarital cohabitation serves as a period of learning. We solve for the optimal policy to be followed by individuals by treating the model as a three stage dynamic programming problem. We find that couples are more discriminating when forming marital unions than when forming cohabiting unions. Cohabitation unions arise among members of the same “class” and there is overlap between the classes formed by marital unions and cohabiting unions. This implies that some cohabiting unions progress to marriage while others do not, a finding borne out by empirical studies. Received: 4 November 1999/Accepted: 4 September 2000     

Employee reactions to positive action policies in the United Kingdom: Does the organization’s justification matter?

Affirmative action remains a contentious topic in both research and practice. While advocates suggest that such action is necessary to overcome demographic imbalances in the labor market, some research shows that these policies can prompt undesirable employee reactions that negate their value. While positive discrimination (i.e., recruiting or promoting solely based on a protected characteristic) remains illegal in the United Kingdom, organizations have increasingly begun adopting positive action measures (i.e., measures aimed at alleviating disadvantage or under-representation based on protected characteristics). However, there is little research looking at how these policies specifically affect employee attitudes or how different organizational rationales for positive action might moderate these effects. This lack of research is even more notable in the UK context. In two experimental studies of UK professionals (N = 353) we find that perceived organizational justice explained the relationship between positive action and affective commitment / turnover intention. However, evidence supporting the effect of organizational rationale was limited.     

Modelling household income dynamics

This paper is about income and poverty dynamics and their socioeconomic correlates. The first half of the paper aims to establish some of the salient facts for Britain, applying the pioneering methods of Bane and Ellwood (1986). Important for poverty dynamics are changes in labour earnings from persons other than the household head, changes in non-labour income (including benefits), and changes in household composition, in addition to changes in the heads' labour earnings. The second half of the paper is a review and critique of the multivariate modelling frameworks which might be used to explain and forecast these salient facts for Britain or elsewhere. Received: 7 January 1999/Accepted: 22 July 1999     

An empirical analysis of the welfare magnet debate using the NLSY

This paper examines the extent to which differences in welfare generosity across states leads to interstate migration. Using microdata from the National Longitudinal Survey of Youth (NLSY) between 1979 and 1992, we employ a quasi-experimental design that utilizes the categorical eligibility of the welfare system. The pattern of cross-state moves among poor single women with children, who are likely to be eligible for benefits is compared to the pattern among other poor households. We find little evidence indicating that welfare-induced migration is a widespread phenomenon. Received: 3 April 1997/Accepted: 4 September 1998     

Immigration and the public sector: Income effects for the native population in Sweden

The immigrants' age structure and labour market situation are major determinants for their net contribution to the public sector. During the 50s, 60s and the 70s the immigrants' net contributions gave positive income effects for the native Swedes. Nowadays there are negative income effects due to the deteriorating employment situation among the immigrants. The yearly positive or negative income effects have at most been 1–2% of the gross national product. A change in the immigrants' employment rate by 1 percentage unit will change their yearly net contribution to the public sector by 0.1% of the gross national product. Received: 2 February 1996/Accepted: 28 July 1998     

The extent of labour specialization in the extended family: A theoretical and empirical analysis

In this paper we present a simple model of labour supply that is cast within the framework of an extended family. The model emphasizes a Ricardian division of labour whereby the specialization is solely driven by marginal productivity and value of time differentials. The empirical implications of the model are derived and tested using data that was collected in France to study the extent of trade within the family network. We find evidence that the extent of specialization is sensitive to the value of time differentials. Received: 17 May 1995 / Accepted: 20 February 1997