Adult Outcomes for Children of Teenage Mothers

Using data from the British Household Panel Survey, this study examines the relationship between several outcomes in early adulthood (e.g. education, inactivity, earnings and health) and being born to a teenage mother. Besides standard cross‐sectional multivariate regression estimates, we also present evidence from non‐parametric estimates and from estimates that account for unmeasured family background heterogeneity by comparing siblings born to the same mother who timed their births at different ages. Regardless of the econometric technique, being born to a teenage mother is usually associated with worse outcomes. An important channel of transmission of this adverse effect is childhood family structure, which plays a more powerful role than childhood family poverty. Albeit smaller, some of the detrimental effects are also found for children of mothers who gave birth in their early 20s.     

THE BIVARIATE EXPONENTIAL DISTRIBUTION; A REVIEW AND SOME NEW RESULTS

Various models have been proposed as bivariate forms of the exponential distribution. A brief but comprehensive review is presented which classifies, interrelates and contrasts the different models and outlines what is known about distributional properties, applicability and estimation and testing of parameters (particularly the association parameter). Some new results are presented for one particular model. Maximum likelihood, and moment–type, estimators of the association parameter are examined. Asymptotic variances are derived and attention is given to the relative efficiency of the estimators and to problems of their evaluation.     

Developing effective e-recruiting websites: Insights for managers from marketers

In recent years, the practice of using corporate websites to recruit job applicants has increased steadily. Despite this trend, however, studies show that approximately 75% of job seekers find the sites too complicated to use successfully [Brown, D. (2004). Unwanted online job seekers swamp HR staff. Canadian HR Reporter, 17(7), 1-2] and that more than 20% have rejected job opportunities based on poorly designed websites [Pastore, M. (2000, March 29). http://www.clickz.com/showPage.html?page=330331]. To address this problem, this article joins Internet marketing and employee recruitment research to offer six development implications for creating an effective “e-recruitment” source on a corporate website. Based on a job marketing approach to the recruitment process and consumer behavior research on persuasive communication and decision making, we present considerations important to creating an online recruiting website that effectively influences the search decisions and behaviors of a target market of desired job candidates.     

Poisson Regression for Clustered Data

We compare five methods for parameter estimation of a Poisson regression model for clustered data: (1) ordinary (naive) Poisson regression (OP), which ignores intracluster correlation, (2) Poisson regression with fixed cluster‐specific intercepts (FI), (3) a generalized estimating equations (GEE) approach with an equi‐correlation matrix, (4) an exact generalized estimating equations (EGEE) approach with an exact covariance matrix, and (5) maximum likelihood (ML). Special attention is given to the simplest case of the Poisson regression with a cluster‐specific intercept random when the asymptotic covariance matrix is obtained in closed form. We prove that methods 1–5, except GEE, produce the same estimates of slope coefficients for balanced data (an equal number of observations in each cluster and the same vectors of covariates). All five methods lead to consistent estimates of slopes but have different efficiency for unbalanced data design. It is shown that the FI approach can be derived as a limiting case of maximum likelihood when the cluster variance increases to infinity. Exact asymptotic covariance matrices are derived for each method. In terms of asymptotic efficiency, the methods split into two groups: OP & GEE and EGEE & FI & ML. Thus, contrary to the existing practice, there is no advantage in using GEE because it is substantially outperformed by EGEE and FI. In particular, EGEE does not require integration and is easy to compute with the asymptotic variances of the slope estimates close to those of the ML.     

基于Gibbs采样的MIMO信号检测改进算法

针对传统Gibbs采样算法的“失控问题”,提出了一种改进算法,在Gibbs迭代采样过程中加入对噪声方差的估计,消除了失控问题。设计了信号检测流程,将最大似然（ML）检测的搜索过程嵌入Gibbs迭代采样过程,减少了最大似然检测的计算步骤。仿真结果表明,所提算法能估计噪声方差,具有接近最大似然检测的性能。     

Price Discrimination and Pricing to Market Behavior of Canadian Canola Exporters

The role of exchange rate fluctuation on the pricing behavior of Canadian canola exporters to Japan, Mexico, and the U.S. is examined using a model identifying noncompetitive and exchange rate related pricing behavior. Price discrimination was identified for Canadian canola exports to the three destinations over the period of 1993–99. Results also suggest that Pricing to Market strategies were employed for Japanese imports. Canadian canola exporters used local currency price stabilization to dampen the effects of relative price changes in the Japanese currency, perhaps linked to the large size of Japanese imports relative to Mexico and the U.S.     

Pareto Index Estimation Under Moderate Right Censoring

Real claim data sometimes are censored from above at a high value induced by the sum insured. In this note we examine the behaviour of extreme-value methods in such settings and propose an adaptation of the popular Hill (1975) estimator. It is argued that the censoring typically cannot exceed 5% for an effective use of the methods suggested.     

相对付出优势对忠诚计划参与意愿的影响效应

本文研究了顾客为获得忠诚计划回报需付出的努力与顾客的参与意愿之间的关系。根据社会比较理论，顾客会以自己与其他顾客的比较结果作为线索，评价在此计划上的相对付出，并根据比较结果决定参与意愿。本文通过三个实验，分别操纵被试的个人努力、其他顾客的参考努力、以隐性方式操纵其他顾客的参考努力等三种情境，来验证以上命题。研究结果发现：（1）顾客考虑是否参与忠诚计划时，会根据与其他顾客比较的相对付出努力作为参考做出决策；（2）当存在相对付出优势时（个人努力〈参考努力），高的回报标准反而能提高顾客的参与意愿；（3）当存在相对付出劣势时（个人努力〉参考努力），高的回报标准削弱了顾客的参与意愿。     

Two-step estimation of panel data models with censored endogenous variables and selection bias

This paper presents some two-step estimators for a wide range of parametric panel data models with censored endogenous variables and sample selection bias. Our approach is to derive estimates of the unobserved heterogeneity responsible for the endogeneity/selection bias to include as additional explanatory variables in the primary equation. These are obtained through a decomposition of the reduced form residuals. The panel nature of the data allows adjustment, and testing, for two forms of endogeneity and/or sample selection bias. Furthermore, it incorporates roles for dynamics and state dependence in the reduced form. Finally, we provide an empirical illustration which features our procedure and highlights the ability to test several of the underlying assumptions.     

Dynamics of Urban Residential Property Prices— A Case Study of the Manhattan Market

In a multivariate vector autoregression framework, this paper investigates the weak efficiency of the urban residential real estate market and the cause of weak efficiency. An error correction model is used to estimate long-term relationships among apartment prices and adjustment speed from disequilibrium to equilibrium. Based on a unique dataset of the Manhattan market, the efficiency of this market, seasonal stationarity of property prices, and the weak exogeneity of leading sub-markets are studied. Our results indicate that, in a market of less heterogeneity and higher transaction volumes, the weak efficiency hypothesis is rejected as in previous studies. This result implies that heterogeneity and lack of transaction information may not be the direct source of market inefficiency. Meanwhile, it is found that there are stable long-term relations among prices of different sub-markets. Interestingly, the price of one-bedroom co-operatives (co-op) is weakly exogenous. This implies that the starting co-op for most home buyers in urban areas is a leading indicator of the entire market, which contradicts the claim that high-end luxury co-op leads the market.