Restricted maximum likelihood estimation of joint mean‐covariance models

The class of joint mean‐covariance models uses the modified Cholesky decomposition of the within subject covariance matrix in order to arrive to an unconstrained, statistically meaningful reparameterisation. The new parameterisation of the covariance matrix has two sets of parameters that separately describe the variances and correlations. Thus, with the mean or regression parameters, these models have three sets of distinct parameters. In order to alleviate the problem of inefficient estimation and downward bias in the variance estimates, inherent in the maximum likelihood estimation procedure, the usual REML estimation procedure adjusts for the degrees of freedom lost due to the estimation of the mean parameters. Because of the parameterisation of the joint mean covariance models, it is possible to adapt the usual REML procedure in order to estimate the variance (correlation) parameters by taking into account the degrees of freedom lost by the estimation of both the mean and correlation (variance) parameters. To this end, here we propose adjustments to the estimation procedures based on the modified and adjusted profile likelihoods. The methods are illustrated by an application to a real data set and simulation studies. The Canadian Journal of Statistics 40: 225–242; 2012 © 2012 Statistical Society of Canada     

A generalized Fleming and Harrington's class of tests for interval‐censored data

The class $G^{\rho,\lambda }$ of weighted log‐rank tests proposed by Fleming & Harrington [Fleming & Harrington (1991) Counting Processes and Survival Analysis, Wiley, New York] has been widely used in survival analysis and is nowadays, unquestionably, the established method to compare, nonparametrically, k different survival functions based on right‐censored survival data. This paper extends the $G^{\rho,\lambda }$ class to interval‐censored data. First we introduce a new general class of rank based tests, then we show the analogy to the above proposal of Fleming & Harrington. The asymptotic behaviour of the proposed tests is derived using an observed Fisher information approach and a permutation approach. Aiming to make this family of tests interpretable and useful for practitioners, we explain how to interpret different choices of weights and we apply it to data from a cohort of intravenous drug users at risk for HIV infection. The Canadian Journal of Statistics 40: 501–516; 2012 © 2012 Statistical Society of Canada     

Gender-specific differences in labor market adjustment patterns: Evidence from the United States

Do men and women behave differently while adjusting labor supply over the business cycle? Using data from the United States, we show that women are significantly more likely to adjust along the intensive margin (number of hours), while men adjust more along the extensive margin (employment). Older, single, and divorced/widowed adjust predominantly along the extensive margin.     

Commentary: Flawed Scientific-Evidence Standards Delay Diesel Regulations

Of 188 government-monitored air toxics, diesel particulate matter (DPM) causes seven times more cancer than all the other 187 air toxics combined, including benzene, lead, and mercury. Yet, DPM is the only air toxic not regulated more stringently under the Clean Air Act, as a hazardous air pollutant (HAP). One reason is that regulators use flawed standards of scientific evidence. The article argues (1) that DPM meets all six specified evidentiary criteria, any one of which is sufficient for HAP regulation and (2) that regulators’ standards of evidence for denying HAP status to DPM (no DPM unit-risk estimate, inadequate dose-response data, alleged weak mechanistic data) err logically and scientifically, set the evidence bar too high, delay regulation, and allow 21,000 avoidable DPM deaths annually in the U.S.     

Understanding innovation performance and its antecedents: A socio-cognitive model

Little attention in the previous literature has been paid to understanding employees’ factors that drive customer development knowledge and performance from the perspective of social psychology. Drawing on social cognitive theory, this study validates a research model that examines the above issue. In the setting of new product development across high-tech firms in Taiwan, this study postulates that innovation self-efficacy, role conflict, and role ambiguity influence innovation performance directly and indirectly via the mediation of customer knowledge development and innovation outcome expectation. This study contributes to the social science literature by applying social cognitive theory to the rarely explored area of innovation performance and by presenting an operationalization of role stressors (i.e., role ambiguity and role conflict) in the area. Lastly, managerial implications and limitations from the empirical findings are provided.     

Measuring inequality with asset indicators

This paper examines whether, in the absence of information on household income or consumption, data on household infrastructure, building materials, and ownership of certain durable assets can be used to measure inequality in living standards. Principal components analysis is used to obtain a relative measure of inequality, and a bootstrap prediction method is provided for use when auxiliary surveys are available. Mexican data is used to show that the inequality methods provided do provide reasonable proxies for inequalities in living standards. An application finds that after controlling for household income and demographics, school attendance of boys in Mexico is negatively related to state-level inequality.     

Altruism and the macroeconomic effects of demographic changes

In this paper we show that the macroeconomic effects of demographic changes strongly depend on the degree of altruism and on the specification of the intertemporal utility function. We allow for agents either to be altruistic in the sense of Barro (1974) or non-altruistic. In the latter case, generations are heterogeneous like in the „unloved children” model of Weil (1989). In the former case, where the model is a standard Ramsey model with identical agents, we distinguish a Millian and a Benthamite intertemporal utility function. For each of these models, we study the effects of an anticipated and unanticipated permanent decline in population growth as well as the consequences of a baby-boom/baby-bust scenario. Received April 17, 1996/Accepted December 10, 1996     

Fetal movement frequency and the effect of associated perinatal factors: Multicenter study

Background

Decreased fetal movements are associated with adverse perinatal outcomes, including stillbirth. Delayed maternal visits to a health care provider after perceiving decreased fetal movements are frequently observed in stillbirths. Informing pregnant women of the normal range of fetal movement frequency is essential in their earlier visits in order to prevent stillbirth.

Did the association between fertility and female employment within OECD countries really change its sign?

Recent literature finds that in OECD countries the cross-country correlation between the total fertility rate and the female labor force participation rate, which until the beginning of the 1980s had a negative value, has since acquired a positive value. This result is (explicitly or implicitly) often interpreted as evidence for a changing sign in the time-series association between fertility and female employment within OECD countries. This paper shows that the time-series association between fertility and female employment does not demonstrate a change in sign. Instead, the reversal in the sign of the cross-country correlation is most likely due to a combination of two elements: First, the presence of unmeasured country-specific factors and, second, country-heterogeneity in the magnitude of the negative time-series association between fertility and female employment. However, the paper does find evidence for a reduction in the negative time-series association between fertility and female employment after about 1985.I benefited from stimulating discussions with Arnstein Aassve, Pau Baizan, Francesco Billari, Henriette Engelhardt, Hans-Peter Kohler and Alexia Prskawetz and a seminar in Rostock. Further, I am grateful to two anonymous referees for very useful suggestions that improved essentially the content of the paper. In addition, I thank Susan Masur, Susann Backer, and Elizabeth Zach for language editing. The views expressed in this paper are the authors own views and do not necessarily represent those of the Max Planck Institute for Demographic Research. Responsible editor: Junsen Zhang.     

Trust games: A meta-analysis

We collect data from 162 replications of the Berg, Dickhaut, and McCabe Investment game (the “trust” game) involving more than 23,000 participants. We conduct a meta-analysis of these games in order to identify the effect of experimental protocols and geographic variation on this popular behavioral measure of trust and trustworthiness. Our findings indicate that the amount sent in the game is significantly affected by whether payment is random, and whether play is with a simulated counterpart. Trustworthiness is significantly affected by the amount by which the experimenter multiplies the amount sent, whether subjects play both roles in the experiment, and whether the subjects are students. We find robust evidence that subjects send less in trust games conducted in Africa than those in North America.