Effects of correlation and missing data on sample size estimation in longitudinal clinical trials

In longitudinal clinical trials, a common objective is to compare the rates of changes in an outcome variable between two treatment groups. Generalized estimating equation (GEE) has been widely used to examine if the rates of changes are significantly different between treatment groups due to its robustness to misspecification of the true correlation structure and randomly missing data. The sample size formula for repeated outcomes is based on the assumption of missing completely at random and a large sample approximation. A simulation study is conducted to investigate the performance of GEE sample size formula with small sample sizes, damped exponential family of correlation structure and non‐ignorable missing data. Copyright © 2008 John Wiley & Sons, Ltd.     

Perceived Aspects of Home Environment and Home Modifications by Older People Living in Rural Areas

This study investigated the relationships between the “perceived aspects” of current home environment of elderly people living in rural areas and their home modification behavior. To investigate this perception, home satisfaction, perception of home capability, and home safety were used as perceived aspects of the home. Data were collected by a questionnaire. The response rate was 43.1%, with 317 eligible questionnaires. The results from this study indicate that there was no significant difference in perceived aspects of home environment between those who modified their homes and those who did not. Regardless of their current home conditions, most elderly respondents (75%) showed high home satisfaction. Results from this study suggest that a modified home environment does not necessarily contribute to an older person's perception of perceived aspects of their home environment.     

Race and the beauty premium: Mechanical Turk workers’ evaluations of Twitter accounts

ABSTRACT

Race, gender, and physical attractiveness strongly affect perceptions of trustworthiness and subsequent face-to-face interactions. This study examines how social media users’ perceived gender, race, and physical attractiveness can impact their standing online. We test these broad hypotheses by having Amazon Mechanical Turk (MTurk) workers evaluate a sample of 816 Twitter accounts. Our results show a ‘beauty premium,’ where MTurk workers say they are more likely to follow Twitter accounts with attractive pro?le photos, and attractive photos are positively associated with evaluations of trust. However, very attractive Black male and female Twitter accounts are associated with lower evaluations of trust compared to their White counterparts. These findings suggest that social media users’ social characteristics, perceived from their username or profile image, can replicate offline inequality online.     

“Don't Cry,You're Not a Baby!”: Emotion,Role and Hierarchy in Korean Language Socialisation Practice

I examine how South Korean children learn culturally specific emotional knowledge, especially affective hierarchy and the association between emotional displays and social roles, through participation in peer talk. An analysis of children's and teachers’ everyday emotional discourses shows that children, rather than passively adopting adult emotional discourses, creatively employ a range of linguistic and communicative features regarding emotions to construct their own culture‐laden emotional world. Findings articulate the role children's peer talk has in cultural reproduction and dynamic aspects of the language socialisation processes.     

A proportional-reduction-in-impurity measure of association for categorical variables

This paper presents a proportional-reduction-in-impurity (PRI) measure for categorical association, that employs application-dependent loss functions which make the measure widely applicable. The well-known proportional -reduction-in-error (PRE) measure is shown to be a special case of the new PRI measure. Moreover, the asymptotic variance of the maximum likelihood estimator (MLE) of the measure is derived to facilitate its use for statistical inference. An extension of the PRI measure to compositional association is made to show that it can have a variety of applications. Selected loss functions are treated to illustrate the derivation of the measure.     

Planned Happenstance Skills and Occupational Identity Status in High School Students

This study investigated how the 5 components of planned happenstance skills are related to adolescents' occupational identity statuses. A canonical correlation analysis was performed with a sample of 370 high school students in South Korea. The results indicated that higher identity statuses (i.e., achievement and moratorium statuses) were significantly related to the 5 components of planned happenstance skills, whereas lower identity statuses (i.e., foreclosure and diffusion statuses) were not significantly related to the 5 components of planned happenstance skills. In addition, the results of the mediation analysis indicated that the transition from moratorium to achievement status was positively mediated by 3 components of planned happenstance skills: optimism, persistence, and risk taking.     

Efficient Markov chain Monte Carlo with incomplete multinomial data

We propose a block Gibbs sampling scheme for incomplete multinomial data. We show that the new approach facilitates maximal blocking, thereby reducing serial dependency and speeding up the convergence of the Gibbs sampler. We compare the efficiency of the new method with the standard, non-block Gibbs sampler via a number of numerical examples.     

Five new towns in the Seoul metropolitan area and their attractions in non-working trips: Implications on self-containment of new towns

In the late 1980s, the Korean government initiated the “Two Million Home Construction Plan” to tackle severe shortages in housing and soaring housing prices. Five new towns (Bundang, Ilsan, Pyeongchon, Sanbon, and Joongdong) were planned around the city of Seoul. By the mid-1990s the residential areas in the five new towns were mostly developed. However, their commercial areas have remained underdeveloped and as a consequence, the new towns are believed to have become bedroom communities.This paper assesses self-containment status of the new towns by analyzing non-working trip patterns in the five new town areas. A survey conducted on non-working trip patterns of the residents in the five new towns and the nearby areas (to shop for groceries, clothing, electronics/jewelry, leisure/entertainment, and to access medical services) reveals that Bundang's commercial dependency upon the city of Seoul has been reduced significantly over the past 5 years (from 1995 to 2000). The survey results on non-working trip patterns of the residents in the five new towns and nearby residential areas in the Seoul Metropolitan Area indicate that the five new towns have been growing as suburban centers in the region in terms of retail attractions, even though they are still maintaining a high dependency on Seoul in terms of working commutes.These observations provide some new indications about self-containment arguments relevant to new town planning. The new towns are currently maintaining a decent degree of self-containment in terms of non-working trip, which has been an important aspect absent in self-containment arguments. In addition, the appeal of self-containment in non-working activities is growing in a dynamic sense. Observations on the dynamic process of the new town developments in Korea demonstrate that the self-containment can be established but through a long taking cumulative and stepwise process rather than immediately by planning.     

A note on the changing relationship between fertility and female employment rates in developed countries

In this paper we look at a panel of OECD aggregate fertility and labor market data between 1970 and 1995 and we report some striking recent developments. Total Fertility Rates (TFR) were falling and Female Participation Rates (FPR) were increasing, conforming to a well known long-run trend. Along the cross-sectional dimension, the correlation between TFR and FPR was negative and significant during the 1970's and up to the early 1980's. This seemed consistent with secular comovements. However, by the late 1980's the correlation had become positive and equally significant. We discuss our findings within the framework of standard neoclassical models of fertility and labor supply adapted to macro data, as in Butz and Ward (1979). Received: 14 April 2000/Accepted: 29 December 2000 All correspondence to Pedro Mira. Namkee Ahn is grateful for financial support received from the Bank of Spain and from Spain's Ministerio de Educación y Cultura, grant SEC97-1249. We benefited from comments by two anonymous referees and by seminar participants at FEDEA, CEMFI and ESPE-98. All remaining errors are our own. Responsible editor: John F. Ermisch.