Statistical analysis of Weibull distributed lifetime data under Type II progressive censoring with binomial removals

This paper considers the analysis of Weibull distributed lifetime data observed under Type II progressive censoring with random removals, where the number of units removed at each failure time follows a binomial distribution. Maximum likelihood estimators of the parameters and their asymptotic variances are derived. The expected time required to complete the life test under this censoring scheme is investigated.     

Socioeconomic Status,Psychosocial Factors and Health in Urban Guyana

Abstract

This study seeks to understand the relationship between socioeconomic status (SES) and self-reported indicators of physical and mental health in an urban Third World context. The data come from a probability sample of 654 adult residents of Georgetown, Guyana. There is a significant inverse association between formal education and morbidity for four of the six measures of health status. In this research the extent to which self-concept, health behaviors, stress and social ties are linked to health status and SES, and can explain SES differences in health status is explored. Psychosocial factors, especially the self-concept measures (self-esteem and mastery) play a moderate role in accounting for educational differences in health status.     

GAMMA-BASED CLUSTERING VIA ORDERED MEANS WITH APPLICATION TO GENE-EXPRESSION ANALYSIS

Discrete mixture models provide a well-known basis for effective clustering algorithms, although technical challenges have limited their scope. In the context of gene-expression data analysis, a model is presented that mixes over a finite catalog of structures, each one representing equality and inequality constraints among latent expected values. Computations depend on the probability that independent gamma-distributed variables attain each of their possible orderings. Each ordering event is equivalent to an event in independent negative-binomial random variables, and this finding guides a dynamic-programming calculation. The structuring of mixture-model components according to constraints among latent means leads to strict concavity of the mixture log likelihood. In addition to its beneficial numerical properties, the clustering method shows promising results in an empirical study.     

Expectation–maximization algorithm for system-based lifetime data with unknown system structure

AStA Advances in Statistical Analysis - In science and engineering, we are often interested in learning about the lifetime characteristics of the system as well as those of the components that made...     

Optimal Bootstrap Sample Size in Construction of Percentile Confidence Bounds

In traditional bootstrap applications the size of a bootstrap sample equals the parent sample size, n say. Recent studies have shown that using a bootstrap sample size different from n may sometimes provide a more satisfactory solution. In this paper we apply the latter approach to correct for coverage error in construction of bootstrap confidence bounds. We show that the coverage error of a bootstrap percentile method confidence bound, which is of order O ( n ^−2/2) typically, can be reduced to O ( n ⁻¹) by use of an optimal bootstrap sample size. A simulation study is conducted to illustrate our findings, which also suggest that the new method yields intervals of shorter length and greater stability compared to competitors of similar coverage accuracy.     

Determinants of fertility control in Korea

The objective of this study is to examine the socioeconomic and intervening determinants of fertility control in Korea. The conceptual framework applied here is based on the synthesis framework of fertility control developed by Easterlin and Crimmins. The data came from the 1974 Korean National Family Survey, which was conducted as part of the World Fertility Survey. The study focuses on the relative importance of the socioeconomic factors and intervening variables in the determination of fertility control. The most interesting finding is that there are only small differentials in fertility control by socioeconomic factors. The analysis emphasizes the importance of examining the determinants of fertility control in terms of the intervening variables, which include the components of natural fertility, desired family size, and costs of fertility control. These intervening variables provide general support for the theoretical predictions. Moreover, most of the coefficients for these variables are statistically significant at the .05 level. The analysis also shows that motivation for fertility control is an important factor in determining use of fertility control.     

Family structure and educational attainment of children: effects of remarriage

This study explores how remarriage alters the effect of living in a female-headed family on children's educational attainment. The analysis is based upon data from a mother/child extract taken from the 1984 March/April Match file of the Current Population Survey. Ordinary least squares regression analysis and logit analysis are used. The results are mixed. While remarriage mitigates the negative effects of single-parent family living on years of school completed and the probability of high school graduation, it exacerbates these effects on the probability of entering college by ages 18–20 years, especially for boys. Thus, while remarriage increases income and reduces time pressures compared to single-parent family living, the presence of a stepfather appears to complicate the college entrance decision.This research is based upon the Ph. D. thesis of Seung Sin Chung, submitted to the School of Human Resources and Family Studies at the University of Illinois at Urbana-Champaign. We are grateful to John W. Graham for considerable effort in preparation of the data extract for this research as well as for comments, to Sara McLanahan for useful discussion, to John Boyd for excellent programming assistance, and to Se-jeong Yang and Yang-Suk Kim for able research assistance. This research was supported in part by NIH Grant # HD19350.     

Aggressive and Prosocial Peer Group Functioning: Effects on Children's Social,School, and Psychological Adjustment

This study examined the effects of aggressive and prosocial contexts of peer groups on children's socioemotional and school adjustment. Data on informal peer groups, social functioning, and different aspects of adjustment were collected from multiple sources in a sample of elementary school children (149 boys, 181 girls; M age = 10 years). Multilevel analyses indicated that group aggressive and prosocial orientations made direct contributions to children's social, school, and psychological functioning. Group contexts also moderated the individual‐level relations between social behavior and self‐perceptions; prosocial behavior was associated with social or scholastic self‐perceptions more evidently in low prosocial and high aggressive groups. The results suggest that the peer group is an important context for children's performance and adjustment in various domains.     

Risk‐Based Probabilistic Approach to Assess the Impact of False Mussel Invasions on Farmed Hard Clams

The purpose of this article is to provide a risk‐based predictive model to assess the impact of false mussel Mytilopsis sallei invasions on hard clam Meretrix lusoria farms in the southwestern region of Taiwan. The actual spread of invasive false mussel was predicted by using analytical models based on advection‐diffusion and gravity models. The proportion of hard clam colonized and infestation by false mussel were used to characterize risk estimates. A mortality model was parameterized to assess hard clam mortality risk characterized by false mussel density and infestation intensity. The published data were reanalyzed to parameterize a predictive threshold model described by a cumulative Weibull distribution function that can be used to estimate the exceeding thresholds of proportion of hard clam colonized and infestation. Results indicated that the infestation thresholds were 2–17 ind clam^?1 for adult hard clams, whereas 4 ind clam^?1 for nursery hard clams. The average colonization thresholds were estimated to be 81–89% for cultivated and nursery hard clam farms, respectively. Our results indicated that false mussel density and infestation, which caused 50% hard clam mortality, were estimated to be 2,812 ind m^?2 and 31 ind clam^?1, respectively. This study further indicated that hard clam farms that are close to the coastal area have at least 50% probability for 43% mortality caused by infestation. This study highlighted that a probabilistic risk‐based framework characterized by probability distributions and risk curves is an effective representation of scientific assessments for farmed hard clam in response to the nonnative false mussel invasion.