A note on information loss in analyzing a mixture model of count data

In this note we consider estimation of a mixture model of count data which is composed of two discrete random variables. Conditional and unconditional estimation procedures are given for estimating the unknown parameter(s) of interest using the likelihood function. Asymptotic relative efficiencies are given to examine the amount of information loss in using the two estimation procedures. Specifically, we study the change in asymptotic relative efficiency, if any, in different parameter settings.     

Are college students health literate?

Abstract

Objective: To examine the health literacy of college students. Participants: A convenience sample of 245 graduate and undergraduate college students. Methods: During February–April of 2018 participants completed the Short Test of Functional Health Literacy which assessed literacy on two passages describing a thyroid scan, and basic healthcare insurance information. Results: Most college students displayed adequate health literacy (99.2%). The ANOVA analyses revealed college classification was the most significant predictor, followed by ethnicity, sex, and primary language. Age was significantly related to health literacy, when holding college classification constant. Interestingly, college major, healthcare work experience, or having health care credentials were not predictors of health literacy. Conclusion: This group of college students had adequate health literacy skills. However, the results of this study revealed demographic disparities that suggest further study.     

Linking dichotomous segregation with multi-group segregation: Weighted segregation ratios in selected U.S. metropolitan areas

The U.S. residential landscape is increasingly multi-racial and multi-ethnic, giving rise to the question of how to compare dichotomous segregation among multiple groups living in the same area. To address the problem in the existing dichotomous approach, which offers no common basis for comparing dichotomous segregation among multiple groups, this paper develops a weighted segregation ratio approach based on Theil’s segregation index and its additive decomposability. This approach can be used to bridge information obtained from dichotomous segregation between specific groups (such as black-white and black-Hispanic), and dichotomous segregation between group and non-group (such as white-non-white and black-non-black) in previous studies. We apply both dichotomous and weighted segregation ratio approaches to 1990 and 2000 U.S. census data. Results are interpreted for five selected metropolitan areas as well as for the weighted national average. This new approach yields distinctive findings that portray the complicated process of residential segregation, including the increasing significance of Hispanic segregation and Asian segregation in the decade from 1990 to 2000.     

Out of Sight,Out of Mind? Patterns of Transnational Contact Among Chinese and Indian Immigrants in Toronto1

There has been considerable discussion in recent decades about the integration patterns of new immigrants. Recognizing advancements in technology and the increased economic integration of countries, some researchers have suggested that the emerging integration trend for immigrants is the transnational pattern, whereby immigrants maintain contact with the home countries. To advance the discussion, this study focuses on general transnational contact, a basic form of transnational activity. The study draws from recently collected large‐scale survey data to explore the patterns of transnational contact within two recent immigrant groups, Asian Indians and Chinese, in Toronto. Our findings show that only a small percentage of immigrants maintain intensive and extensive transnational contact. As well, our findings are less consistent with the transnational perspective than with the assimilation perspective on the effects of socioeconomic background on transnational contacts.     

Borrowing Information across Populations in Estimating Positive and Negative Predictive Values

A marker's capacity to predict risk of a disease depends on disease prevalence in the target population and its classification accuracy, i.e. its ability to discriminate diseased subjects from non-diseased subjects. The latter is often considered an intrinsic property of the marker; it is independent of disease prevalence and hence more likely to be similar across populations than risk prediction measures. In this paper, we are interested in evaluating the population-specific performance of a risk prediction marker in terms of positive predictive value (PPV) and negative predictive value (NPV) at given thresholds, when samples are available from the target population as well as from another population. A default strategy is to estimate PPV and NPV using samples from the target population only. However, when the marker's classification accuracy as characterized by a specific point on the receiver operating characteristics (ROC) curve is similar across populations, borrowing information across populations allows increased efficiency in estimating PPV and NPV. We develop estimators that optimally combine information across populations. We apply this methodology to a cross-sectional study where we evaluate PCA3 as a risk prediction marker for prostate cancer among subjects with or without previous negative biopsy.