Kernel-based global MLE of partial linear random effects models for longitudinal data

Random effects models have been playing a critical role for modelling longitudinal data. However, there are little studies on the kernel-based maximum likelihood method for semiparametric random effects models. In this paper, based on kernel and likelihood methods, we propose a pooled global maximum likelihood method for the partial linear random effects models. The pooled global maximum likelihood method employs the local approximations of the nonparametric function at a group of grid points simultaneously, instead of one point. Gaussian quadrature is used to approximate the integration of likelihood with respect to random effects. The asymptotic properties of the proposed estimators are rigorously studied. Simulation studies are conducted to demonstrate the performance of the proposed approach. We also apply the proposed method to analyse correlated medical costs in the Medical Expenditure Panel Survey data set.     

In-home firearm access among US adolescents and the role of religious subculture: Results from a nationally representative study

Religious participation is linked to numerous positive safety outcomes for adolescents. Scant attention, however, has been paid to associations between religious participation and safety risks among adolescents. Using data from Add Health (N = 18,449), a nationally representative school-based sample of US adolescents, this study examines the relationship between adolescents' religious affiliation and easy access to firearms at home. Regression analyses adjust for complex sampling design and compare easy firearm access at home among conservative Protestant adolescents to adolescent firearm access in other religious traditions. Conservative Protestant adolescents have a substantially greater likelihood of easy access to a gun at home compared to adolescents of all other major religious traditions in the United States. Recognizing differences in adolescent firearm access between subcultural groups can help public health interventions more effectively identify and address the needs of vulnerable populations. The paper's conclusion considers suggestions for effective policy and programmatic initiatives.     

Measurement and decomposition of the Malmquist productivity index for parallel production systems

The conventional Malmquist productivity index (MPI), which ignores the internal structure of a production system when measuring changes in performance between two periods, may produce misleading results. This paper thus takes the operations of the component processes into account in investigating the MPI of parallel production systems. A relational data envelopment analysis (DEA) model is developed to measure the biennial MPIs of the system and internal processes at the same time, and it is shown that the former is a linear combination of the latter. This decomposition helps identify the processes that cause the decline in performance of the system. An example of 39 branches of a commercial bank, with deposits, sales, and services as the three major functions operating in parallel, is used to illustrate this approach.     

The determination of the least distance to the strongly efficient frontier in Data Envelopment Analysis oriented models: Modelling and computational aspects

Determining the least distance to the efficient frontier for estimating technical inefficiency, with the consequent determination of closest targets, has been one of the relevant issues in recent Data Envelopment Analysis literature. This new paradigm contrasts with traditional approaches, which yield furthest targets. In this respect, some techniques have been proposed in order to implement the new paradigm. A group of these techniques is based on identifying all the efficient faces of the polyhedral production possibility set and, therefore, is associated with the resolution of a NP-hard problem. In contrast, a second group proposes different models and particular algorithms to solve the problem avoiding the explicit identification of all these faces. These techniques have been applied more or less successfully. Nonetheless, the new paradigm is still unsatisfactory and incomplete to a certain extent. One of these challenges is that related to measuring technical inefficiency in the context of oriented models, i.e., models that aim at changing inputs or outputs but not both. In this paper, we show that existing specific techniques for determining the least distance without identifying explicitly the frontier structure for graph measures, which change inputs and outputs at the same time, do not work for oriented models. Consequently, a new methodology for satisfactorily implementing these situations is proposed. Finally, the new approach is empirically checked by using a recent PISA database consisting of 902 schools.     

A three-stage hybrid approach for weight assignment in MADM

How to determine weights for attributes is one of the key issues in multiple attribute decision making (MADM). This paper aims to investigate a new approach for determining attribute weights based on a data envelopment analysis (DEA) model without explicit inputs (DEA-WEI) and minimax reference point optimisation. This new approach first considers a set of preliminary weights and the most favourite set of weights for each alternative or decision making unit (DMU) and then aggregates these weight sets to find the best compromise weights for attributes with the interests of all DMUs taken into account fairly and simultaneously. This approach is intended to support the solution of such MADM problems as performance assessment and policy analysis where (a) the preferences of decision makers (DMs) are either unclear and partial or difficult to acquire and (b) there is a need to consider the best "will" of each DMU. Two case studies are conducted to show the property of this new proposed approach and how to use it to determine weights for attributes in practice. The first case is about the assessment of research strengths of EU-28 member countries under certain measures and the second is for analysing the performances of Chinese Project 985 universities, where the weights of the attributes need to be assigned in a fair and unbiased manner.     

How Early Life Religious Exposure Relates to the Timing of First Birth

This article examines intermediary processes explaining how religious socialization and involvement early in life are related to the timing of first births for women in the United States. The theory of conjunctural action forms the basis for hypotheses for how religious schemas and materials operate to influence birth timing. Using the National Longitudinal Survey of Youth data and event history methods, the study finds evidence for expected family size, work–family gender ideology, educational attainment and enrollment, cohabitation, and age at marriage as mediators of associations between early life religious exposure (affiliation and attendance) and the timing of nonmaritally and maritally conceived first births. These findings corroborate other research identifying the long reach of religious socialization and involvement in youth, elucidate some of the pathways for these connections, and motivate further work to understand linkages between religion and family behaviors in the United States.     

Anticipating the “Ball and Chain”? Reciprocal Associations Between Marital Expectations and Delinquency

Marriage has been identified as a mechanism that may explain decreased delinquency among young adults, but whereas marriage is increasingly delayed, crime continues to decrease across the transition to adulthood. Most adolescents and young adults expect to marry one day, and these expectations may suppress delinquency. Conversely, increased delinquency may also predict decreased marital expectations. Longitudinal data from the National Longitudinal Survey of Youth 1997 cohort (N = 7,057), a sample of youth who were aged 12 to 17 years in 1997, were used to examine the reciprocal association between an expressed expectation to marry soon and participation in delinquent behavior. Results from an autoregressive cross‐lagged structural equation model suggested that greater expectations to marry were significantly associated with less delinquent activity 1 year later. Greater delinquent activity was not significantly associated with subsequent marital expectations. Youth with the greatest expectations to marry may temper their behavior even before vows are taken.     

The Gudaga Research Program: A Case Study in Undertaking Research with an Urban Aboriginal Community

This paper presents the Gudaga Research Program as a case study describing the practice principles used to implement a successful research partnership with an urban Aboriginal community in south-western Sydney. This is one of few papers that address research issues unique to working with urban Aboriginal communities, in which the Aboriginal culture of the community is not homogenous. The authors argue that the relationships between the researchers and key community members and research participants underpin the research success. Throughout, the authors show that ongoing processes to nurture and reaffirm these relationships are important and require ongoing investment. A proposed practice framework demonstrates the relationship between knowledge and understanding of Aboriginal history and culture, the underpinning values including trust, respect, and reciprocity, and shared skills and communication. Examples of how these were built into the research are provided. These are important skills that have application beyond the research process.     

Multiple imputation for ordinal longitudinal data with monotone missing data patterns

Missing data often complicate the analysis of scientific data. Multiple imputation is a general purpose technique for analysis of datasets with missing values. The approach is applicable to a variety of missing data patterns but often complicated by some restrictions like the type of variables to be imputed and the mechanism underlying the missing data. In this paper, the authors compare the performance of two multiple imputation methods, namely fully conditional specification and multivariate normal imputation in the presence of ordinal outcomes with monotone missing data patterns. Through a simulation study and an empirical example, the authors show that the two methods are indeed comparable meaning any of the two may be used when faced with scenarios, at least, as the ones presented here.     

Estimating Box-Cox power transformation parameter via goodness-of-fit tests

Box–Cox power transformation is a commonly used methodology to transform the distribution of the data into a normal distribution. The methodology relies on a single transformation parameter. In this study, we focus on the estimation of this parameter. For this purpose, we employ seven popular goodness-of-fit tests for normality, namely Shapiro–Wilk, Anderson–Darling, Cramer-von Mises, Pearson Chi-square, Shapiro-Francia, Lilliefors and Jarque–Bera tests, together with a searching algorithm. The searching algorithm is based on finding the argument of the minimum or maximum depending on the test, i.e., maximum for the Shapiro–Wilk and Shapiro–Francia, minimum for the rest. The artificial covariate method of Dag et al. (2014) is also included for comparison purposes. Simulation studies are implemented to compare the performances of the methods. Results show that Shapiro–Wilk and the artificial covariate method are more effective than the others and Pearson Chi-square is the worst performing method. The methods are also applied to two real-life datasets. The R package AID is proposed for implementation of the aforementioned methods.