Explore the vast range of titles available.

Promoting birth certification is central to achieving legal identity for all - target 16.9 of the 2030 Sustainable Development Goals. Nigeria is not on track to achieve this goal with its low coverage of birth certification (BC). This study is aimed at identifying patterns of BC and its associated individual- and community-level factors, using pooled cross-sectional data from three rounds (2008, 2013, and 2018) of the nationally representative Nigerian Demographic and Health Survey. A weighted sample of 66,630 children aged 0–4 years was included, and a two-level multilevel logistic model which accommodates the hierarchical nature of the data was employed. Of the total sample, 17.1% [95% CI: 16.3–17.9] were reported to be certified. Zamfara state (2.3, 95% CI: 0.93–3.73) and the Federal Capital Territory (36.24, 95% CI: 31.16–41.31) reported the lowest and the highest BC rates. Children with an SBA [AOR = 1.283, 95% CI: 1.164–1.413] and with at least one vaccination [AOR = 1.494, 95% CI: 1.328–1.681] had higher odds of BC. The AOR for mothers with at least one prenatal visit was 1.468 [95% CI: 1.271–1.695], and those aged 30–34 years at the time of birth [AOR = 1.479, 95% CI: 1.236–1.772] had the highest odds. Further, the odds of BC increased the most for mothers [AOR = 1.559, 95% CI: 1.329–1.829] and fathers [AOR = 1.394, 95% CI: 1.211–1.605] who were tertiary-educated. In addition, children in middle-income [AOR = 1.430, 95% CI: 1.197–1.707] or rich wealth HHs [AOR = 1.776, 95% CI: 1.455–2.169] or those whose families had bank accounts [AOR = 1.315, 95% CI: 1.187–1.456] had higher odds. Living in non-poor and within close proximity to a registration center (RC) act as protective factors for BC, while living in poor communities [AOR = 0.613, 95% CI: 0.486–0.774] and more than 10kms from an RC reduce the odds of BC [AOR = 0.466, 95% CI: 0.377–0.576]. The study identified several protective and risk factors which policymakers can adopt as strategic areas for universal birth certification. National and sub-national programs should integrate non-formal institutions as well as target child and maternal utilization of healthcare services to promote BC in Nigeria.

Purpose Many studies in medical research are currently based on large-scale health surveys. Data collected in these surveys are usually obtained by following complex sampling designs, which include techniques such as stratification and clustering. Thus, special care should be taken with this kind of data, given that traditional statistical techniques are usually not valid in this context. In this study, we focus on the estimation of the discrimination ability of logistic regression models by means of the area under the receiver operating characteristic (ROC) curve (AUC). An AUC estimator which accounts for complex sampling designs has recently been proposed. The purpose of this study is to compare the performance of traditional and new design-based AUC estimators to estimate the AUC of logistic regression models fitted to complex sampling-design health data. Methods A simulation study has been carried out to compare the performance of traditional and design-based AUC estimators when working with complex survey data. For this purpose, the population of COVID-19 patients in the Basque Country has been considered. This population has been sampled several times following different sampling designs, a logistic regression model has been fitted to each of these samples, and the AUC has been estimated using traditional and design-based estimators. Those estimates have been compared to the true population AUC. Results While the design-based AUC estimator offers unbiased results, the traditional AUC estimator may be biased depending on the scenario. Both the sampling design and the variables considered in this design have an effect on the performance of those estimators. In particular, the type of design affects the variability of both estimators, being larger when clustering is involved. In addition, the stronger the relationship between design variables and outcome, the more biased results offers the traditional AUC estimator. Conclusion The use of the design-based AUC estimator is recommended over the traditional one when working with complex survey data in order to avoid biased AUC estimates.

This paper presents the R Analyzer for Large-Scale Assessments (RALSA), a newly developed R package for analyzing data from studies using complex sampling and assessment designs. Such studies are, for example, the IEA’s Trends in International Mathematics and Science Study and the OECD’s Programme for International Student Assessment. The package covers all cycles from a broad range of studies. The paper presents the architecture of the package, the overall workflow and illustrates some basic analyses using it. The package is open-source and free of charge. Other software packages for analyzing large-scale assessment data exist, some of them are proprietary, others are open-source. However, RALSA is the first comprehensive R package, designed for the user experience and has some distinctive features. One innovation is that the package can convert SPSS data from large scale assessments into native R data sets. It can also do so for PISA data from cycles prior to 2015, where the data is provided in tab-delimited text files along with SPSS control syntax files. Another feature is the availability of a graphical user interface, which is also written in R and operates in any operating system where a full copy of R can be installed. The output from any analysis function is written into an MS Excel workbook with multiple sheets for the estimates, model statistics, analysis information and the calling syntax itself for reproducing the analysis in future. The flexible design of RALSA allows for the quick addition of new studies, analysis types and features to the existing ones.

Introduction Universal access to handwashing facilities with soap and water (HSW) at home forms a core mandate of SDG 6.2, yet globally it continues to stand as a major unfinished priority in realizing equitable sanitation and hygiene for all. Objectives Although recent evidence indicates that India has made rapid progress in the proportion of households reporting a home HSW, understanding what hinders the achievement of universal coverage remains critical. The current study pursues two objectives: first, it examines and estimates the extent to which the socioeconomic and demographic inequalities are shaping the HSW prevalence. Second, using decomposition analysis, it seeks to estimate the contributions of each of these structural inequalities to the overall shortfall in universal coverage for remedial policy interventions. Data and methods The present study is based on the nationally representative household-level data from the Multiple Indicator Survey (MIS) 2020-21 in India. Analyses of total and differential prevalence in HSW practices among various socioeconomic and demographic subpopulations were carried out using design weighted Horvitz-Thompson and non-linear estimators. Binary logistic regression-based generalized concentration-index decomposition analysis was carried out to assess the potential socio-economic and demographic contributors to inequality and further the percentage contributions of these factors were estimated. Results The study has revealed a stark disparity in rural (76%) and urban (92.1%) basic HSW facilities. Prevalence of HSW had increased significantly with the UMPCE quintile class, level of education of the household head ( p  = 0.000), upper-caste social groups, access to improved water sources, and exclusive household toilets. The results of the adjusted logistic regression validate these findings. Household’s wealth index was responsible for about 35% of the overall inequality in access to HSW, followed by the educational level of the household head (22%), the household’s exclusive access to a toilet (21%), and social groups (6%). Conclusion Despite significant gains, large socio-economic and demographic disparities still impede universal household access to HSW in India. Bridging this gap requires equity-focused policies that prioritize the poorest households, strengthen rural infrastructure, promote universal education, and integrate inclusive hygiene promotion with sanitation programs for the marginalized groups to realize SDG 6.2.

Multi-level models provide a convenient framework for analyzing data from survey samples with hierarchical structures. Inferential procedures that take account of survey design features are well established for single-level (or marginal) models. However, methods that are valid for general multi-level models are somewhat limited. This paper presents a unified method for two-level models, based on a weighted composite likelihood approach, that takes account of design features and provides valid inferences even for small sample sizes within level 2 units. The proposed method has broad applicability and is straightforward to implement. Empirical studies have demonstrated that the method performs well in estimating the model parameters. Moreover, this research has an important implication: it provides a particular scenario to showcase the unique merit of the composite likelihood method where the likelihood method would not work.

Background: Allergic diseases, such as allergic rhinitis, eczema, and asthma, are prevalent among adolescents and are associated with various health concerns, including poor sleep quality and mental health problems. Although previous research has investigated the general association between allergic conditions and sleep disturbances, few studies have examined how allergic diseases relate to sleep duration. Methods: We performed secondary analysis of the data obtained from the 19th Korea Youth Risk Behavior Survey (2023), which included 52,880 middle and high school students. Data was analyzed using complex sample design techniques, descriptive statistics, t-tests, and analyses of variance and covariance conducted to explore associations between allergic diseases and sleep duration on weekdays. Covariates included sex, school type, academic performance, socioeconomic status, and residential type. Results: The average weekday sleep duration among adolescents was 6.2 h, which was significantly shorter than that recommended by the U.S. Centers of Disease Control and Prevention (8–10 h). Among allergic conditions, allergic rhinitis was significantly associated with reduced sleep duration (p = 0.001), unlike asthma (p = 0.119) and eczema (p = 0.586). Additional differences in sleep duration were observed by sex, academic performance, socioeconomic status, and living arrangements. Conclusions: Managing allergic rhinitis may be crucial to promoting adequate sleep during adolescence. Furthermore, future research should incorporate physiological indicators to assess sleep quality, as self-reported measures may not capture sleep disturbances such as night-time awakenings. These findings can inform the development of integrated health strategies to enhance physical and psychological well-being of adolescents.

Background The current public health research agenda was to identify the means to reduce oral health inequalities internationally. The objectives of this study were to provide evidence of inequality in unmet dental needs and to find influencing factors attributable to those among South Korean adults. Methods Pooled cross-sectional data from the fourth Korean National Health and Nutrition Examination Survey (2007–2009) on 17,141 Korean adults were used. Demographic factors (sex, age, and marital status), socioeconomic factors (education level, employment status, and income level), need factors (normative dental needs and self-perceived oral health status), and oral health-related factors (the number of decayed teeth, the presence of periodontitis, and the number of missing teeth) were included. Multiple logistic regression analysis was performed. Results Of South Korean adults, 43.9% had perceived unmet dental needs, with the most common reason being financial difficulties. The disparities in unmet dental care needs were strongly associated with income level, normative treatment needs, and self-perceived oral health status. The low-income group, people with normative dental treatment needs, and those with perceived poor oral health status were more likely to have unmet dental needs. There was considerable inequality in unmet dental care needs due to economic reasons according to such socioeconomic factors as income and education level. Conclusions Public health policies with the expansion of dental insurance coverage are needed to reduce inequalities in unmet dental care needs and improve the accessibility of dental care services to vulnerable groups who are experiencing unmet dental care needs due to socioeconomic factors despite having normative and self-perceived needs for dental treatment.

Misclassifications in binary responses have long been a common problem in medical and health surveys. One way to handle misclassifications in clustered or longitudinal data is to incorporate the misclassification model through the generalized estimating equation (GEE) approach. However, existing methods are developed under a non-survey setting and cannot be used directly for complex survey data. We propose a pseudo-GEE method for the analysis of binary survey responses with misclassifications. We focus on cluster sampling and develop analysis strategies for analyzing binary survey responses with different forms of additional information for the misclassification process. The proposed methodology has several attractive features, including simultaneous inferences for both the response model and the association parameters. Finite sample performance of the proposed estimators is evaluated through simulation studies and an application using a real dataset from the Canadian Longitudinal Study on Aging. Les mauvaises classifications pour une variable réponse binaire donnée constituent un problème commun dans les enquêtes médicales. En présence de données longitudinales ou en grappe, une façon de traiter cette problématique consiste à incorporer un modèle de mauvaise classification à une approche par équations d’estimation généralisées (EEG). Les méthodes existantes n’ont toutefois pas été conçues pour des données d’enquêtes et ne peuvent donc pas être utilisées directement pour de telles données. Les auteurs proposent une méthode pseudo-EEG pour l’analyse de réponses binaires dans les enquêtes comportant de la mauvaise classification. Ils se concentrent sur l’échantillonnage par grappe et développent des stratégies pour analyser les réponses binaires en exploitant différentes formes d’information additionnelle à propos du processus de mauvaise classification. La méthodologie proposée comporte de nombreuses caractéristiques attrayantes, notamment la capacité d’inférer simultanément le modèle de réponse et les paramètres d’association. Les auteurs évaluent les performances de leur approche sur des échantillons finis par des études de simulation et une application à des données réelles de l’Étude longitudinale canadienne sur le vieillissement (ÉLCV).

International large-scale assessments (ILSAs) provide invaluable information for researchers and policy makers. Analysis of their data, however, requires methods that go beyond the usual analysis techniques assuming simple random sampling. Several software packages that serve this purpose are available. One such is the R Analyzer for Large-Scale Assessments (RALSA), a newly developed R package. The package can work with data from a large number of ILSAs. It was designed for user experience and is suitable for analysts who lack technical expertise and/or familiarity with the R programming language and statistical software. This paper presents the technical aspects of RALSA—the overall design and structure of the package, its internal organization, and the structure of the analysis and data preparation functions. The use of the data.table package for memory efficiency, speed, and embedded computations is explained through examples. The central aspect of the paper is the utilization of code reuse practices to the achieve consistency, efficiency, and safety of the computations performed by the analysis functions of the package. The comprehensive output system to produce multi-sheet MS Excel workbooks is presented and its workflow explained. The paper also explains how the graphical user interface is constructed and how it is linked to the data preparation and analysis functions available in the package.