Search

The deployment of statistical models—such as those used in item response theory—necessitates the use of indices that are informative about the degree to which a given model is appropriate for a specific data context. We introduce the InterModel Vigorish (IMV) as an index that can be used to quantify accuracy for models of dichotomous item responses based on the improvement across two sets of predictions (i.e., predictions from two item response models or predictions from a single such model relative to prediction based on the mean). This index has a range of desirable features: It can be used for the comparison of non-nested models and its values are highly portable and generalizable. We use this fact to compare predictive performance across a variety of simulated data contexts and also demonstrate qualitative differences in behavior between the IMV and other common indices (e.g., the AIC and RMSEA). We also illustrate the utility of the IMV in empirical applications with data from 89 dichotomous item response datasets. These empirical applications help illustrate how the IMV can be used in practice and substantiate our claims regarding various aspects of model performance. These findings indicate that the IMV may be a useful indicator in psychometrics, especially as it allows for easy comparison of predictions across a variety of contexts. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is increasingly being used in the social sciences to find patterns and make predictions. The use of ML methods has grown significantly in recent years, with a fourfold increase since 2017. This trend can be attributed to a shift in the appreciation of predictive algorithms, the development of ML training programs, and the availability of large datasets and computing power. However, it is important to address ethical concerns and ensure fairness and unbiasedness in the algorithms used. The use of ML in the social sciences has the potential to bring about significant changes in the research process. [Extracted from the article]

Background: Variations in the age patterns and magnitudes of excess deaths, as well as differences in population sizes and age structures, make cross-national comparisons of the cumulative mortality impacts of the COVID-19 pandemic challenging. Life expectancy is a widely used indicator that provides a clear and cross-nationally comparable picture of the population-level impacts of the pandemic on mortality.Methods: Life tables by sex were calculated for 29 countries, including most European countries, Chile and the USA, for 2015-2020. Life expectancy at birth and at age 60 years for 2020 were contextualized against recent trends between 2015 and 2019. Using decomposition techniques, we examined which specific age groups contributed to reductions in life expectancy in 2020 and to what extent reductions were attributable to official COVID-19 deaths.Results: Life expectancy at birth declined from 2019 to 2020 in 27 out of 29 countries. Males in the USA and Lithuania experienced the largest losses in life expectancy at birth during 2020 (2.2 and 1.7 years, respectively), but reductions of more than an entire year were documented in 11 countries for males and 8 among females. Reductions were mostly attributable to increased mortality above age 60 years and to official COVID-19 deaths.Conclusions: The COVID-19 pandemic triggered significant mortality increases in 2020 of a magnitude not witnessed since World War II in Western Europe or the breakup of the Soviet Union in Eastern Europe. Females from 15 countries and males from 10 ended up with lower life expectancy at birth in 2020 than in 2015. [ABSTRACT FROM AUTHOR]

Population Studies advances research on fertility, mortality, family, migration, methods, policy, and beyond, yet it lacks a recent, rigorous review. We examine all papers published between 1947 and 2020 (N = 1,901) and their authors, using natural language processing, social network analysis, and mixed methods that combine unsupervised machine learning with qualitative coding. After providing a brief history, we map the evolution in authorship and papers towards shorter, multi-authored papers, also finding that females comprise 33.5 per cent of authorship across the period under study, with varied sex ratios across topics. Most papers examine fertility, mortality, and family, studying groups and change, but topics vary over time. Children are rarely studied, and research on women focuses on family planning, fertility decline, and unions, whereas key domains for research on men are migration, historical demography (war, famine), and employment. Research on Africa and Asia focuses on family planning, with work on fertility decline concentrated on North America and Europe, consistent with theories of demographic transition. Our resulting discussion identifies future directions for demographic research. [ABSTRACT FROM AUTHOR]

Population Studies advances research on fertility, mortality, family, migration, methods, policy, and beyond, yet it lacks a recent, rigorous review. We examine all papers published between 1947 and 2020 (N = 1,901) and their authors, using natural language processing, social network analysis, and mixed methods that combine unsupervised machine learning with qualitative coding. After providing a brief history, we map the evolution in authorship and papers towards shorter, multi-authored papers, also finding that females comprise 33.5 per cent of authorship across the period under study, with varied sex ratios across topics. Most papers examine fertility, mortality, and family, studying groups and change, but topics vary over time. Children are rarely studied, and research on women focuses on family planning, fertility decline, and unions, whereas key domains for research on men are migration, historical demography (war, famine), and employment. Research on Africa and Asia focuses on family planning, with work on fertility decline concentrated on North America and Europe, consistent with theories of demographic transition. Our resulting discussion identifies future directions for demographic research. [ABSTRACT FROM AUTHOR]

Summary: We mechanize some of the richest yet significantly under‐utilized data resources within developed, ‘Open Data' economies. We show how it is possible to scrape, parse, clean and merge tens of thousands of disaggregated public payments datasets in an attempt to bridge the methodological gap between newly available data from the administrative sphere and applications in empirical social science research. We outline techniques to unambiguously link records to various freely available institutional registers. In particular, we offer guidance on overcoming the substantial challenges of heterogeneous provision and administrative recording errors in the absence of Uniform Resource Identifiers, namely in the form of an approximate, domain‐specific ‘record‐linkage' type matching algorithm. As an illuminating example, we construct a cleaned database of 24,581,192 local government payments subject to the Local Transparency Codes which total £169.87bn in value. We overcome various challenges in a detailed examination of the procurement of services by local government from the voluntary sector: an important contemporary issue due to the rise of the ‘Big Society’ political ideology of the early 21st century. Finally, we motivate future work in this area and discuss potential international applications and practical advancements. [ABSTRACT FROM AUTHOR]

We draw on 120 years of biographical data (N = 120,764) contained within Who’s Who—a unique catalogue of the British elite—to explore the changing relationship between elite schools and elite recruitment. We find that the propulsive power of Britain’s public schools has diminished significantly over time. This is driven in part by the wane of military and religious elites, and the rise of women in the labor force. However, the most dramatic declines followed key educational reforms that increased access to the credentials needed to access elite trajectories, while also standardizing and differentiating them. Notwithstanding these changes, public schools remain extraordinarily powerful channels of elite formation. Even today, the alumni of the nine Clarendon schools are 94 times more likely to reach the British elite than are those who attended any other school. Alumni of elite schools also retain a striking capacity to enter the elite even without passing through other prestigious institutions, such as Oxford, Cambridge, or private members clubs. Our analysis not only points to the dogged persistence of the “old boy,” but also underlines the theoretical importance of reviving and refining the study of elite recruitment. [ABSTRACT FROM AUTHOR]

This is a short paper which details the user-written StatFact add-in released by IHS on November 10, 2014. The first section introduces and explains the motivation behind the development of the add-in, the second section details the econometric procedures undertaken and the third provides guidance on the use of the software. The fourth section outlines two empirical examples, and the fifth suggests possible implementations and further developments. [ABSTRACT FROM AUTHOR]

This scientometric review of genome-wide association studies (GWAS) from 2005 to 2018 (3639 studies; 3508 traits) reveals extraordinary increases in sample sizes, rates of discovery and traits studied. A longitudinal examination shows fluctuating ancestral diversity, still predominantly European Ancestry (88% in 2017) with 72% of discoveries from participants recruited from three countries (US, UK, Iceland). US agencies, primarily NIH, fund 85% and women are less often senior authors. We generate a unique GWAS H-Index and reveal a tight social network of prominent authors and frequently used data sets. We conclude with 10 evidence-based policy recommendations for scientists, research bodies, funders, and editors. Melinda Mills and Charles Rahal discuss genome-wide association studies published in the last 13 years, finding increases in sample sizes, rates of discovery, and traits studied over time. They discuss limitations, including sample diversity, and make recommendations for scientists and funding bodies. [ABSTRACT FROM AUTHOR]