Generating Bivariate Uniform Data with a Full Range of Correlations and Connections to Bivariate Binary Data

In this article, random number generation algorithms for generating bivariate uniform data based on a known class of symmetric bivariate uniform distributions that allow the entire correlation range are given, and its previously unrecognized connection with bivariate binary data is established via matching the cumulative distribution functions.     

Resolving inconsistencies in trends in old-age disability: Report from a technical working group

In September 2002, a technical working group met to resolve previously published inconsistencies across national surveys in trends in activity limitations among the older population. The 12-person panel prepared estimates from five national data sets and investigated methodological sources of the inconsistencies among the population aged 70 and older from the early 1980s to 2001. Although the evidence was mixed for the 1980s and it is difficult to pinpoint when in the 1990s the decline began, during the mid- and late 1990s, the panel found consistent declines on the order of 1%-2.5% per year for two commonly used measures in the disability literature: difficulty with daily activities and help with daily activities. Mixed evidence was found for a third measure: the use of help or equipment with daily activities. The panel also found agreement across surveys that the proportion of older persons who receive help with bathing has declined at the same time as the proportion who use only equipment (but not personal care) to bathe has increased. In comparing findings across surveys, the panel found that the period, definition of disability, treatment of the institutionalized population, and age standardizing of results were important to consider. The implications of the findings for policy, national survey efforts, and further research are discussed.     

Effects of soccer on stock markets: The return–volatility relationship

This paper assesses the effects of domestic soccer teams’ performances against foreign rivals on stock market returns as well as on the return–volatility relationship. Data from Chile, Spain, Turkey and the United Kingdom support propositions that soccer teams results in international cups affect stock market returns and the return–volatility relationship. Evidence from Spain and the UK, soccer powerhouses, suggests that losses are associated with lower returns and higher risk aversion but evidence from Chile and Turkey, where soccer is the most important sport but teams are not as successful, reveals that wins are associated with higher returns and lower risk aversion.     

MultiOrd: An R Package for Generating Correlated Ordinal Data

In this article, operational details of an R package MultiOrd that is designed for the generation of correlated ordinal data are described, and examples of some important functions are given. The package provides a valuable and needed tool that has been lacking for generating multivariate ordinal data.     

Who Can Help People with HIV/AIDS in Africa? Governance of HIV/AIDS and Civil Society

This paper locates NGOs dealing with HIV/AIDS problems in sub-Saharan Africa into the larger governance context within which they function. This aims at a theoretical shift to assess the aspirational characteristics for the agency of NGOs that are used to legitimate contracting out implementation of internationally designed HIV/AIDS policies to these organizations. The paper interrogates the nature and impact of the governance structure on NGOs and then looks at the implications of this for HIV/AIDS. The questioning is based on a juxtaposition of the perspective of international policy fora in relation to civil society organizations with the way NGO work is perceived by the people at the receiving end of the policies. The paper suggests that as part of the international governance structure, NGOs are limited within the policy frameworks created by this structure. Furthermore, due to their organizational characteristics, NGOs lack capacity to establish sustainable long-term interventions relevant for sociocultural change as perceived by people themselves.     

A Romerian contribution to the empirics of economic growth

Mankiw, Romer, and Weil (1992) made the Solovian set up widely used to test the determinants of economic growth and the speed of convergence. In accordance with the nature of the Solow framework, almost all empirical growth studies considered technological progress constant and identical across countries and over time, and hence underemphasized its role. In this study, in order to overcome this weakness, we propose that the Mankiw, Romer, and Weil (1992) set-up should be replaced by the Solovianized Romer (1990) framework, thus allowing the role of technology to be considered in the empirical analysis. In particular, within this framework, the growth rate of technology varies across economies and over time. We estimate the convergence equation derived from Solovianized Romer model for 31 OECD countries for the period 1980–2008 by applying the system GMM approach. The empirical findings of the model support the conditional convergence hypothesis, but reveal a lower convergence rate than that predicted by the existing literature. As a policy implication, we argue that, investment in R&D and human capital are important determinants of convergence, and in cases where economies are unable to allocate sufficient resources to R&D, policy makers should ease the diffusion of technology (e.g., via FDI or trade) in order to retain a high convergence rate.     

Concurrent generation of binary and nonnormal continuous data through fifth-order power polynomials

Data collection process in most observational and experimental studies yield different types of variables, leading to the use of joint models that are capable of handling multiple data types. Evaluation of various statistical techniques that have been developed for mixed data in simulated environments requires concurrent generation of multiple variables. In this article, I present an important augmentation to a unified framework proposed in our previously published work for simultaneously generating binary and nonnormal continuous data given the marginal characteristics and correlation structure, via fifth-order power polynomials that are known to extend the area covered in the skewness-elongation plane and to provide a better approximation to the probability density function of the continuous variables. I evaluate how well the improved methodology performs in comparison to the original one, in a simulated setting with illustrations of algorithmic steps. Although the relative gains for the associational quantities are not substantial, the augmented version appears to better capture the marginal quantities that are pertinent to the higher-order moments, as indicated by very close resemblance between the specified and empirically computed quantities on average.     

PoisNor: An R package for generation of multivariate data with Poisson and normal marginals

In this article, the operational details of the R package PoisNor that is designed for simulating multivariate data with count and continuous variables with a prespecified correlation matrix are described, and examples of some important functions are given. The data-generation mechanism is a combination of the “NORmal To Anything” principle and a recently established connection between Poisson and normal correlations. The package provides a unique and useful tool that has been lacking for generating multivariate mixed data with Poisson and normal components.     

Why Do We Care About Having More than Others? Socioeconomic Determinants of Positional Concerns in Different Domains

This paper uses survey data to provide empirical evidence regarding the importance of positional concerns in different domains and their determinants. In the survey, respondents are asked to choose between a world in which they have more of a good than others and a world in which their endowment along with everyone else is greatly improved, but they have less than others. Our results lend support to the claim that positional concerns play a crucial role in the decision-making process of individuals, though they appear to be more influential in some domains than others. Moreover, empirical results point out relationships between the age, gender, education, and income level of the respondents and their positional concerns in different domains.     

On accurate and precise generation of generalized Poisson variates

This article is concerned with comparison of a few random variate generation techniques for the generalized Poisson distribution. An evaluation is conducted on the degree of proximity between the estimates for its two distributional parameters and first four moments, and the specified or computed true population values via commonly accepted accuracy and precision measures in a simulated setting.