Estimating network properties from snowball sampled data

This article addresses the estimation of topological network parameters from data obtained with a snowball sampling design. An approximate expression for the probability of a vertex to be included in the sample is derived. Based on this sampling distribution, estimators for the mean degree, the degree correlation, and the clustering coefficient are proposed. The performance of these estimators and their sensitivity with respect to the response rate are validated through Monte Carlo simulations on several test networks. Our approach has no complex computational requirements and is straightforward to apply to real-world survey data. In a snowball sample design, each respondent is typically enquired only once. Different from the widely used estimator for Respondent-Driven Sampling (RDS), which assumes sampling with replacement, the proposed approach relies on sampling without replacement and is thus also applicable for large sample fractions. From the simulation experiments, we conclude that the estimation quality decreases with increasing variance of the network degree distribution. Yet, if the degree distribution is not to broad, our approach results in good estimates for the mean degree and the clustering coefficient, which, moreover, are almost independent from the response rate. The estimates for the degree correlation are of moderated quality.     

Estimating intrahousehold allocation in a collective model with household production

The purpose of this paper is to estimate the intra-family distribution of income and the individual demand for leisure and household production from Swedish cross-sectional household data. As a basis for the analysis, we use a collective model where each individual is characterized by his or her own utility function and divides total time between leisure, household production and market work. For the purpose of comparison, we also estimate a version that is consistent with a more traditional model of labor supply, the unitary model. Received: 14 April 2000/Accepted: 12 January 2001     

Trust, tenure insecurity, and land certification in rural Ethiopia

This paper assesses the impact of a land certification program in Ethiopia on the level of interpersonal and institutional trust among households in the Amhara region. The land certification program is designed to enhance land tenure security of farmers, by maintaining (egalitarian) status quo land distribution and equity concerns. The major contribution of the analysis lies in the exogenous nature of the program which addresses the endogeneity problems that characterize related studies, assessing the impact of policy related variables on trust. The effects of the land certification program on trust are identified both by the difference-in-difference approach and by non-parametrical analysis of average treatment effects. Overall trust is found to be enhanced by the certification program, with trust towards formal institutions being more responsive to the program than interpersonal trust. The major policy implication of the result is that trust could be invested on through policy changes regarding the economic betterment of societies.     

Studying social capital in situ: A qualitative approach

In recent years, the concept of social capital – broadly defined as co-operative networks based on regular, personal contact and trust – has been widely applied within cross-disciplinary human science research, primarily by economists, political scientists and sociologists. In this article, I argue why and how fieldwork anthropologists should fill a gap in the social capital literature by highlighting how social capital is being built in situ. I suggest that the recent inventions of “bridging” and “bonding” social capital, e.g., inclusive and exclusive types of social capital, are fruitful concepts to apply in an anthropological fieldwork setting. Thus, my case study on the relationship between local people and newcomers in the rural Danish marginal municipality of Ravnsborg seeks to reveal processes of bridging/bonding social capital building. Such a case study at the micro level has general policy implications for a cultural clash between two different groups by demonstrating the complexity of a social capital mix where bonding social capital strongly prevails. This ultimately leads to a “social trap” (Rothstein 2005), implying widespread distrust and serious social and economic costs for a whole population. Gunnar Lind Haase Svendsen is Senior Researcher, at the Institute of Rural Research and Development, Southern University of Denmark. He is the co-author, with G. T. Svendsen, of The Creation and Destruction of Social Capital: Entrepreneurship, Co-operative Movements and Institutions (Edward Elgar, Cheltenham, UK, 2004, Paperback edition, October 2005); and author of Samarbejde og konfrontation. Opbygning og nedbrydning af social kapital i de danske landdistrikter 1864–2003 [Cooperation and Confrontation. The Creation and Destruction of Social Capital in Rural Denmark 1864–2003], Ph.D. dissertation, University of Sourthern Denmark, Esbjerg, 2004: http://www.humaniora.sdu.dk/phd/dokumenter/filer/Afhandlinger-30.pdfg. Gunnar Svendsen's scholarly interests include Bourdieusian Economics (new socioeconomics), capital theory, social capital, rural civic movements, and rural discourses. He has recently finished a research project for the Danish Ministry of the Interior about the role of intangible assets (culture, networks, and historical traditions) for differences in economic performance (DEP) among four Danish local communities.     

Consequences of Family Policies on Childbearing Behavior: Effects or Artifacts?

This article argues for a more careful consideration of theoretical and methodological approaches in studies of the effects of public policies, labeled here as family policies, on childbearing behavior. We employ elements of comparative welfare‐state research, of the sociology of “constructed categories,” and of “the new institutionalism” to demonstrate that investigations into policy effects need to contextualize policies and need to reduce their complexity by focusing on “critical junctures,”“space,” and “uptake.” We argue that the effects of family policies can only be assessed properly if we study their impact on individual behavior. Event‐history models applied to individual‐level data are the state‐of‐the‐art of such an approach. We use selected empirical studies from Sweden to demonstrate that the type of approach that we advocate prevents us from drawing misleading conclusions.     

A precise estimator for the log-normal mean

The log-normal distribution is frequently encountered in applications. The uniformly minimum variance unbiased (UMVU) estimator for the log-normal mean is given explicitly by a formula found by Finney in 1941. In contrast to this the most commonly used estimator for a log-normal mean is the sample mean. This is possibly due to the complexity of the formula given by Finney. A modified maximum likelihood estimator which approximates the UMVU estimator is derived here. It is sufficiently simple to be implemented in elementary spreadsheet applications. An elementary approximate formula for the root-mean-square error of the suggested estimator and the UMVU estimator is presented. The suggested estimator is compared with the sample mean, the maximum likelihood, and the UMVU estimators by Monte Carlo simulation in terms of root-mean-square error.     

Fiducial and Posterior Sampling

The fiducial coincides with the posterior in a group model equipped with the right Haar prior. This result is generalized here. For this the underlying probability space of Kolmogorov is replaced by a σ-finite measure space and fiducial theory is presented within this frame. Examples are presented that demonstrate that this also gives good alternatives to existing Bayesian sampling methods. It is proved that the results provided here for fiducial models imply that the theory of invariant measures for groups cannot be generalized directly to loops: there exist a smooth one-dimensional loop where an invariant measure does not exist.