Clustering to reduce regional heterogeneity: A spanish case-study

Statistical methods of dimension reduction and classification are used to obtain homogeneous local-area clustering with regard to the most relevant demographic parameters. The dimension reduction is conducted in two stages using Principal Component Analysis and a modified k-mean procedure is proposed to determine the final clusters. This clustering will be useful in future demographic studies at a local level, in particular to obtain forecasts of demographic rates and population projections. The region of Castile and León in Spain is used to illustrate the method. A Poisson model is used to explore the advantages of the new clustering over the more conventional classification based on provinces.     

On the Selection of Distributions for Stochastic Variables

One of the main steps in an uncertainty analysis is the selection of appropriate probability distribution functions for all stochastic variables. In this paper, criteria for such selections are reviewed, the most important among them being any a priori knowledge about the nature of a stochastic variable, and the Central Limit Theorem of probability theory applied to sums and products of stochastic variables. In applications of these criteria, it is shown that many of the popular selections, such as the uniform distribution for a poorly known variable, require far more knowledge than is actually available. However, the knowledge available is usually sufficient to make use of other, more appropriate distributions. Next, functions of stochastic variables and the selection of probability distributions for their arguments as well as the use of different methods of error propagation through these functions are discussed. From these evaluations, priorities can be assigned to determine which of the stochastic variables in a function need the most care in selecting the type of distribution and its parameters. Finally, a method is proposed to assist in the assignment of an appropriate distribution which is commensurate with the total information on a particular stochastic variable, and is based on the scientific method. Two examples are given to elucidate the method for cases of little or almost no information.     

L’art des bergers et les moutons qualifiés Les figures sociales en jeu sur le marché agricole

On the basis of meticulous chronicles kept about the making of mutton in the Barèges valley in the French Pyrenees, this sociological study of markets examines changes in the complex relations formed between economic interests and local identities in farming. In the 1970s, pressure to standardize mutton for sale on a national market tended to efface the specific characteristics of local produce from this area in particular. In the 1980s however, producers tried to resist in various ways — direct sales in 1984, a brand name strategy in 1987 — against this loss of specificity in an undifferentiated marketplace. In 1995, a label of origin (AOC) was drawn up that not only singled out and stabilized local produce but also redefined groups of actors, ranging from producers who now focus on quality produce to consumers who increasingly look like gourmets searching for “originality”. Furthermore, this certification process led to closely linking the production and sale of produce to the promotion of a redefined local identity, which we might have imagined as being threatened owing to the expansion of business rationales.     

Schools and Educational Outcomes: What Causes the “Race Gap” in Student Test Scores?*

Objective. African‐American and Hispanic students often have lower test scores than white students at all levels of education. In this article, we examine whether school factors impact racial groups differentially, helping reduce the test score gaps, and whether school policies benefit one racial group at the expense of another. Methods. The data is individual‐level data from a school district in California. Multivariate analysis (FGLS) is used to study the effect of school factors and race on test scores, after controlling for individual and school attributes. Results. School factors have a small differential effect by race on test scores. The school policies that have a positive influence on minorities' scores often involve an environment where closer attention is paid to the needs of students. Conclusion. Most school policies have a small effect on test scores, impacting all racial groups in a similar manner, without redistributing benefits across groups.     

The inclusion of minority groups in clinical trials: problems of under representation and under reporting of data

Objective: To evaluate the representation of minority groups in randomized control trials (RCTs), and the frequency with which this information is reported. Study Design: Reviewers collected data on the racial/ethnic composition of study samples from all RCTs published in six leading medical journals in 1999. Results: Of the 280 RCTs, most (204, 71.3%) provided no information on the race/ethnicity of participants. Of the 89 U.S.-based RCTs, 50 (56.1%) reported their minority distribution. Relative to other trials, those funded by the National Institute of Health (NIH) (n = 52) were more likely to report race/ethnicity data (55.8% vs. 23.7%; x2 = 20.9, p <_0.001) and to include nonwhite participants (13.5 % vs. 12.5%; x2=22.7, p<_0.001). Conclusion: Minority groups are currently under-represented in clinical trials. Information on the race and ethnicity of clinical trial participants is currently underreported in six leading medical journals. Reporting of minority group information was significantly better only in NIH funded trials, which also were more likely to include nonwhite participants. This suggests that mandatory reporting policies may have a positive effect on both reporting and representation.     

The reasonable man — a social choice approach

Most legal systems rely heavily on the notion of the reasonable man. Here an attempt is made to analyze the reasonable man in a social choice model. The main argument is that if the reasonable man satisfies a certain set of axioms, he essentially coincides with one of the individuals, both in terms of his preferences and in terms of his expectations.     

Estimation of covariance functions by a fully data-driven model selection procedure and its application to Kriging spatial interpolation of real rainfall data

In this paper, we propose a data-driven model selection approach for the nonparametric estimation of covariance functions under very general moments assumptions on the stochastic process. Observing i.i.d replications of the process at fixed observation points, we select the best estimator among a set of candidates using a penalized least squares estimation procedure with a fully data-driven penalty function, extending the work in Bigot et al. (Electron J Stat 4:822–855, 2010). We then provide a practical application of this estimate for a Kriging interpolation procedure to forecast rainfall data.     

The Importance of Early Childhood Poverty

Most poor children achieve less, exhibit more problem behaviors and are less healthy than children reared in more affluent families. We look beyond correlations such as these to a recent set of studies that attempt to assess the causal impact of childhood poverty on adult well-being. We pay particular attention to the potentially harmful effects of poverty early in childhood on adult labor market success (as measured by earnings), but also show results for other outcomes, including out-of-wedlock childbearing, criminal arrests and health status. Evidence suggests that early poverty has substantial detrimental effects on adult earnings and work hours, but on neither general adult health nor such behavioral outcomes as out-of-wedlock childbearing and arrests. We discuss implications for indicators tracking child well-being as well as policies designed to promote the well-being of children.     

Stochastic Algorithms,Symmetric Markov Perfect Equilibrium,and the ‘curse’ of Dimensionality

This paper introduces a stochastic algorithm for computing symmetric Markov perfect equilibria. The algorithm computes equilibrium policy and value functions, and generates a transition kernel for the (stochastic) evolution of the state of the system. It has two features that together imply that it need not be subject to the curse of dimensionality. First, the integral that determines continuation values is never calculated; rather it is approximated by a simple average of returns from past outcomes of the algorithm, an approximation whose computational burden is not tied to the dimension of the state space. Second, iterations of the algorithm update value and policy functions at a single (rather than at all possible) points in the state space. Random draws from a distribution set by the updated policies determine the location of the next iteration's updates. This selection only repeatedly hits the recurrent class of points, a subset whose cardinality is not directly tied to that of the state space. Numerical results for industrial organization problems show that our algorithm can increase speed and decrease memory requirements by several orders of magnitude.