Label‐ and Level‐Invariant Graphical Log‐Linear Models

We introduce two types of graphical log‐linear models: label‐ and level‐invariant models for triangle‐free graphs. These models generalise symmetry concepts in graphical log‐linear models and provide a tool with which to model symmetry in the discrete case. A label‐invariant model is category‐invariant and is preserved after permuting some of the vertices according to transformations that maintain the graph, whereas a level‐invariant model equates expected frequencies according to a given set of permutations. These new models can both be seen as instances of a new type of graphical log‐linear model termed the restricted graphical log‐linear model, or RGLL, in which equality restrictions on subsets of main effects and first‐order interactions are imposed. Their likelihood equations and graphical representation can be obtained from those derived for the RGLL models.     

Do immigrants screened for skills do better than family reunification immigrants?

"It is sometimes thought that immigrants [to the United States] who are screened for occupational skills are likely to become more productive Americans than immigrants who gain admission on the basis of family ties to native-born U.S. citizens or to previous immigrants. However, the expected differential may be small or nonexistent because: 1) kinship immigrants have access to family networks; 2) whereas employers may screen for short-term productivity, family members may screen for long-term productivity; and 3) native-born U.S citizens who sponsor spouses may be particularly adept at screening for long-term success. Longitudinal data on the 1977 immigrant cohort is used to compare initial and longer-term occupational outcomes among employment and kinship immigrants. Results indicate a narrowing of the differential, due both to higher rates of occupational downgrading among employment immigrants and of occupational upgrading among kinship immigrants."     

DERIVING IMPLICATIONS OF COMPARISON THEORY FOR DEMOGRAPHIC PHENOMENA:

This article describes the use of comparison theory to generate testable implications about demographic phenomena, and, to illustrate, derives some implications of comparison theory for migration behavior. Using two strategies for deriving predictions, known as the micromodel and macromodel strategies, we obtain a variety of theoretical results for the three types of actors in migration situations — the migrant, others in the origin country, and others in the destination country — for bilateral relations between origin and destination countries, and for the effects of the societal valued goods and the income distribution and its inequality on the differential propensity to emigrate among rich and poor.     

Inequality and deprivation within and between groups: An illustration of European union countries

This paper broadens the approach of Hey and Lambert (Q. J. Econ. 95,567–573 1980) regarding relative deprivation to the case in which individuals compare themselves with individuals belonging not only to their own group, but also to other groups. In this way, we obtain the average deprivation of a population in relation to another. This allows us to establish a correspondence between the decomposition of the Gini coefficient based on a partition of the population, and the decomposition of deprivation into two components. One quantifies deprivation within the subpopulation and the other deprivation between populations. An empirical illustration is given, based on the European Community Household Panel (ECHP). The authors acknowledge the financial support of the Spanish Government–MCYT, (SEC2001-1668) and would like to thank Jacques Silber and two anonymous referees for their suggestions.     

Estimating the emigration rates of legal immigrants using administrative and survey data: The 1971 cohort of immigrants to the United States

Based on administrative and survey data as well as data-based assumptions about the bounds on alien address reporting, this study provides estimates of the lower and upper bounds for the cumulative net emigration rates, by country and area of origin, of the FY1971 cohort of legal immigrants to the United States as of January 1979. The merged data indicate that the cumulative net emigration rate for the entire cohort could have been as high as 50 percent. Canadian emigration was probably between 51 and 55 percent. Emigration rates for legal immigrants from Central America, the Caribbean (excluding Cuba), and South America were at least as high as 50 percent, and could have been as high as 70 percent. Emigration rates for Koreans and Chinese could not have exceeded 22 percent over the same period.