Estimating ordered parameters by linear programming

There are many models that require the estimation of a set of ordered parameters. For example, multivariate analysis of variance often is formulated as testing for the equality of the parameters versus an ordered alternative. This problem, referred to as isotonic inference, constrained inference, or isotonic regression, has led to the development of general solutions, not often easy to apply in special models. In this expository paper, we study the special case of a separable convex quadratic programming problem for which the optimality conditions lead to a readily solved linear complementarity problem in the Lagrange multipliers, and subsequently to an equivalent linear programming problem, whose solution can be used to recover the solution of the original isotonic problem. The method can be applied to estimating ordered correlations, ordered binomial probabilities, ordered Poisson parameters, ordered exponential scale parameters, or ordered risk differences.     

Circuits of schooling: A sociological exploration of parental choice of school in social class contexts

Parental choice of school is one of the main platforms of government education policy and is the centre piece of the Parents Charter. But sociological understanding of choice and choice-making is woefully underdeveloped. This paper draws on an ESRC study of market forces in education to explore social class variations in choice of school in one specific locality. The complexity of choice-making is portrayed using data from interviews with parents and it is argued that middle-class parents are taking full advantage of ‘the market’ to sustain or re-assert their class advantages.     

Female Labor Force Participation in Urban and Rural China1

Abstract The objective of this study is to examine female labor force participation and its determinants in rural and urban China. The sociological literature has demonstrated that participation tends to increase in urban and industrialized places where women have higher levels of education and fewer children, where more workers are engaged in service pursuits, and where family structure is less traditional. With the use of data on counties and cities (N = 2,377) from the I-percent sample of the 1982 census of the People's Republic of China, it was found that female labor force participation is likely to rise in areas with increased agricultural employment, educational levels, proportion of female-headed households, and higher male-to-female sex ratios. Both the size of the service sector and the fertility rate had negligible effects on female labor force participation. Although, on average, rural places have slightly higher levels of female labor force participation, when other variables are controlled, urban places have a higher rate of female participation. In addition, the findings suggest that market factors (i.e., education) are more likely to determine the rate of female labor force participation in urban areas; whereas demographic and social factors (i.e., sex ratio and household structure) play a more important role in explaining the female labor force participation in rural counties.     

The nature of gender

I explain a biosocial model of women’s gendered behavior (behavior on which the sexes differ). This model integrates a macro sociological theory with a biological theory derived from primate behavior. The sociological model is designed to explain changes in the relationship between sex and behavior over time or between groups. The biological model is designed to explain individual within-sex variance and between-sex variance in gendered behavior in a cohort. Results from an original study are presented to demonstrate that within-sex variance in women’s gendered behavior is explained well by the primate model. I conclude that human nature is gendered. The implications of this conclusion are explored for demographic and other social science research.