Comparing Population Distributions from Bin-aggregated Sample Data: An Application to Historical Height Data from France

Institut d'Anàlisi Econòmica (CSIC), Barcelona, Spain.
Economics and human biology (Impact Factor: 1.9). 05/2011; 9(4):419-37. DOI: 10.1016/j.ehb.2011.05.002
Source: PubMed


We develop a methodology to estimate underlying (continuous) population distributions from bin-aggregated sample data through the estimation of the parameters of mixtures of distributions that allow for maximal parametric flexibility. The statistical approach we develop enables comparisons of the full distributions of height data from potential army conscripts across France's 88 departments for most of the nineteenth century. These comparisons are made by testing for differences-of-means stochastic dominance. Corrections for possible measurement errors are also devised by taking advantage of the richness of the data sets. Our methodology is of interest to researchers working on bin-aggregated or histogram-type data, something that is still widely done since much of the information that is publicly available is in that form, often due to restrictions based on confidentiality concerns.

Download full-text


Available from: David E. Sahn
  • [Show abstract] [Hide abstract]
    ABSTRACT: Since the pioneering study of Le Roy Ladurie and his team, the idea that mean height can be considered as a reliable indicator of the standard of living has emerged from a long debate among historians and economists. Considering height in this respect, nineteenth-century France, unlike most Western countries, did not pay an urban penalty. Thanks to a substantial set of individual data (105,324 observations), based on the draft lottery of Frenchmen born in the year 1848, we are able to prove that this “French exception” did not, in fact, exist. The larger the town, the shorter were the conscripts. Among the towns, Paris had the shortest conscripts. By combining individual data with the agricultural survey of 1852, we are able to identify those factors that compensated for this urban penalty—that were positively correlated with height: nutritional availability, the literacy rate, and life expectancy.
    No preview · Article · Jan 2014 · Cliometrica
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper discusses the many dimensions of health inequality, a multi-faceted concept, which examines the dispersion in the distribution of health spending, the provision of health services, health capabilities and health outcomes. The underlying concern is motivated by issues of both social justice and economic efficiency, recognizing health's central role as a condition of human existence. While the paper includes a wide-ranging discussion of conceptual issues, most of it is devoted to introducing approaches to empirical analysis of health inequality, ranging from fiscal incidence to decomposition analysis. It also focuses on the distinction between the univariate and gradient approaches. The former involves making comparisons of cardinal or scalar indicators of health inequality and distributions of health, regardless of whether health is correlated with welfare measured along other dimensions. This univariate approach measures pure inequalities in health in a fashion that is similar to what is done for income distribution. In contrast, the gradient approach generally focuses on making comparisons of health across populations with different social and economic characteristics.
    Full-text · Article · Dec 2012 · African Development Review
  • [Show abstract] [Hide abstract]
    ABSTRACT: This study mainly aims to explore the spatio-temporal patterns and to simulate the future scenario of population change in Beijing based on the fifth and sixth census data at township level. The main contents and results were summed up as follows: (1) The resident population of Beijing increased with an average annual rate of 3.5% between 2000 and 2010, and the population increased by 0.6 million every year. Beijing was one of the megacities which were classified into the first range for their great amount of increased population. (2) There was an obvious circle structure in space. The population of inner city was almost stagnant; it had a rapid growth in the suburbs, and a high rate in the outer city. However, it had an increase only in the county seat and the key towns in the ecological conservation region of Beijing. (3) In terms of the CA/MAS scenario simulation analysis, in the spontaneous layout scenario, employment opportunities will be further agglomerated to the inner city, while population is suburbanized constantly. This will increase the city's commuter stress and aggravate the condition of city traffic block. When adjusting the parameters of employment and thus strengthening the guide policy of urban population living in working function, the problem of imbalance between industrial space and residential space in the urban internal space scale can be solved. At the same time, the formation of cluster of small towns can be promoted and urban commuter pressure can be reduced. Then comes the city's radiation and diffusion effect. The authors suggest that, in order to optimize the spatial distribution of population in Beijing, more efforts should be made to coordinate the relationship between employment and residents. An important way is to accelerate regional coordinated development, and to plan multi-centers development as groups.
    No preview · Article · Oct 2014