Real and Synthetic Household Populations and Their Analysis: An Example of Early Historical Census Microdata (Rostock in 1819) (original) (raw)
Related papers
2010
The main purpose of this paper is to report on an initial validation of methods for dealing with micro-census data with no delineated households. After describing the 1819 census of Rostock we test the possibilities of using an algorithm that creates households according to a strictly defined set of rules. The census of 1867 will be taken as our reference point for designing such rules of assigning people to household units and for assessing the appropriateness of the algorithm's fit to the census of 1819. In the final part we discuss the outcome of the algorithm for different groups within the urban population and the strengths and weaknesses of this approach.
Residence Patterns and Demographic Constraints
Journal of Family History, 2015
This article provides an account of how demographic conditions have shaped co-coresidence patterns in historic Eastern Europe. Census microdata from eighteenth-century Poland, Lithuania, Belarus, and Ukraine are confronted with the computer microsimulation of kin sets to show how the combined effects of fertility, marriage, and mortality influenced the availability of kin for coresidence. The enactment of demographic constraints on residential chances is illustrated by exploring two issues central to historical demographic interest: leaving home and intergenerational coresidence. This article closes with an agenda for comparative studies of historical household systems that takes demographic constraints on coresidence more seriously into account.
Some Methodological Issues in Counting Communities and Households
In this article we discuss some of the limitations of conventional census techniques that assign all individuals to a single household in a single community. In areas with high rates of mobility and where people may belong to several households, traditional census methods can lead to very deceptive results that are poor guides for policy making and the delivery of services. The article suggests some ways census methods could be improved, so they can yield more informative and useful results.
Alternative household classifications for the 2001 Census
Environment and Planning A, 2004
This paper anticipates the release of a series of new household classifications as part of the standard output from the 2001 UK Census. It contains essential background information for census users interested in using these classifications. In addition to describing the classifications, we outline the background to the classifications, and the consultation undertaken to ensure that each classification reflects real user demand.
Automatic Household Identification for Historical Census Data
Advances in Artificial Intelligence, Proceedings of 30th Canadian Conference on Artificial Intelligence, 2017
In this paper, we present a method, that uses domain knowledge, to automatically discover and assign household identifiers to individual historical records. We apply this algorithm on a full count real census (the 1891 Canadian census) to assign household identifiers to all the records.
A Regression Approach to Estimating the Average Number of Persons per Household
Demography, 2002
In the housing unit method, population is calculated as the number of households times the average number of persons per household (PPH), plus the population residing in group quarters facilities. Estimates of households and the group quarters population can be derived directly from concurrent data series, but estimates of PPH have traditionally been based on previous values or estimates for larger areas. In our study, we developed several regression models in which PPH estimates were based on symptomatic indicators of PPH change. We tested these estimates using countylevel data in four states andfound them to be more precise and less biased than estimates based on more commonly used methods.
2009
The advent of microsimulation approaches in travel demand modeling, wherein activity-travel patterns of individual travelers are simulated in time and space, has motivated the development of synthetic population generators. These generators typically use census-based marginal distributions on household attributes to generate joint distributions on variables of interest using standard iterative proportional fitting (IPF) procedures. Households are then randomly drawn from an available sample in accordance with the joint distribution such that household-level attributes are matched perfectly. However, these traditional procedures do not control for person-level attributes and joint distributions of personal characteristics. In this paper, a heuristic approach, called the Iterative Proportional Updating (IPU) algorithm, is presented to generate synthetic populations whereby both household-level and person-level characteristics of interest can be matched in a computationally efficient manner. The algorithm involves iteratively adjusting and reallocating weights among households of a certain type (cell in the joint distribution) until both household and person-level attributes are matched. The algorithm is illustrated with a small example, and then demonstrated in the context of a real-world application using small geographies (blockgroups) in the Maricopa County of Arizona in the United States. The algorithm is found to perform very well, both from the standpoint of matching household and person-level distributions and computation time. It appears that the proposed algorithm holds promise to serve as a practical population synthesis procedure in the context of activitybased microsimulation modeling.