Poster session on Demographic methods and data

Estimation of inherent coverage error in census count is an highly addressed problem in statistical demography.
In this article we briefly discuss the statistical methodology to obtain the omission rate in Indian census using Dual System
Estimation(DSE) technique. We have explicitly studied the correlation bias factor involved in the estimate, its extent
and consequences. A new potential source of bias in the estimate is introduced. At the survey
time, more efficient enumerators (than census time) are appointed and
this fact may inflate the dependency between two lists and
lead to a significant bias. Some examples are given to
demonstrate this argument in various plausible situations. We have suggested one simple and flexible approach which can control the bias.
Our proposed estimator can efficiently overcome the potential bias by achieving desired degree of accuracy(almost unbiased) with relatively better efficiency. Overall improvements and consistency in the results are explored through simulation study on different populations. New estimator is also compared also with another type of dual system estimator used by Indian Sample Registration System(SRS) to estimate number of births and deaths.

Demographic behaviour is shaped not only by characteristics at the individual level, but also by the context in which individuals are embedded. The Contextual Database of the Generations and Gender Programme (GGP) supports research about the impact of contextual factors on demographic behaviour. It facilitates research on micro-macro links by providing cross-country comparative contextual data on demographic, socio-economic and policy developments, covering up to 60 countries in Europe, North America, Asia and Oceania. Although conceptually linked to the Generations and Gender Survey, it can also be used as contextual data source for the analysis of data from other surveys or to study macro-trends. The GGP-Contextual Database comprises a unique combination of features, with which it might serve as a blue print/platform for future contextual databases of other demographic surveys and/or world regions. This includes providing harmonized cross-country comparative time-series of indicators often including sub-national regional data, policy developments, and a dynamic web environment with innovative functionalities, e.g. in terms of metadata documentation by single data-entry and automatic geo-coding. The paper presents conceptual considerations as well as guidelines for data collection and harmonization.

The purposes of this study are to examine a method to overcome the shortage of historical data on mortality of the elderly and to find the best model to forecast Korean mortality rates overall. To extend the mortality for ages 75 and over, we test two methods of estimating death probabilities: the 2-parameter logistic model and the Brass-Logit model. Based on the Mean Absolute Percent Error (MAPE), the logistic model has better performance than the Brass-Logit model. Four stochastic forecasting models (the Lee-Carter Model, the adjusted Lee-Carter Model, the Lee-Miller Model, and the Coherent Lee-Carter Model) are fitted to the period 1970-2010. The forecasts are compared to actual mortality for that period. The results of this evaluation show that the Coherent Lee-Carter Model is consistently more accurate in forecasting Korean mortality rates than other compared models. The Coherent Lee-Carter model yields a higher life expectancy at birth for both sexes and a larger difference between sexes than other models in which sex differentials diminish rapidly.

Levels of educational attainment are the main component of human capital that is used in many models, mostly related to economics. However a large majority of data on education suffer from severe flows, hampering any trend and regression analysis on levels of educational attainment. We show in this paper how picking the right data and adjusting it so that it becomes consistent across ages and countries can be a real hassle. This exercise was done in the framework of Wittgenstein Centre for Demography and Global Human Capital new round of population projections by levels of educational attainment from 2000 to 2060 and the reconstruction of the same data back to 1960. Both exercises require base-year data on population disaggregated by levels of educational attainment by age and sex. These were gathered for 170 countries for six education categories between 2000 and 2011.

Population movement and its impact on other social, economic and demographic characteristics have been increasing attention of social scientists and demographers in recent years and a large number of studies on migration have been conducted. The majority of studies used macro level approach by operating on highly aggregate data for countries, district, states and the nation as a whole. In recent years the study of migration at the micro-level is useful and it is governed by human grouping on probabilistic and stochastic approach. Households play a very important role in decision of an individual to move or not to move from the household. The main objective of the paper is to develop a probability model for the total number of migrants from a household. The suitability of the model is tested through observer data. A primary source of data has been used for this study. The area of the study is Varanasi district in Eastern Uttar Pradesh, India. Result suggests that the proposed model under consideration is a better approximation to observed distribution of rural out migration at the micro level. Thus it may be a useful tool in calculating the various probabilities connected with the out-migration from the household.

The present study attempt to explore small area estimation techniques for estimation of Infant Mortality rate (IMR) at district level for the major state of India. Since many health data are unavailable at the district level, policymaker sometimes rely on state-level dataset to understand the health need at district level. District level data on births and deaths from Civil Registration System and Service Statistics are inadequate and not access able uniformly for all the districts. To meet the challenge for the need of district level indicators, the present study is an attempt to assess the data from the available sources and integrate them through small area estimation techniques to provide district level estimation infant mortality rate (IMR).The estimates of IMR by small area method provide robust result as evident from small gap from Sample Registration System (SRS) and National Family Health Survey (NFHS-3) at state level. The concluding remark is small area estimation is good for estimating IMR at district level.

ABSTRACT: Several studies have indicated that fertility transition has been taking place in some sub-Saharan African countries, including Ghana. There is a need for a continuous systematic attempt to identify the factors associated with the transition. Accordingly, the present study was based on the Bongaarts framework and its reformulation by John Stover to examine the proximate determinants of fertility over three sets of surveys in Ghana.-1998, 2003 and 2008 Ghana Demographic and Health Survey (GDHS). The difference in the index of sterility in the two models may be attributable to the use of all forms of sterility by John Stovers whiles Bongaarts model uses only pathological sterility.The use of sexual activity rather than marriage in Stover’s model is also a better measurement of inhibiting factor associated with pregnancy risk since non-marital sex has been high in Ghana.

A long standing priority in global health has been meeting the health needs of the youngest population, children under the age of 5. Efforts to improve the wellbeing of the population under 5 years of age requires accurate and timely assessment of the current levels and trends of mortality risk in children under the age of 5. Here we present an updated methodological strategy using Spatio-temporal and Gaussian process regressions to synthesize disparate mortality data sources into a coherent time series of 5q0 estimates with 95% uncertainty bounds. We anticipate that in rigorous predictive validity tests this updated modeling strategy will again outperform other synthesis modeling options including LOESS and spline-regression.

This paper aims to study the evolution of adult mortality in small areas in Brazil from 1980 to 2010. We use 45q15 as a summary measure of adult mortality across small areas in Brazil. In order to produce the estimates, we propose a methodological approach that combines death distribution methods (DDM) to indirect standardization and Bayesian statistics, in order to produce more reliable estimates of adult mortality for small areas. We focus on adult mortality because there are much more studies on infant and child mortality for sub-national population using indirect demographic techniques (Souza, Hill and Dal Poz, 2010; Castro and Simões, 2009). The studies on child and infant mortality are also showing a convergence of levels across regions in Brazil, thus the main changes in life expectancy in recent years should be explained by changes and variation in adult mortality levels.

In this paper we aim to study the fertility prospects of Brazil major regions based on a cohort analysis, starting from the mid-1960s. Using micro-census data from 1980 to 2010 it is reconstructed the fertility history of women in five macro regions of the country, namely: North, Northeast, South, Southeast and Midwest. Based on the complete birth history, we reconstruct cohort fertility and afterwards, we apply two methods to analyze the past, present and future trends in Brazilian fertility. First, it is applied a basic benchmark cohort model in order to understand the past and present progress of fertility. For the future prospects, we apply a New Cohort Fertility Forecasts, developed by Myrskylä et al. (2012). As results, we see that there are clear regional differences in cohort fertility. Even in cohort perspective, the levels of Brazilian cohort fertility are still below replacement levels and very concentrated at the young ages of reproductive span. However, in the more developed South and Southeast parts of the country there are signs of fertility postponement. This will result in further decline of fertility in the near future.