Count data models for demographic data

"This paper deals with the estimation of single equation models in which the counts are regressed on a set of observed individual characteristics such as age, gender, or nationality....We propose a generalized event count model to simultaneously allow for a wide class of count data models and account for over- and underdispersion. This model is successfully applied to German data on fertility, divorces and mobility." (SUMMARY IN FRE)     

Count data models for demographic data∗

Key demographic variables, such as the number of children and the number of marriages or divorces, can only take integer values. This papers deals with the estimation of single equation models in which the counts are regressed on a set of observed individual characteristics such as age, gender, or nationality. Most empirical work in population economics has neglected the fact that the dependent variable is a nonnegative integer. In the few cases where this feature was recognized, the authors advocated the use of the Poisson regression model. The Poisson model imposes, however, the equality of conditional mean and variance, a restriction which is often rejected by the data. We propose a generalized event count model to simultaneously allow for a wide class of count data models and account for over‐ and underdispersion. This model is successfully applied to German data on fertility, divorces and mobility.     

Indigenous data sovereignty and COVID-19 data issues for American Indian and Alaska Native Tribes and populations

Journal of Population Research - Indigenous Peoples in the United States have been experiencing disproportionate impacts of COVID-19. American Indian and Alaska Native persons are more likely to be...     

Interpolation and forecasting of population census data

Since population censuses are not annually implemented, population estimates are needed for the intercensal period. This paper describes simultaneous implementations of the temporal interpolation and forecasting of the population census data, aggregated by age and period. Since age equals period minus cohort, age-period-cohort decomposition suffers from the identification problem. In order to overcome this problem, the Bayesian cohort (BC) model is applied. The efficacy of the BC model for temporal interpolation is examined in comparison with official Japanese population estimates. Empirical results suggest that the BC model is expected to work well in temporal interpolation. Regarding the age-period-cohort decomposition of the Japanese census data, it is shown that the cohort effect is the largest while the other two effects are very small but not negligible. With regard to the forecasting of the Japanese population, the official population forecast considerably outperforms the BC forecast in most forecast horizons. However, the pace of increase in root mean square error for longer-term forecasting is larger in the official population forecast than in the BC forecasts. As a result, a variant of the BC forecast is best for 10-year forecast.     

Consistent correction of census and vital registration data

A new procedure is developed for simultaneously and consistently correcting 2 or more censuses and intercensal registered births and deaths. The procedure begins with a set of preliminary correction factors, which are not necessarily consistent. It then uses the mathematics of finite-dimensional vector spaces to derive an optimal set of final consistent correction factors. The optimization procedure is based on the principle that there exists in a hyperplane a unique point of minimum distance from a fixed point not in the hyperplane. For purposes of illustration, the procedure is applied to the censuses of 1970, 1975, and 1980 and intercensal registered births and deaths for the periods 1970-1975 and 1975-1980 for the Republic of Korea.     

Collection and publication of population census data]

Some characteristics of the 1982 census of China are described. The discussion covers the manual and machine processing of data, how much detailed data will be available, individual and categorized data, and total and desired data. The major categories of data to be made available, including age, sex, fertility, and mortality statistics, are listed. The author notes that the results will be released in three stages, with the final results available by the end of 1984.     

Child survivorship estimation: methods and data analysis

"The past 20 years have seen extensive elaboration, refinement, and application of the original Brass method for estimating infant and child mortality from child survivorship data. This experience has confirmed the overall usefulness of the methods beyond question, but it has also shown that...estimates must be analyzed in relation to other relevant information before useful conclusions about the level and trend of mortality can be drawn.... This article aims to illustrate the importance of data analysis through a series of examples, including data for the Eastern Malaysian state of Sarawak, Mexico, Thailand, and Indonesia. Specific maneuvers include plotting completed parity distributions and 'time-plotting' mean numbers of children ever born from successive censuses. A substantive conclusion of general interest is that data for older women are not so widely defective as generally supposed."     

The data and the dynamics of the Chinese populations

Historical demographic data on populations of the Chinese cultural area including counts, registrations, and continuous records are discussed in terms of problems of analysis. For many decades, censuses, investigations, and registration reports yielded generally faulty data on the numbers, and the age and sex structures of the populations. The problem here is not the adjustment of age and sex structures, but the use of faulty structures to estimate the dynamics of the population in the absence of either successive investigations or vital statistics. This paper analyzes these problems according to historical eras (Chinese Farm Population 1919-1932) or geographical areas (Taiwan, Manchuria, etc.). The writer concludes that further pursuit of estimates that agree with the Chinese demographic realities of the period requires a) a wider integration of comparable data and b) adjustment of age structures in relation to the habitual errors in response, the systematic biases in registration, and the deviations reflecting erratic factors or historic events.