Volume 59 - Number 4 - Winter 1993

N. Methods of Research and Analysis Including Models

Studies concerned with demographic methods and with methods from other disciplines that have been applied to demographic data as a whole. Includes mathematical demography and studies on methods of estimation and indirect estimation. Methodological studies and models concerned with one demographic variable, such as migration, are coded under the category concerned with that topic and cross-referenced to this heading. Studies on models used to investigate relationships between demographic variables and for the analysis of empirical data are also coded under this heading.

59:40710 Burch, Thomas K. Estimating the Goodman, Keyfitz and Pullum kinship equations: an alternative procedure. Population Studies Centre Discussion Paper, No. 93-8, ISBN 0-7714-1555-9. Jul 1993. 10 pp. University of Western Ontario, Population Studies Centre: London, Canada. In Eng.
The author presents an alternative procedure for evaluating the relationships among mortality, fertility, and kin numbers. The procedure is developed using software created since the publication of a previous paper concerned with such relationships.
For the paper by Leo A. Goodman et al., published in 1974, see 40:3393 and 42:2501.
Correspondence: University of Western Ontario, Population Studies Centre, Room 3227, Social Science Centre, London, Ontario N6A 5C2, Canada. Location: Princeton University Library (SPR).

59:40711 Burch, Thomas K. Theory, computers and the parameterization of demographic behaviour. Population Studies Centre Discussion Paper, No. 92-10, ISBN 0-7714-1486-2. Nov 1992. 13, [2] pp. University of Western Ontario, Population Studies Centre: London, Canada. In Eng.
The author compares the history and use of the Coale-McNeil and the Hernes models of first marriage. The focus is on reasons why the first model has been more widely used by demographers.
Correspondence: University of Western Ontario, Population Studies Centre, London, Ontario N6A 5C2, Canada. Location: Princeton University Library (SPR).

59:40712 Crawford, David L.; Pollak, Robert A.; Vella, Francis. Order and inference in qualitative response models. Seattle Population Research Center Working Paper, No. 93-4, Nov 1992. 35 pp. University of Washington, Seattle Population Research Center: Seattle, Washington; Battelle Seattle Research Center: Seattle, Washington. In Eng.
The authors define two types of ordered qualitative response models and discuss their applications. These applications are illustrated using data on the educational attainment of young Australian women.
Correspondence: Seattle Population Research Center, c/o University of Washington, Center for Studies in Demography and Ecology Library, Department of Sociology DK-40, Seattle, WA 98195. Location: Princeton University Library (SPR).

59:40713 Guo, Guang. Event-history analysis for left-truncated data. Sociological Methodology, Vol. 23, 1993. 217-43 pp. Washington, D.C. In Eng.
"This paper aims at providing a practical guidance for coping with social science event-history data that are left-truncated, especially when the length of exposure prior to observation is known. Only the case of single events is treated, although much of the discussion should be applicable to the case of repeated events, in which only the first spell is likely to be left-truncated. Marital dissolution data from the Panel Study of Income Dynamics (PSID) are used as an example...."
Correspondence: G. Guo, University of North Carolina, POB 2688, Chapel Hill, NC 27515-2688. Location: Princeton University Library (SPR).

59:40714 Hill, Daniel H.; Axinn, William G.; Thornton, Arland. Competing hazards with shared unmeasured risk factors. Sociological Methodology, Vol. 23, 1993. 245-77 pp. Washington, D.C. In Eng.
"The present paper develops a generalization of the standard discrete-time competing hazards model that allows for the types of stochastic dependencies resulting from shared unmeasured risk factors. An empirical example is provided using the process by which young women form their first conjugal residential union, with married and unmarried cohabitation representing the competing alternatives. The results suggest considerable and significant similarity of the alternatives in terms of the unmeasurables. It is also shown that, as a result, the independence assumption leads to substantially biased estimates of the net marriage and net cohabitation survival functions." The data concern a cohort of white children born in Detroit, Michigan, in 1961 and their mothers, followed up to 1985.
Correspondence: D. H. Hill, University of Toledo, Survey Research Institute, Toledo, OH 43606. Location: Princeton University Library (SPR).

59:40715 Kim, Young J.; Schoen, Robert. On the intrinsic force of convergence to stability. Mathematical Population Studies, Vol. 4, No. 2, 1993. 89-102, 149 pp. New York, New York/Yverdon, Switzerland. In Eng. with sum. in Fre.
"Observed populations differ greatly in the speed with which they approach the stable form, but what determines rates of convergence is not fully understood....Here we examine the trajectory to stability, derive a mathematical expression for the force of convergence, and provide an approximate relationship in terms of the mean and variance of the stable net maternity function." Trajectories for Japan, Togo, and the United States are used as illustrations.
Correspondence: Y. J. Kim, Johns Hopkins University, Department of Population Dynamics, 615 North Wolfe Street, Baltimore, MD 21205. Location: Princeton University Library (SPR).

59:40716 Lee, Elisa T. Statistical methods for survival data analysis. Wiley Series in Probability and Mathematical Statistics: Applied Probability and Statistics, 2nd ed. ISBN 0-471-61592-7. LC 91-27926. 1992. xii, 482 pp. John Wiley and Sons: New York, New York/Chichester, England. In Eng.
This book "is intended to meet the need for a single volume covering the methodologies appropriate for the analysis of survival data. The book has been written for biomedical investigators, statisticians, epidemiologists, and researchers in other disciplines who are involved or interested in analyzing survival data. It covers the most commonly used methods, parametric and nonparametric, in survival data analysis and can be used as a reference resource or textbook. In addition, it provides guidelines for the planning and design of clinical trials." Innovations in this second edition include a discussion of population life tables, introduction of the concepts of standardized mortality ratio and standardized incidence ratio, and the inclusion of information on survival-data-analysis computer programs written over the past 10 years.
Correspondence: John Wiley and Sons, 605 Third Avenue, New York, NY 10158-0012. Location: Princeton University Library (SPR).

59:40717 Levy, Michel L. The specificity of demography: cohort analysis. [Specificite de la demographie: l'analyse "longitudinale"] Population et Societes, No. 284, Nov 1993. 1-3 pp. Paris, France. In Fre.
Some aspects of cohort analysis are discussed and illustrated using data for France on occupations, employment, and elderly women living alone.
Correspondence: M. L. Levy, Institut National d'Etudes Demographiques, 27 rue du Commandeur, 75675 Paris Cedex 14, France. Location: Princeton University Library (SPR).

59:40718 Mitra, S.; Levin, Martin L. Complex roots of Lotka's integral equation for a special model of net maternity rates. Janasamkhya, Vol. 8, No. 2, Dec 1990. 115-32 pp. Kariavattom, India. In Eng.
"An attempt to obtain the solutions of Lotka's integral equation has been made in this paper by assuming a Pearsonian Type III function for the age distribution of the net maternity rates. The shifting of the origin of the function from the traditional value of age zero to the most meaningful lower boundary of the reproductive interval gave rise to an analytical expression of the equation with interesting properties most of which have not yet been encountered in similar endeavors."
Correspondence: S. Mitra, Emory University, Atlanta, GA 30322. Location: Princeton University Library (SPR).

59:40719 Pollard, John H.; Valkovics, Emil J. The Gompertz distribution and its applications. Genus, Vol. 48, No. 3-4, Jul-Dec 1992. 15-28 pp. Rome, Italy. In Eng. with sum. in Fre; Ita.
"In this paper we study the underlying Gompertz distribution and develop formulae for the moments and other characteristics of this useful but apparently unknown distribution. We find that the skewness and kurtosis of the distribution are fixed constants independent of the two distribution parameters, and this would appear to be the reason for the mixed success writers have experienced fitting the curve to fertility data. We also show the distribution of the minimum of n independent Gompertz variables, all having the same c-parameter, is itself a Gompertz variable with the same c-parameter."
Correspondence: J. H. Pollard, Macquarie University, School of Economic and Financial Studies, Sydney, NSW 2109, Australia. Location: Princeton University Library (SPR).

59:40720 Prskawetz, Alexia. Deterministic chaos versus stochastic modeling in demography. [Deterministisches Chaos versus stochastische Modellierung in der Demographie.] Zeitschrift fur Bevolkerungswissenschaft, Vol. 18, No. 4, 1992. 495-517 pp. Wiesbaden, Germany. In Ger. with sum. in Eng; Fre.
"New statistical and graphical methods derived from the theory of nonlinear dynamic systems are introduced. By means of these methods a periodical time series can be classified in more detail. It can be especially checked whether the irregular character of time series is caused by non-linear, deterministic--especially chaotic--dynamics or by stochastic dynamics. These methods are illustrated on the basis of Austrian birth data."
Correspondence: A. Prskawetz, Osterreichischen Akademie der Wissenschaften, Institut fur Demographie, Hintere Zollamtsstrasse 2B, 1033 Vienna, Austria. Location: Princeton University Library (SPR).

59:40721 Raftery, Adrian E.; Aghajanian, Akbar; Lewis, Steven M.; Kahn, Michael J. Event history modeling of World Fertility Survey data. Seattle Population Research Center Working Paper, Rev. ed. No. 93-1, Jun 1993. 31 pp. University of Washington, Seattle Population Research Center: Seattle, Washington; Battelle Seattle Research Center: Seattle, Washington. In Eng.
The authors propose a modeling strategy that permits the application of event history analysis to World Fertility Survey data. They test the model using data on aspects of fertility decline in Iran.
Correspondence: Seattle Population Research Center, c/o University of Washington, Center for Studies in Demography and Ecology Library, Department of Sociology DK-40, Seattle, WA 98195. Location: Princeton University Library (SPR).

59:40722 Retherford, Robert D.; Choe, Minja Kim. Statistical models for causal analysis. ISBN 0-471-55802-8. LC 93-23423. 1993. xiv, 258 pp. John Wiley and Sons: New York, New York. In Eng.
"This book provides a quick overview of statistical models commonly used in causal analyses of nonexperimental data in the social and biomedical sciences. Topics covered are simple bivariate regression, multiple regression, multiple classification analysis, path analysis, logit regression, multinomial logit regression, and survival models (proportional hazard models and hazard models with time dependence)." The methods described are illustrated using data from the 1974 Fiji Fertility Survey, conducted as part of the World Fertility Survey.
Correspondence: John Wiley and Sons, 605 Third Avenue, New York, NY 10158-0012. Location: Princeton University Library (SPR).

59:40723 Schoen, Robert; Kim, Young J. Hyperstability. Johns Hopkins Population Center Papers on Population, No. 93-10, Oct 1993. 28 pp. Johns Hopkins University, School of Hygiene and Public Health, Population Center: Baltimore, Maryland. In Eng.
"This paper describes a closed form demographic model with changing vital rates." The model is tested using hypothetical and U.S. data for the period 1920-1973.
Correspondence: Johns Hopkins University, School of Hygiene and Public Health, Population Center, 615 North Wolfe Street, Room 2300, Baltimore, MD 21205-2179. Location: Princeton University Library (SPR).

59:40724 Xie, Yu. Log-multiplicative models for discrete-time, discrete-covariate event history data. Population Studies Center Research Report, No. 93-286, Aug 1993. 25, [21] pp. University of Michigan, Population Studies Center: Ann Arbor, Michigan. In Eng.
The author develops "a new class of discrete-time, discrete-covariate models for modelling nonproportionality in event history data within the log-multiplicative framework." The models are tested using data from the U.S. National Longitudinal Mortality Study and the June 1980 Current Population Survey.
Correspondence: University of Michigan, Population Studies Center, 1225 South University Avenue, Ann Arbor, MI 48109-2609. Location: Princeton University Library (SPR).


Copyright © 1993-1996, Office of Population Research, Princeton University.