It is argued that P-values and the tests based upon them give unsatisfactory results, especially in large samples. It is shown that, in regression, when there are many candidate independent variables, standard variable selection procedures can give very misleading results. Also, by selecting a single model, they ignore model uncertainty and so underestimate the uncertainty about quantities of interest. The Bayesian approach to hypothesis testing, model selection, and accounting for model uncertainty is presented. Implementing this is straightforward through the use of the simple and accurate BIC approximation, and it can be done using the output from standard software. Specific results are presented for most of the types of model commonly used in sociology. It is shown that this approach overcomes the difficulties with P-values and standard model selection procedures based on them. It also allows easy comparison of nonnested models, and permits the quantification of the evidence for a null hypothesis of interest, such as a convergence theory or a hypothesis about societal norms.

https://www.jstor.org/stable/pdfplus/271063.pdf

Bayesian Model Selection in Social Research

This paper considers Bayesian counterparts of the classical tests for good- ness of fit and their use in judging the fit of a single Bayesian model to the observed data. We focus on posterior predictive assessment, in a framework that also includes conditioning on auxiliary statistics. The Bayesian formulation facilitates the con- struction and calculation of a meaningful reference distribution not only for any (classical) statistic, but also for any parameter-dependent "statistic" or discrep- ancy. The latter allows us to propose the realized discrepancy assessment of model fitness, which directly measures the true discrepancy between data and the posited model, for any aspect of the model which we want to explore. The computation required for the realized discrepancy assessment is a straightforward byproduct of the posterior simulation used for the original Bayesian analysis. We illustrate with three applied examples. The first example, which serves mainly to motivate the work, illustrates the difficulty of classical tests in assessing the fitness of a Poisson model to a positron emission tomography image that is constrained to be nonnegative. The second and third examples illustrate the details of the posterior predictive approach in two problems: estimation in a model with inequality constraints on the parameters, and estimation in a mixture model. In all three examples, standard test statistics (either a χ 2 or a likelihood ratio) are not pivotal: the difficulty is not just how to compute the reference distribution for the test, but that in the classical framework no such distribution exists, independent of the unknown model parameters.

/pdf/posterior-predictive-assessment-of-model-fitness-via-1wc3dk7ymj.pdf

Posterior predictive assessment of model fitness via realized discrepancies

Large, pervasive, and persistent racial inequalities exist in the onset, courses, and outcomes of illness. A comprehensive understanding of the patterning of racial disparities indicates that racism in both its institutional and individual forms remains an important determinant. There is an urgent need to build the science base that would identify how to trigger the conditions that would facilitate needed societal change and to identify the optimal interventions that would confront and dismantle the societal conditions that create and sustain health inequalities.

Miles to go before we sleep: racial inequities in health.

L’etude turque sur la valeur conferee aux enfants a porte sur trois generations relevant de trois niveaux socio-economiques dans centre metropolitain et deux zones rurales. Les resultats ont montre qu’il y avait sur les trois derrieres decennies un net accroissement des valeurs psychologiques attribuees aux enfants et une chute correspondante des valeurs utilitaires et economiques. La preference pour le fils a ete remplacee par la preference pour la fille, ce qui traduit un changement de la dynamique et des roles familiaux. Des modifications analogues dans ce qui est attendu des enfants, les qualites que l’on souhaite trouver chez cux et les nombres reels, desires et ideaux d’enfants sont coherents avec les attentes; le modele du changement familial propose par Kagitcibasi est ainsi confirme. Les comparaisons des valeurs attribuees aux enfants sur les trois decennies par generation et niveau social aide a comprendre l’evolution et le changement social de la societe turque, voire de societes comparables.



The Turkish Value of Children Study consisted of three generations from three socioeconomic strata in a metropolitan center and from two rural areas. The findings showed a sharp increase in the psychological, and a corresponding decrease in the utilitarian/economic values attributed to children over the last three decades. Son preference has been replaced by daughter preference, pointing to changing family dynamics and family roles. Corresponding modifications in expectations from (adult) children, qualities desired in children, and actual, desired, and ideal numbers of children are in line with expectations, providing support for Kagitcibasi's Model of Family Change. Comparisons of values attributed to children over three decades and across generations and social strata provide insights for understanding social change and development in Turkish society and possibly in similar societies.

Value of Children and Family Change: A Three‐Decade Portrait From Turkey

Alma-Ata: Rebirth and Revision 6 Interventions to address maternal, newborn, and child survival: what difference can integrated primary health care strategies make?

Is the onset of fertility decline caused by structural socioeconomic changes or by the transmission of new ideas? The decline of marital fertility in Iran provides a quasi-experimental setting for addressing this question. Massive economic growth started in 1955; measurable ideational changes took place in 1967. We argue that the decline is described more precisely by demand theory than by ideation theory. It began around 1959, just after the onset of massive economic growth but well before the ideational changes. It paralleled the rapid growth of participation in primary education, and we found no evidence that the 1967 events had any effect on the decline. More than one-quarter of the decline can be attributed to the reduction in child mortality, a key mechanism of demand theory. Several other findings support this main conclusion.

Demand or ideation? Evidence from the Iranian marital fertility decline.

During the 1970s many developing countries experienced some transition to lower fertility. The size of fertility decline was remarkable in some countries such as those in Southeast Asia. On the other hand in some countries in West Asia and North Africa the transition toward lower fertility was very minimal. Furthermore the pace of fertility decline for some of the countries which had moved toward lower levels of fertility declined in 1990s and some countries are experiencing a stall in their transition. Despite the slowdown and stalled fertility transition experiences of other countries in West Asia and the North Africa region Iranian fertility rates have shown signs of sharp decline. The recent censuses and surveys both regional and national are consistent with a strong declining trend which started in the later part of 1980s and seem to be continuing into the new century. This paper utilizes the data from the 2000 Demographic and Household Survey of Iran to examine the pace of fertility transition and gives insight to the fast pace of decline during the 1990s and beyond. (excerpt)

/pdf/the-pace-of-fertility-decline-in-iran-finding-from-the-1hoyzcestt.pdf

The Pace of Fertility Decline in Iran: Finding from the Demographic and Health Survey*

A researcher used censuses and surveys to analyze 1966-1976 and 1976-1986 population data to compare population growth and fertility of Iran under the Shah with those of theocratic Iran. Between 1966-1976 the government introduced policies which improved the legal and social status of women and promoted fertility control. These resulted in a reduction in the annual population growth rate from 3.1-2.7%. In fact the crude birth rate fell from 49-42.7. Yet the rural birth rate (49.1) was still 1 of the highest in the world. A rising age at marriage contributed to the fall in fertility. For example in 1966 46.5% of 15-19 year old women were married compared to 34.2% in 1976. In fact the singulate mean age of marriage increased from 18.4-19.7. Further the percentage of women of reproductive age who were married decreased 81-75% between 1966-1976. Moreover age specific fertility rates fell for all 20-40 year old women. Indeed total fertility declined from 7.7-6.3. This was more pronounced in urban areas (6.9-4.4). As a result of the Iranian Revolution and the Iran-Iraq war population size increased rapidly from 33.7-49.4 million (1976-1986)--3.8% annual growth rate. Further the crude birth rate increased 12% (1986 47.6). In addition at least 1.8 million people from Afghanistan sought refuge in Iran. Moreover the age at 1st marriage was not any higher than in 1986 than it was in 1976. In fact the government reduced the legal age to 9 for females and 14 for males. Further it abolished the family planning council. In addition the proportion of 15-59 year old married women only decreased 3% between 1976-1986 compared to 6% between 1976-1986. Age specific fertility rates increased significantly especially for 40-44 year olds (32%). Further total fertility rose to 7 and the increase was especially high in urban areas (16% increase compared to 8% in rural areas). As of the end of 1991 there were indications that the government recognized the population problem and had taken steps to promote family planning.

Population change in Iran 1966-86: a stalled demographic transition?

PIP: This article traces the history of Iran's population policy from the establishment of a family planning (FP) policy in 1967 to the present. Context for the discussion is provided by a review of population growth in the country since 1900. Indicators for 1966, 1976, and 1986 show population size growing from 25.7 million to 33.7 and 49.4, respectively, as the crude birth rate fluctuated from 49 to 42.7 to 47.6, and the total fertility rate changed from 7.7 to 6.3 to 7.0. These figures reflect changes in population policy which promoted the use of effective contraceptive methods among urban women in the period 1967-79 but which led to only 11% acceptance by 1977. From 1979 until 1988, the newly established Islamic Republic allowed family planning programs to disintegrate. In 1988, the results of overpopulation could be seen, and a new program was established in 1989 with the full concurrence of religious authorities. This program is attempting to 1) encourage birth spacing of 3-4 years, 2) discourage early and late pregnancies, and 3) limit family size to three children. Government support for this program is evident in financing commitments and in the creation of disincentives to have more than three children. Services are provided in 400 centers which emphasize sterilization and provide a range of contraceptive options including Norplant and injectables. Data from the 1976-77 Iran Fertility Survey (IFS) and the 1992 Contraceptive Prevalence Survey (CPS) show that, in 1976, 85% of women had heard of oral contraceptives. The CPS revealed 90% knowledge of at least one method and more than 70% approval of FP. The IRS showed 35.9% of all currently married women using contraceptives; the corresponding CPS figure was 64.6%. The urban-rural gap in knowledge and use which existed in 1976 also narrowed by 1992, but the popularity of certain methods varied by urban-rural residence. Positive determinants of contraceptive use for both periods include literacy and number of living children. Preliminary data reveal that the new program has led to a significantly reduced growth rate as well as a decline in the total fertility rate and in the number of registered births. These declines may also be due to a significant increase in marriage age from 1986 to 1991. Iran's new FP program has been successful because it has the support of religious leaders and operates with the moral authority of a fatva issued by the Ayatollah Khomeini. Other Islamic countries could create successful programs in a similar way.

A new direction in population policy and family planning in the Islamic Republic of Iran.

This article examines the fertility transition pattern and related demographic social economic and political factors in the Islamic Republic of Iran over the period 1976-96. Data on fertility rates were obtained from the Survey of Population Growth of Iran (1976) and the post-census enumeration survey (1996). During the period 1976-86 the rate of population growth accelerated dramatically (3.4% annually). This increase depending mainly on an increase in the crude birth rate constituted a reversal of the trend during the previous 10-year interval. However during the period 1986-96 the census revealed a sharp decline in the population growth rate and crude birth rate. This declining trend accelerated between 1991 and 1996. Demographic factors affecting fertility change were the increase in the average age of marriage the decrease in the proportion of the population that was married and the increase in age-specific fertility rates for women aged >25 years. There was a potential fertility decline among the rural population. An estimated 12 million women will be added to the 15-49 age group during the period 1996-2006. This demographic fact alone is justification for the government to continue providing strong support for family planning services and to expand the budget for improving family planning services and reducing the contraceptive failure rate.

Akbar Aghajanian

Papers

Demand or ideation? Evidence from the Iranian marital fertility decline.

The Pace of Fertility Decline in Iran: Finding from the Demographic and Health Survey*

Population change in Iran 1966-86: a stalled demographic transition?

A new direction in population policy and family planning in the Islamic Republic of Iran.

Fertility transition in the Islamic Republic of Iran: 1976-1996