A Graphical Tool for Interpreting Regression Coefficients of Trinomial Logit Models

Multinomial logit (also termed multi-logit) models permit the analysis of the statistical relation between a categorical response variable and a set of explicative variables (called covariates or regressors). Although multinomial logit is widely used in both the social and economic sciences, the interpretation of regression coefficients may be tricky, as the effect of covariates on the probability distribution of the response variable is nonconstant and difficult to quantify. The ternary plots illustrated in this article aim at facilitating the interpretation of regression coefficients and permit the effect of covariates (either singularly or jointly considered) on the probability distribution of the dependent variable to be quantified. Ternary plots can be drawn both for ordered and for unordered categorical dependent variables, when the number of possible outcomes equals three (trinomial response variable); these plots allow not only to represent the covariate effects over the whole parameter space of the dependent variable but also to compare the covariate effects of any given individual profile. The method is illustrated and discussed through analysis of a dataset concerning the transition of master’s graduates of the University of Trento (Italy) from university to employment.     

Using the Theory of Planned Behaviour to Understand Motivation to Register Births in Lombok,Indonesia

Despite government interest in promoting birth registration, more than a third of Indonesian children do not have a birth certificate, affecting the realisation of both their human and citizen rights. While barriers to registering children's births in Indonesia have been assessed, there is limited research on how communities perceive the importance of having a birth certificate. This study used focus group discussions to explore parental motivations around birth registration. The results of a thematic analysis found that perceived use of birth certificates, perceived control over the application process and social norms related to certificate ownership affect the intention to apply.     

The demographic context of recent change in the structure of American households

This article examines recent changes in the structure of American households within the context of broad population changes. Decreases in married-couple households and increases in single-parent households are almost entirely due to the changing patterns of marriage, divorce, fertility, and child custody; headship rates for families have remained relatively stable. Increases in single-person and other nonfamily households are due to increases in the size of the unmarried, childless population and to the aging of this population. Increasing propensities to live alone or with nonrelatives were observed between 1970 and 1980, but these behavioral changes have abated during the early 1980s.     

Household Headship Among Unmarried Persons in the United States, 1970–1985

Recent trends in rates of household headship and headship differentials by sex and color are examined within the context of a model that expresses the likelihood of heading an independent household as a function of age, marital status, parental status, and individual money income. The parameters of this model are consistent with predictions derived from a "life-course" perspective and are stable across period, sex, and color. Nonetheless, residual effects of period, sex, and color persist even after the independent variables are taken into account.     

Central hypogonadism due to a giant, “silent” FSH-secreting,atypical pituitary adenoma: effects of adenoma dissection and short-term Leydig cell stimulation by luteinizing hormone (LH) and human chorionic gonadotropin (hCG)

We present a case report of an atypical giant pituitary adenoma secreting follicle-stimulating hormone (FSH). A 55-year-old patient presented for erectile dysfunction, loss of libido and fatigue. The biochemical evaluation showed very high FSH serum levels in the presence of central hypogonadism. Neither testicular enlargement nor increased sperm count was observed, thus a secretion of FSH with reduced biological activity was supposed. The histological examination after neuro-surgery showed an atypical pituitary adenoma with FSH-positive cells. Hypogonadism persisted and semen analyses impaired until azoospermia in conjunction with the reduction in FSH levels suggesting that, at least in part, this gonadotropin should be biologically active. Thus, we hypothesized a concomitant primary testicular insufficiency. The patient underwent short-term treatment trials with low doses of either recombinant luteinizing hormone (LH) or human chorionic gonadotropin (hCG) in three consecutive treatment schemes, showing an equal efficacy in stimulating testosterone (T) increase. This is the first case of atypical, giant FSH-secreting pituitary adenoma with high FSH serum levels without signs of testicular hyperstimulation, in presence of hypogonadism with plausible combined primary and secondary etiology. Hypophysectomized patients may represent a good model to assess both pharmacodynamics and effective dose of LH and hCG in the male.     

The use of nativity data to estimate ethnic characteristics and patterns

Until recently, nativity data for the first and second generations (the foreign stock) have been the primary source of census information on white ethnic groups in the United States. With the development of an ancestry item, it is now possible to deal with all generations regardless of birthplace. The 1979 Current Population Survey provides a rare opportunity to cross-tabulate the results obtained from each system in order to determine the degree of overlap in the populations and the extent to which inferences about the social characteristics of ethnic groups are altered. The degree of overlap varies enormously among groups, but the results show that inferences based on nativity data are fairly close to those that would be obtained with the use of the ethnic ancestry item. This is an encouraging result for researchers obliged to use nativity data in working with earlier censuses.     

Likelihood-based risk estimation for variance-gamma models

Although the variance-gamma distribution is a flexible model for log-returns of financial assets, so far it has found rather limited applications in finance and risk management. One of the reasons is that maximum likelihood estimation of its parameters is not straightforward. We develop an EM-type algorithm based on Nitithumbundit and Chan (An ECM algorithm for skewed multivariate variance gamma distribution in normal mean–variance representation, arXiv:1504.01239, 2015) that bypasses the evaluation of the full likelihood, which may be difficult because the density is not in closed form and is unbounded for small values of the shape parameter. Moreover, we study the relative efficiency of our approach with respect to the maximum likelihood estimation procedures implemented in the VarianceGamma and ghyp R packages. Extensive simulation experiments and real-data analyses suggest that the multicycle ECM algorithm gives the best results in terms of root-mean-squared-error, for both parameter and value-at-risk estimation. The performance of the routines in the ghyp R package is similar but not as good, whereas the VarianceGamma package produces worse results, especially when the shape parameter is small.     

Confidence in selected institutions in 1975: An attempt at replication across two national surveys

A comparison of responses to four attitudinal items included in two national surveys reveals significant differences between surveys in the marginal distributions of all four items. These discrepancies are attributed to differences in survey ‘context’ (i.e., the nature of the questions which preceded the items of interest in the interview schedules). Despite the differences in marginal distributions, however, the four items showed identical relationships in both surveys to five background characteristics of respondents in 18 of 20 tests. Although the generalizability of these findings to other attitudinal items is an open question, they do suggest the inadvisability of combining data collected in surveys using markedly different interview schedules into a time series of subjective social indicators. Contextual effects are apparently less critical in cross-sectional analyses of survey data.