A Comparison of Bayesian and Sampling Theory Inferences in a Probit Model

HE PROBIT MODEL IS A POPULAR DEVICE for explaining binary choice decisions in econometrics. It has been used to describe choices such as labor force participation, travel mode, home ownership, and type of education. These and many more examples can be found in papers by Amemiya (1981) and Maddala (1983). Given the contribution of economics towards explaining such choices, and given the nature of data that are collected, prior information on the relationship between a choice probability and several explanatory variables frequently exists. Bayesian inference is a convenient vehicle for including such prior information. Given the increasing popularity of Bayesian inference it is useful to ask whether inferences from a probit model are sensitive to a choice between Bayesian and sampling theory techniques. Of interest is the sensitivity of inference on coefficients, probabilities, and elasticities. We consider these issues in a model designed to explain choice between fixed and variable interest rate mortgages. Two Bayesian priors are employed: a uniform prior on the coefficients, designed to be noninformative for the coefficients, and an inequality restricted prior on the signs of the coefficients. We often know, a priori, whether increasing the value of a particular explanatory variable will have a positive or negative effect on a choice probability. This knowledge can be captured by using a prior probability density function (pdf) that is truncated to be positive or negative. Thus, three sets of results are compared:those from maximum likelihood (ML) estimation, those from Bayesian estimation with an unrestricted uniform prior on the coefficients, and those from Bayesian estimation with a uniform prior truncated to accommodate inequality restrictions on the coefficients.

Closing the gender gap in Bangladesh: Inequality in education, employment and earnings

Assesses the status of women in Bangladesh by analysing the dynamics of female participation in labour force and education as well as gender earnings differentials at the macro level. The study finds evidence of growing commercialisation of women’s work in Bangladesh. Although the bulk of the female labour force is engaged in self-employment activities in the rural area or in low-skilled textile and readymade garment industries in the urban area, women’s participation in high-skill and entrepreneurial jobs as well as various decision-making bodies is also on the rise. While the gender wage differentials have been considerably reduced in many industries, in general women tend to be paid less than men. There have been remarkable improvements in women’s educational attainments compared to men. Further, female access to education is found to be highly correlated with overall female labour force participation, and relative to male participation. The overall results are suggestive of an improvement in the status of women in Bangladesh.

Risk indicators for increased probing depth in an isolated population in Brazil

Background: The aim of this study was to assess the prevalence, extent, and severity of probing depth (PD) and to investigate the associations between demographic, socioeconomic, and behavioral risk indicators and PD in a periodontally untreated and isolated population in Brazil. Methods: The target population consisted of all individuals aged >= 12 years as identified by a census. Consenting participants were submitted to a full-mouth clinical examination of six sites per tooth and were interviewed using a structured written questionnaire. Results: Among the 214 subjects who were interviewed and clinically examined, PD >= 4 mm was observed in 54% to 83% of the subjects, depending on age, whereas the age-dependent prevalence of PD :6 mm ranged from 5% among 12- to 19-year-olds to 50% among 40- to 49-year-olds, decreasing to 40% among subjects >= 50 years of age. Multivariate analyses identified supragingival calculus (odds ratio [OR] = 5.4 to 10.3; 95% confidence intervals [CIs]: 2.5 to 11.6 and 4.0 to 26.2 for 20% to 50% and > 50% of the sites, respectively) as a risk indicator for PD A mm, whereas age :40 years (OR = 9.0; 95% CI: 1.7 to 48.5), being a moderate/heavy smoker (OR = 3.7; 95% CI: 1.4 to 10. 1), and having supragingival calculus in 20% to 50% of sites (OR = 6.8; 95% CI: 1.4 to 32.4) or in >50% of sites (OR = 15.3; 95% CI: 3.2 to 73.6) were risk indicators for PD >= 6 mm. Having undergone urgency dental treatment was a protective factor for PD A and >= 6 mm (OR = 0.4; 95% CI: 0.2 to 0.8). Conclusions: Increased PD is highly prevalent in this isolated population. Behavioral factors played a significant role as risk indicators for increased PD in this isolated population.