Factor analysis for ranked data with application to a job selection attitude survey

Summary.  Factor analysis is a powerful tool to identify the common characteristics among a set of variables that are measured on a continuous scale. In the context of factor analysis for non-continuous-type data, most applications are restricted to item response data only. We extend the factor model to accommodate ranked data. The Monte Carlo expectation–maximization algorithm is used for parameter estimation at which the E-step is implemented via the Gibbs sampler. An analysis based on both complete and incomplete ranked data (e.g. rank the top q out of k items) is considered. Estimation of the factor scores is also discussed. The method proposed is applied to analyse a set of incomplete ranked data that were obtained from a survey that was carried out in GuangZhou, a major city in mainland China, to investigate the factors affecting people's attitude towards choosing jobs.     

Gender,lineage, and fertility‐related outcomes in Ghana

A growing literature examines the empirical relationship between the joint reproductive preferences of marital partners and reproductive outcomes in Africa. Less explored is how spousal power in decision making may be influenced by lineage type. Using pooled data from Ghana, we investigate how lineage affects gendered reproductive decision outcomes and find some evidence that matrilineal women are more able than nonmatrilineal women to translate their reproductive preferences into action consistent with their goals.     

HEAVY-TAILED-DISTRIBUTED THRESHOLD STOCHASTIC VOLATILITY MODELS IN FINANCIAL TIME SERIES

To capture mean and variance asymmetries and time‐varying volatility in financial time series, we generalize the threshold stochastic volatility (THSV) model and incorporate a heavy‐tailed error distribution. Unlike existing stochastic volatility models, this model simultaneously accounts for uncertainty in the unobserved threshold value and in the time‐delay parameter. Self‐exciting and exogenous threshold variables are considered to investigate the impact of a number of market news variables on volatility changes. Adopting a Bayesian approach, we use Markov chain Monte Carlo methods to estimate all unknown parameters and latent variables. A simulation experiment demonstrates good estimation performance for reasonable sample sizes. In a study of two international financial market indices, we consider two variants of the generalized THSV model, with US market news as the threshold variable. Finally, we compare models using Bayesian forecasting in a value‐at‐risk (VaR) study. The results show that our proposed model can generate more accurate VaR forecasts than can standard models.     

Testing symmetry under a skew Laplace model

We develop tests of hypothesis about symmetry based on samples from possibly asymmetric Laplace distributions and present exact and limiting distribution of the test statistics. We postulate that the test statistic derived under the Laplace model is a rational choice as a measure of skewness and can be used in testing symmetry for other, quite general classes of skew distributions. Our results are applied to foreign exchange rates for 15 currencies.     

Flipping and ex post aggregation

We show that Bayesian ex post aggregation is unstable with respect to refinements. Suppose a group of Bayesians use ex post aggregation. Since it is a joint problem, each agent's problem is captured by the same model, but probabilities and utilities may vary. If they analyze the same situation in more detail, their refined analysis should preserve their preferences among acts. However, ex post aggregation could bring about a preference reversal on the group level. Ex post aggregation thus depends on how much information is used and may keep oscillating (“flipping”) as one keeps adding more information. Received: 16 April 2002/Accepted: 27 May 2002     

Ethnic preferences and perceptions among Asian and White British middle school children

Asian and White middle school children were shown photographs of unknown Afro-Caribbean, Asian, and White individuals of approximately the same age as themselves, and asked which one wax most like them, which one they would prefer to be, which ones they would prefer to engage in various activities with, and finally, to allocate positive and negative traits to the three groups or to nobody. A similar majority of both Asian and While children selected an own-race photograph as being most like them, but only about a half selected the own-race photograph as the one they would most like to he. For sharing activities, children showed a strong own-tender preference, followed by an own-race preference. White children stated a greater preference for sharing activities with White children, then with Afro-Caribbean children, and least with Asian children. Asian children preferred Asian and White children the most, Afro-Caribbean the least. On a stereotypes test, similar trends were obtained; White children evaluated While children highest and Asian lowest; Asian children tended to evaluate Asian children highest but to a nonsignificant extent. The relative proportion of Asian/White children in school appeared to have little systematic influence on the results, thus arguing against the contact hypothesis of prejudice reduction in its simple form.     

Female Victim Perceptions of the Causes of Male Spouse Abuse*

Victims of spouse abuse were interviewed concerning their views of why their husbands were abusive. It was hypothesized that by concentrating on one specific characteristic of this kind previously undocumented patterns of response would be elicited from the subjects. It was concluded that the women's reasons for the violence perpetrated by their spouses serve as justification for the abusers’actions and legitimize maintenance of the relationship.     

The Effects of ROTC Program Participation on Socioeconomic Status and Life Satisfaction*

Using mail survey data based on a stratified systematic sample [N = 686] of 1983–1988 graduates of a medium-sized state university, this research evaluates whether ROTC program participation constitutes an independent source of human capital in civilian labor markets by comparing postgraduate earnings (annual income), prestige and authority, and life satisfaction of ROTC program participants with those of nonparticipants. The results revealed no statistically significant ROTC program participation effects, independent of subsequent military status. ROTC program participation paid off in terms of occupational prestige and authority for those on active duty, but not for those in national guard or reserve units. Neither ROTC participation nor current military status affected income or life satisfaction levels.