Bayesiam simultaneous estimation for several multinomial distributions

A Bayesian method is proposed for estimating the cell probabilities of several multinomial distributions. Parameters of different distributions are taken to be a priori exchangeable. The prior specification is based upon mixtures of a hierarchical distribution, referred to as the multivariate “Dirichlet-Dirichlet” distribution. The analysis is facilitated by a multinomial approximation relating to the multinomial-Dirichlet distribution. The posterior estimates depend upon measures of entropy for the various distributions and shrink the individual observed proportions towards values obtained by pooling the data across the distributions. As well as incorporating prior information they are particularly useful when some of the cell frequencies are zero. We use them to investigate a numerical classification of males of various vocations, according to cause of death.     

Lifecycle effects on consumer financial product portfolios in South Africa: An exploratory analysis of four ethnic groups

This paper assesses ownership of 16 financial products by households in different lifecycle stages amongst four ethnic groups (Africans, Coloureds, Asians, and Whites) in South Africa. The lifecycle hypothesis indicates younger households should own more debt-related financial products, whereas households in intermediate lifecycle stages should own more financial products to accumulate assets; both these claims are disconfirmed for all groups. However, White households in intermediate household stages own more financial products than younger and older households, consistent with previously reported lifecycle findings in Western countries. Consistent with the literature on innovation adoption we find that younger, affluent and highly educated households amongst the other three ethnic groups tend to own more financial products than older Africans, Coloureds and Asians. These results indicate that innovation adoption literature may better describe financial product ownership in developing countries than the lifecycle hypothesis.     

Gambling Behaviors Among Oxford House Residents: A Preliminary Investigation

The present study investigated the prevalence of gambling behaviors among 71 individuals recovering from substance-dependent disorders and living in self-run recovery homes (Oxford Houses). Residents were given the South Oaks Gambling Screen to assess gambling behaviors and pathological gambling, and 19.7% of the sample was identified as having probable pathological gambling. These residents reported proportionately more involvement in a variety of gambling behaviors than other residents. Engagement in various gambling activities was consistent with previous investigations and suggested that self-run recovery homes such as Oxford Houses might be suitable referral sources for recovering persons who have comorbid gambling problems.     

非竞争型投入占用产出模型及其应用——中美贸易顺差透视(英文)

本文构建了一种能够反映中国加工贸易特点的非竞争(进口)型投入占用产出模型,提出了一个国家全部出口与分部门、分大类商品的单位出口对国内增加值和就业的拉动效应的计算方法,从数学上证明了出口总值等于出口商品所包含的完全国内增加值与完全进口额之和,并据此编制了2002年中美两国的非竞争(进口)型投入占用产出表,测算和分析了中美两国出口对各自国内增加值和就业的影响。     

Input-occupancy-output models of the non-competitive type and their application - an examination of the China-US trade surplus

本文构建了一种能够反映中国加工贸易特点的非竞争（进口）型投入占用产出模型,提出了一个国家全部出口与分部门、分大类商品的单位出口对国内增加值和就业的拉动效应的计算方法,从数学上证明了出口总值等于出口商品所包含的完全国内增加值与完全进口额之和,并据此编制了2002年中美两国的非竞争（进口）型投入占用产出表,测算和分析了中美两国出口对各自国内增加值和就业的影响。     

Gender Differences in Competition: Evidence From a Matrilineal and a Patriarchal Society

We use a controlled experiment to explore whether there are gender differences in selecting into competitive environments across two distinct societies: the Maasai in Tanzania and the Khasi in India. One unique aspect of these societies is that the Maasai represent a textbook example of a patriarchal society, whereas the Khasi are matrilineal. Similar to the extant evidence drawn from experiments executed in Western cultures, Maasai men opt to compete at roughly twice the rate as Maasai women. Interestingly, this result is reversed among the Khasi, where women choose the competitive environment more often than Khasi men, and even choose to compete weakly more often than Maasai men. These results provide insights into the underpinnings of the factors hypothesized to be determinants of the observed gender differences in selecting into competitive environments.     

Optimal and efficient semi-Latin squares

An (n×n)/k$(n\times n)/k$semi-Latin square is an n×n square array in which nk distinct symbols (representing treatments) are placed in such a way that there are exactly k   symbols in each cell (row–column intersection) and each symbol occurs once in each row and once in each column. Semi-Latin squares form a class of row–column designs generalising Latin squares, and have applications in areas including the design of agricultural experiments, consumer testing, and via their duals, human–machine interaction. In the present paper, new theoretical and computational methods are developed to determine optimal or efficient (n×n)/k$(n\times n)/k$ semi-Latin squares for values of n and k for which such semi-Latin squares were previously unknown. The concept of subsquares of uniform semi-Latin squares is studied, new applications of the DESIGN package for GAP are developed, and exact algebraic computational techniques for comparing efficiency measures of binary equireplicate block designs are described. Applications include the complete enumeration of the (4×4)/k$(4\times 4)/k$ semi-Latin squares for k=2,…,10$k=2,\dots ,10$, and the determination of those that are A-, D-, and E-optimal, the construction of efficient (6×6)/k$(6\times 6)/k$ semi-Latin squares for k=4,5,6$k=4,5,6$, and counterexamples to a long-standing conjecture of R.A. Bailey and to a similar conjecture of D. Bedford and R.M. Whitaker.     

Local Labor Market Characteristics and the Occupational Concentration of Different Sociodemographic Groups1

Abstract This paper analyzes the extent to which employment opportunities for different sociodemographic groups are concentrated in a limited number of occupations within their local labor market areas. Data from the STF-4 file of the 1980 Census of Population and Housing are used to measure the occupational concentration of these groups in 318 labor market areas (LMAs) in the United States. Regression analysis demonstrates the significance of local labor market characteristics for the occupational concentration of women and men and of whites and blacks. Gender differences in occupational concentration are strongly related to the differential effects of the industrial composition of the local labor market. Racial differences in occupational concentration are affected by the fact that working in larger, more densely populated LMAs is more significant for blacks than for whites.     

Managers' uses of models

This paper argues that management scientists need to understand how models are used by managers and correspondingly apply appropriate criteria to their own efforts. Types of models used by managers are discussed. Then an example is presented of how such understanding can be used to evaluate the worth of formal analysis. The evidence points to patterns of quite different inquiry and response by managers than have typically been envisioned by management scientists.