Asymptotic normality of MRPP statistics from invariance principles of u-statistics

Multi-response permutation procedures (MRPP) were recently introduced to test differences between a priori classified groups of objects ( Mielke, Berry Johnson, 1976; Mielke, 1979 ). The null distributions of the MRPP statistics were initially conjectured to be asymptotically normal for some specified conditions within the setting of a sequence of finite populations due to Madow ( 1948 ).

Asymptotic normality of a class of MRPP statistics (under the null hypothesis) is shown in two cases: (i) the setting which considers the populations to be the samples resulting from sequential independent identically distributed (i.i.d.) sampling (sampling from infinite populations) and (ii) the setting of a sequence of increasingly large finite populations (sampling from finite populations). The results are direct applications of the weak convergence of a U-statistic process in the i.i.d. case to a Brownian motion (Bhattacharyya and Sen, 1977) and of the weak convergence of a U-statistic process in the finite populations case to a Brownian bridge (Sen, 1972). The conditions are milder for the i.i.d. case than for the finite populations case. However, neither case provides a restriction of a practical consequence in applications of MRPP. In either case, convergence is shown to depend on the asymptotic ratios of the group sizes to the population size.     

Using High-Frequency Data in Dynamic Portfolio Choice

This article evaluates the economic benefit of methods that have been suggested to optimally sample (in an MSE sense) high-frequency return data for the purpose of realized variance/covariance estimation in the presence of market microstructure noise (Bandi and Russell, 2005a, 2008). We compare certainty equivalents derived from volatility-timing trading strategies relying on optimally-sampled realized variances and covariances, on realized variances and covariances obtained by sampling every 5 minutes, and on realized variances and covariances obtained by sampling every 15 minutes. In our sample, we show that a risk-averse investor who is given the option of choosing variance/covariance forecasts derived from MSE-based optimal sampling methods versus forecasts obtained from 5- and 15-minute intervals (as generally proposed in the literature) would be willing to pay up to about 80 basis points per year to achieve the level of utility that is guaranteed by optimal sampling. We find that the gains yielded by optimal sampling are economically large, statistically significant, and robust to realistic transaction costs.     

The Impact of Privatization on the Earnings of Restructured Workers: Evidence From the Oil Industry

We study the long-term impact of job displacement from a big state owned enterprise as a result of its privatization in a developing country. Our results suggest large reductions in earnings, which persist throughout the years. However, we also find that the displaced worker’s post-displacement earnings are in line with competitive market wages, and unrelated to sector of employment or to tenure losses, indicating that the long-term reduction in earnings as a result of displacement because of privatization can be traced to the loss of wage rents. Our results indicate that job displacement in SOEs may have very large redistributive implications for the workers involved but that this loss does not necessarily reflect the loss of specific human capital associated to these jobs.

An information theoretic approach to post randomization methods under differential privacy

Statistics and Computing - Post randomization methods are among the most popular disclosure limitation techniques for both categorical and continuous data. In the categorical case, given a...     

American Attitudes toward Guest Worker Policies

In this study we use data from a 2004 New York Times/CBS News national survey to analyze public opinion toward a guest worker program and to compare predictors of support for guest worker and general immigration policies. In general, Americans tend to be divided in their attitudes toward a guest worker program, although support for temporary worker policies is stronger when legalization for unauthorized immigrants is conditioned on certain requirements, and when the program is coupled with enhanced border security. The results of the bivariate probit analysis indicate that individuals who favor reducing the immigration level also tend to oppose instituting a guest worker program. Perceptions of the “costs” of immigration emerged as the most important determinant of individuals’ attitudes toward immigration policies; such beliefs contributed to opposition to a guest worker policy and support for reducing the immigration level. We also found that residents of high‐immigration states and Latinos were more likely to support a temporary worker program. However, these characteristics do not appear to influence individuals’ judgments about the number of immigrants who should be admitted to the United States. Findings regarding the impact of political partisanship and ideology on attitudes toward the two policies were more ambiguous.     

Aversion to inequality in Italy and its determinants

The main goal of this paper is to estimate the preferences of the Italian society towards equity in order to verify whether preferences (i) have changed across the years, and (ii) can be related to specific socio-demographic characteristics. Introducing equity concerns in the implementation of economic policies is a fundamental problem faced by both economists and policy makers. This paper uses a social welfare function à la Jorgenson and Slesnick to estimate societys aversion towards inequality by implement in a voting scheme for compiling individuals equity preferences in to a social choice by majority rule. The results show that preferences are highly polarized toward a low and a high concern for equity aversion and that this concern is significantly related with several sociodemographic characteristics. Among them, income plays an important role with richer people tending to favor less equity. Results also show that preferences towards equity have changed across the years.     

Internationalisation and outsourcing of operations and product development in the fashion industry

This paper investigates the choices in terms of internationalisation and outsourcing of operations and product development activities, as well as collaboration practices used within and across organisations, in different segments of the European fashion industry. Based on multiple, in-depth case studies from Italy, Germany and the UK, the paper shows that fashion companies adopt different configurations of operations and product development, i.e. integrated, collaborative and virtual, ranging from local-integrated models to global-full outsourcing of operations and product development activities. For each configuration, different collaboration practices are in use. Product line positioning and quality, firm size, sales volumes and technical complexity of the products are the key drivers determining the configuration choices and the adoption of certain collaboration practices.     

Fiducial Inferences for the Truncated Exponential Distribution

Lindqvist and Taraldsen (2005 Lindqvist , B. H. , Taraldsen , G. ( 2005 ). Monte Carlo conditioning on a sufficient statistic . Biometrika 92 : 451 – 464 .[Crossref], [Web of Science ®] , [Google Scholar]) introduced an interesting parametric family of distributions in the unit interval. In this note, inference procedures are given, both from the classical and the Bayesian view point. It is shown numerically through various examples that the posterior distribution for the parameter and the induced fiducial distribution are almost equivalent. The parametric family under study is a regular member of the Natural Exponential Family and so use of this fact permits induction of a unique fiducial in terms of the minimal sufficient statistic.     

The role of need for contraception in the evaluation of interventions to improve access to family-planning methods

A nonrandomized experiment carried out in Jharkhand, India, shows how the effects of interventions designed to improve access to family-planning methods can be erroneously regarded as trivial when contraceptive use is utilized as dependent variable, ignoring women's need for contraception. Significant effects of the intervention were observed on met need (i.e., contraceptive use by women who need contraception) but not on contraceptive use (i.e., contraceptive use by women who may or may not need contraception). Met need captures the woman's success in overcoming barriers to access to family planning, whereas contraceptive use confounds this construct with risk of pregnancy and fertility desires. Exceptions to this rule are identified.