Influence measure for the L1 regression

Because outliers and leverage observations unduly affect the least squares regression, the identification of influential observations is considered an important and integrai part of the analysis. However, very few techniques have been developed for the residual analysis and diagnostics for the minimum sum of absolute errors, L₁ regression. Although the L₁ regression is more resistant to the outliers than the least squares regression, it appears that outliers (leverage) in the predictor variables may affect it. In this paper, our objective is to develop an influence measure for the L₁ regression based on the likelihood displacement function. We illustrate the proposed influence measure with examples.     

The Gamma-count distribution in the analysis of experimental underdispersed data

Event counts are response variables with non-negative integer values representing the number of times that an event occurs within a fixed domain such as a time interval, a geographical area or a cell of a contingency table. Analysis of counts by Gaussian regression models ignores the discreteness, asymmetry and heteroscedasticity and is inefficient, providing unrealistic standard errors or possibly negative predictions of the expected number of events. The Poisson regression is the standard model for count data with underlying assumptions on the generating process which may be implausible in many applications. Statisticians have long recognized the limitation of imposing equidispersion under the Poisson regression model. A typical situation is when the conditional variance exceeds the conditional mean, in which case models allowing for overdispersion are routinely used. Less reported is the case of underdispersion with fewer modeling alternatives and assessments available in the literature. One of such alternatives, the Gamma-count model, is adopted here in the analysis of an agronomic experiment designed to investigate the effect of levels of defoliation on different phenological states upon the number of cotton bolls. Data set and code for analysis are available as online supplements. Results show improvements over the Poisson model and the semi-parametric quasi-Poisson model in capturing the observed variability in the data. Estimating rather than assuming the underlying variance process leads to important insights into the process.     

Small area estimation for longitudinal surveys

Over the last few years many studies have been carried out in Italy to identify reliable small area labour force indicators. Considering the rotated sample design of the Italian Labour Force Survey, the aim of this work is to derive a small area estimator which borrows strength from individual temporal correlation, as well as from related areas. Two small area estimators are derived as extensions of an estimation strategies proposed by Fuller (1990) for partial overlap samples. A simulation study is carried out to evaluate the gain in efficiency provided by our solutions. Results obtained for different levels of autocorrelation between repeated measurements on the same outcome and different population settings show that these estimators are always more reliable than the traditional composite one, and in some circumstances they are extremely advantageous.The present paper is financially supported by Murst-Cofin (2001) Lutilizzo di informazioni di tipo amministrativo nella stima per piccole aree e per sottoinsiemi della popolazione (National Coordinator Prof. Carlo Filippucci).     

Predicting Severity of Foreign Body Injuries in Children in Upper Airways: An Approach Based on Regression Trees

The entry of a small item into the upper airways is one of the leading causes of injuries in children up to 14 years old. The aim of this study is to characterize types of objects causing choking along with the features of the children involved in the accident and compare results with current standards. The European Survey on Foreign Bodies Injuries Study (ESFBI) collected data on foreign body injuries from 19 European countries. The data from ESFBI were selected according to the ICD-9-CM codes 933 (foreign body in the pharynx and larynx) and 934 (foreign body in the trachea, bronchi, and lungs). Both a classification tree and a linear discriminant analysis (LDA) have been set up to predict the probability that an injured child experiences a hospitalization. The classification tree provides flowchart-type decision rules and allows for analyzing the impact of the item features, the children characteristics, and the circumstances of the accidents on the severity of the foreign body injuries. Results showed that children younger than 3.5 who are involved in an accident have a high probability to experience a hospitalization.     

Inflated beta distributions

This paper considers the issue of modeling fractional data observed on [0,1), (0,1] or [0,1]. Mixed continuous-discrete distributions are proposed. The beta distribution is used to describe the continuous component of the model since its density can have quite different shapes depending on the values of the two parameters that index the distribution. Properties of the proposed distributions are examined. Also, estimation based on maximum likelihood and conditional moments is discussed. Finally, practical applications that employ real data are presented.     

A Gender Lens on Quality of Life: The Role of Sense of Community,Perceived Social Support,Self-Reported Health and Income

Quality of life (QoL) refers to a subjective evaluation that is embedded in a cultural, social and environmental context. It is a multidimensional concept and its assessment covers four domains: physical health, psychological health, social relationships, and environment. Although many studies report on QoL, literature rarely addressed the question of the QoL predictors from a gender perspective. Present study aimed at investigating gender differences in the determinants of QoL. Specifically, gender was considered as a moderator in the relationship between predictors of QoL (i.e. socio-demographic characteristics, perceived health, income, social support and sense of community) and each dimension of QoL. 654 Italian adults participated in the study. Results show that men outscore women on the physical, the psychological and the environmental domains of QoL. Considering determinants of QoL, sense of community and self-reported health operate in a similar fashion for both genders. On the contrary, social support is more predictive for women’s QoL, whereas the income level is more significant for men’s QoL. Implications are discussed.     

Psychometric Properties of the Medical Outcome Study Social Support Survey with a General Population Sample of Undergraduate Students

Among non-clinical populations, perceived social support is an important factor in health maintenance and well-being. Among measures that purport to assess perceived social support, the Medical Outcomes Study Social Support Survey (MOS-SSS) is based on a strong conceptual framework and has been subjected to a rigorous psychometric evaluation. Since no studies have investigated its psychometric properties with a young, non-clinical population, the purpose of this study is to investigate the psychometric properties (construct validity, internal consistency, and test–retest reliability) of an Italian version of the MOS-SSS with a non-clinical population sample. A convenience sample of 485 undergraduate students (73.0 % female; mean age = 21.81 ± 1.52) has been recruited. With regards to scale dimensionality, the best fit measurement model found support for the four subscales proposed by the original version: emotional and informational support, tangible support, positive social interactions, and affectionate support (χ ²/df = 4.49; CFI = .92; TLI = .91; RMSEA = .08). MOS-SSS subscales showed good internal consistency (Cronbach’s alpha for the subscales ranged from .848 to .939). Significant correlations were found with measures of psychological well-being (Ryff’s Scales of Psychological Well-Being) and depression (Beck-Depression Inventory-II). Test–retest stability was tested by examining a subsample (N = 225) over a 10-week period (correlation coefficients for the subscales ranged from .502 to .579). The findings suggest that MOS-SSS presents good psychometric characteristics with a young general population sample. Therefore, the MOS-SSS seems to be a psychometrically sound measure for the evaluation of perceived social support among young non-clinical populations.     

Social security privatisation: the lessons from the Chilean experience for other Latin American countries and the USA

The purpose of this article is to analyse the economic and social implications of the privatisation of social security in Chile and to draw some lessons from the Chilean experience. The focus of the analysis is on the costs and benefits of the privatised system and its impact on social equity. Thus, the main section of the article is devoted to the analysis of the 20-year-old Chilean experience. This section is followed by a discussion of privatisation in other Latin American countries and the impact that World Bank's policies have had on the region. The last section looks at the lessons for the United States and argues against the establishment of a partially private plan in the USA.