A partial dependence factorial analysis to deal with selection bias in observational studis

This thesis presents a creative and practical approach to dealing with the problem of selection bias. Selection bias may be the most important vexing problem in program evaluation or in any line of research that attempts to assert causality. Some of the greatest minds in economics and statistics have scrutinized the problem of selection bias, with the resulting approaches – Rubin’s Potential Outcome Approach(Rosenbaum and Rubin,1983; Rubin, 1991,2001,2004) or Heckman’s Selection model (Heckman, 1979) – being widely accepted and used as the best fixes. These solutions to the bias that arises in particular from self selection are imperfect, and many researchers, when feasible, reserve their strongest causal inference for data from experimental rather than observational studies. The innovative aspect of this thesis is to propose a data transformation that allows measuring and testing in an automatic and multivariate way the presence of selection bias. The approach involves the construction of a multi-dimensional conditional space of the X matrix in which the bias associated with the treatment assignment has been eliminated. Specifically, we propose the use of a partial dependence analysis of the X-space as a tool for investigating the dependence relationship between a set of observable pre-treatment categorical covariates X and a treatment indicator variable T, in order to obtain a measure of bias according to their dependence structure. The measure of selection bias is then expressed in terms of inertia due to the dependence between X and T that has been eliminated. Given the measure of selection bias, we propose a multivariate test of imbalance in order to check if the detected bias is significant, by using the asymptotical distribution of inertia due to T (Estadella et al. 2005) , and by preserving the multivariate nature of data. Further, we propose the use of a clustering procedure as a tool to find groups of comparable units on which estimate local causal effects, and the use of the multivariate test of imbalance as a stopping rule in choosing the best cluster solution set. The method is non parametric, it does not call for modeling the data, based on some underlying theory or assumption about the selection process, but instead it calls for using the existing variability within the data and letting the data to speak. The idea of proposing this multivariate approach to measure selection bias and test balance comes from the consideration that in applied research all aspects of multivariate balance, not represented in the univariate variable- by-variable summaries, are ignored. The first part contains an introduction to evaluation methods as part of public and private decision process and a review of the literature of evaluation methods. The attention is focused on Rubin Potential Outcome Approach, matching methods, and briefly on Heckman’s Selection Model. The second part focuses on some resulting limitations of conventional methods, with particular attention to the problem of how testing in the correct way balancing. The third part contains the original contribution proposed , a simulation study that allows to check the performance of the method for a given dependence setting and an application to a real data set. Finally, we discuss, conclude and explain our future perspectives.

The factorial analysis of human ability.

Errata slip inserted.

Career-path analysis using optimal matching and self-organizing maps

This paper is devoted to the analysis of career paths and employability. The state-of-the-art on this topic is rather poor in methodologies. Some authors propose distances well adapted to the data, but are limiting their analysis to hierarchical clustering. Other authors apply sophisticated methods, but only after paying the price of transforming the categorical data into continuous, via a factorial analysis. The latter approach has an important drawback since it makes a linear assumption on the data. We propose a new methodology, inspired from biology and adapted to career paths, combining optimal matching and self-organizing maps. A complete study on real-life data will illustrate our proposal.

Validation of order rank scales based on compositional data analysis: a proposal

Usually, psychometricians apply classical factorial analysis to evaluate construct validity of order rank scales. Nevertheless, these scales have particular characteristics that must be taken into account: total scores and rank are highly relevant

Caracterización de poblaciones nativas de maíz mediante Análisis de Procrustes Generalizado y Análisis Factorial Múltiple

El establecimiento de relaciones entre taxones es un paso esencial en el proceso de catalogación y evaluación del material conservado en un Banco de Germoplasma. Existen distintos métodos de evaluación en función del tipo de caracteres estudiados. Cuando el registro de caracteres se repite en el tiempo y en distintos ambientes, se debe separar la variabilidad intrínsecamente genética entre los taxones de aquella que se debe al ambiente, y más aún, de la posible variabilidad debida a la interacción genotipo*ambiente para el posterior establecimiento de relaciones puramente filogenéticas. En el presente trabajo se estudia comparativamente la factibilidad de aplicación de dos estrategias de análisis estadístico para dar solución a este problema. La primera corresponde al análisis tradicional donde se realiza un Análisis de Componentes Principales sobre los caracteres promedios a lo largo de los diferentes ambientes; y la segunda son métodos más complejos en los cuales cada dato es originado por tres modos: individuos, variables y condiciones ambientales, tales como el Análisis Factorial Múltiple y el Análisis de Procrustes Generalizado. Si bien las configuraciones resultantes fueron todas equivalentes, los métodos de tres vías permiten la interpretación de la interacción genotipo*ambiente.

Factorial structure and reliability of a perceived influence on selection of a specialized plan of studies, IPEP, in secondary school students of Chillan, Chile

To evaluate these factors, the scale of perceived influences on the election of a specialized plan of studies, IPEP, was built and in this study its factorial structure and reliability were evaluated. The instrument was applied to 115 students, chosen by quote sampling. They were students of a subsidized private secondary school from the city of Chillan, Chile. An exploratory factorial analysis identified eight factors in the scale IPEP: Academic projection, Personal development, Maintenance of the social environment, Academic requirements, Satisfaction of others' expectations, Vocational information, Image of the plan and Family pressure. The results present an initial factorial structure, that empirically and theoretically adequate, whose factors were reliable and conceptually useful. These factors distinguish psychogenic and sociogenic aspects of the vocational process, and allow to initiate diagnostic and investigative actions in relation to this early vocational election that is established in secondary schools of the Chilean educational system

Factorial structure and reliability of a perceived influence on selection of a specialized plan of studies, IPEP, in secondary school students of Chillan, Chile

To evaluate these factors, the scale of perceived influences on the election of a specialized plan of studies, IPEP, was built and in this study its factorial structure and reliability were evaluated. The instrument was applied to 115 students, chosen by quote sampling. They were students of a subsidized private secondary school from the city of Chillan, Chile. An exploratory factorial analysis identified eight factors in the scale IPEP: Academic projection, Personal development, Maintenance of the social environment, Academic requirements, Satisfaction of others' expectations, Vocational information, Image of the plan and Family pressure. The results present an initial factorial structure, that empirically and theoretically adequate, whose factors were reliable and conceptually useful. These factors distinguish psychogenic and sociogenic aspects of the vocational process, and allow to initiate diagnostic and investigative actions in relation to this early vocational election that is established in secondary schools of the Chilean educational system

Factorial structure and reliability of a perceived influence on selection of a specialized plan of studies, IPEP, in secondary school students of Chillan, Chile

To evaluate these factors, the scale of perceived influences on the election of a specialized plan of studies, IPEP, was built and in this study its factorial structure and reliability were evaluated. The instrument was applied to 115 students, chosen by quote sampling. They were students of a subsidized private secondary school from the city of Chillan, Chile. An exploratory factorial analysis identified eight factors in the scale IPEP: Academic projection, Personal development, Maintenance of the social environment, Academic requirements, Satisfaction of others' expectations, Vocational information, Image of the plan and Family pressure. The results present an initial factorial structure, that empirically and theoretically adequate, whose factors were reliable and conceptually useful. These factors distinguish psychogenic and sociogenic aspects of the vocational process, and allow to initiate diagnostic and investigative actions in relation to this early vocational election that is established in secondary schools of the Chilean educational system

Analysis of factors influencing the physical, chemical and sensorial properties of Serra da Estrela cheeses

The objective of this study was to evaluate the chemical, color, textural, and sensorial characteristics of Serra da Estrela cheese and also to identity the factors affecting these properties, namely thistle ecotype, place of production, dairy and maturation. The results demon- strated that the cheeses lost weight mostly during the first stage of maturation, which was negatively correlated with moisture content, being this also observed for fat and protein contents. During maturation the cheeses became darker and with a yellowish coloration. A strong corre- lation was found between ash and chlorides contents, being the last directly related to the added salt in the manufacturing process. The flesh firmness showed a strong positive correlation with the rind harness and the firmness of inner paste. Stickiness was strongly related with all the other textural properties being indicative of the creamy nature of the paste. Adhesiveness was posi- tively correlated with moisture content and negatively correlated with maturation time. The trained panelists liked the cheeses, giving high overall assessment scores, but these were not significantly correlated with the physicochemical properties. The salt differences between cheeses were not evident for the panelists, which was corroborated by the absence of correlation between the perception of saltiness and the analyzed chlorides con- tents. The Factorial Analysis of the chemical and physical properties evidenced that they could be explained by two factors, one associated to the texture and the color and the other associated with the chemical properties. Finally, there was a clear influence of the thistle ecotype, place of production and dairy factors in the analyzed properties.

Construção e validação de uma escala multi-factorial de motivação no trabalho (mult-moti)

Esta investigação tem como objectivo a construção e validação de uma Escala MultiFactorial de Motivação no Trabalho para a população portuguesa. A ausência de instrumentos para medir várias dimensões da motivação levou ao desenvolvimento e elaboração desta escala de motivação. A escala integra 28 itens decorrentes de uma pesquisa teórica que contempla algumas teorias da motivação. Participaram nos estudos de validação da escala 444 colaboradores de empresas de novas tecnologias de ambos os sexos, com idades compreendidas entre os 19 e os 34 anos. A escala apresenta bons índices de consistência interna (valores entre 0.72 e 0.84) e uma análise factorial que revelou a existência de uma estrutura tetrafactorial com 49% de variância explicada: motivação com a organização do trabalho, motivação com realização e poder, motivação de desempenho e motivação associada ao envolvimento. Esperase ainda que novos estudos possam ser desenvolvidos a partir desta mesma escala.

The effect of consumer education on unit price usage : an early exploratory study

Consumer awareness and usage of Unit Price (UP) information continues to hold academic interest. Originally designed as a device to enable shoppers to make comparisons between grocery products, it is argued consumers still lack a sufficient understanding of the device. Previous research has tended to focus on product choice, effect of time, and structural changes to price presentation. No studies have tested the effect of UP consumer education on grocery shopping expenditure. Supported by distributed learning theories, this is the first study to condition participants over a twenty week period, to comprehend and employ UP information while shopping. A 3x5 mixed factorial design was employed to collect data from 357 shoppers. A 3 (Control, Massed, Spaced) x 5 (Time Point: Week 0, 5, 10, 15 and 20) mixed factorial analysis of variance (ANOVA) was performed to analyse the data. Preliminary results revealed that the three groups differed in their average expenditure over the twenty weeks. The Control group remained stable across the five time points. Results indicated that both intensive (Massed) and less intensive (Spaced) exposure to UP information achieved similar results, with both group reducing average expenditure similarly by Week 5. These patterns held for twenty weeks, with conditioned groups reducing their grocery expenditure by over 10%. This research has academic value as a test of applied learning theories. We argue, retailers can attain considerable market advantages as efforts to enhance customers’ knowledge, through consumer education campaigns, can have a positive and strong impact on customer trust and goodwill toward the organisation. Hence, major practical implications for both regulators and retailers exist.

Escala de Creencias Post-Críticas : análisis psicométrico para su aplicación al estudio de la religiosidad en Argentina

Resumen: Se analizan las propiedades psicométricas de la escala de creencias post-críticas (PCBS) en una muestra de 410 ciudadanos de 18 a 55 años de Córdoba/Argentina, seleccionados a partir de un muestreo no aleatorio. La escala fue traducida para el contexto local. A partir del uso complementario de Escalamiento Multidimensional y Análisis Factorial de componentes principales, se replican las dos dimensiones constitutivas de la PCBS (inclusión-exclusión en la trascendencia e interpretación literal-simbólica de los contenidos religiosos) y las cuatro sub-escalas propuestas: Crítica Externa, Segunda Ingenuidad, Ortodoxia, y Relativismo. El estudio reporta los índices de fiabilidad y la validez externa para cada una de éstas, y se discuten cuestiones operativas y conceptuales de su adecuación en Argentina.

Las Tecnologías de la Información y la Comunicación en la gestión de tesorería: modelo explicativo

[ES] En el presente trabajo se analiza el uso de las TIC (Tecnologías de la Información y la Comunicación) en las responsabilidades de la gestión de la tesorería, tomando como referencia para su estudio las empresas de la CAPV (Comunidad Autónoma del País Vasco). Los resultados indican que las TIC más utilizadas por las empresas en operaciones financieras son el software financiero, Internet y la banca electrónica. Además, estos resultados han permitido desarrollar un modelo explicativo del uso de las TIC en las principales funciones del tesorero, como son la gestión de cobros y pagos, gestión de la liquidez, previsiones de tesorería a corto plazo, gestión de saldos bancarios en fecha valor, negociación con entidades financieras, gestión de la financiación del déficit de tesorería, gestión de la colocación de puntas de tesorería y gestión de riesgos de tipo de interés y tipo de cambio.

DUAQUAL: calidad percibida por docentes y alumnos en la gestión universitaria

[ES] El proceso de Bolonia ha remarcado una perspectiva institucional en la preocupación por la gestión de la calidad del servicio prestado en las universidades y otras instituciones de enseñanza superior. La calidad del servicio en la educación superior no se centra exclusivamente en el proceso de enseñanza- aprendizaje y en la relación entre docente y discente, sino que debe estar también garantizada en el servicio prestado por las bibliotecas universitarias, los servicios de acción social, los servicios académicos y las secretarías departamentales.