Ana Sousa Ferreira

A Population-Based Assessment of Midlife Portuguese Women's Experience of Perimenopause and Menopause

The frequency of changes experienced by menopausal women is variable in different cultures. It is our purpose to identify the symptoms that Portuguese women consider to be related to menopause. We also wish to evaluate the relations between these symptoms and menopausal status, sociodemographic and lifestyle factors, and medication—menopausal hormone therapy (MHT) and psychotropics. In women with a low educational level, the frequency of symptoms and the consumption of psychotropic medication is higher, and the practice of exercise is lower, as is the use of MHT. Our results may be useful in providing guidance to health care professionals.

Enhancing the selection of a model-based clustering with external categorical variables

In cluster analysis, it can be useful to interpret the partition built from the data in the light of external categorical variables which are not directly involved to cluster the data. An approach is proposed in the model-based clustering context to select a number of clusters which both fits the data well and takes advantage of the potential illustrative ability of the external variables. This approach makes use of the integrated joint likelihood of the data and the partitions at hand, namely the model-based partition and the partitions associated to the external variables. It is noteworthy that each mixture model is fitted by the maximum likelihood methodology to the data, excluding the external variables which are used to select a relevant mixture model only. Numerical experiments illustrate the promising behaviour of the derived criterion.

A Comparative Study on Discrete Discriminant Analysis through a Hierarchical Coupling Approach

In discrete discriminant analysis the high-dimensionality problem often causes discriminant methods to perform poorly, specially in the multiclass case. The Hierarchical Coupling Model (HIERM) enables a reduction of the multiclass problem into several biclass problems embedded in a binary tree. With this approach, at each level of the tree, the basic affinity coefficient is used to select the new couple of classes among all possible forms of merging the original classes. After identifying the pair of classes to be considered, the decision rule for this biclass problem is based on the combining model that minimizes the error rate. The performance of this model leads to a considerable improvement in the misclassification error rate. Furthermore, its representation is appealing which makes it easily interpretable. In this study we propose to explore the comparison of the HIERM model with other models where the choice of the decomposition at each level of the binary tree among all possible forms of merging is made using one of the traditional similarity coefficients in Cluster Analysis. The performance of HIERM and the new models is compared on real data.

Discrete Discriminant Analysis: The Performance of Combining Models by a Hierarchical Coupling Approach

We are concerned with combining models in discrete discriminant analysis in the multiclass (K > 2) case. Our approach consists of decomposing the multiclass problem in several biclass problems embedded in a binary tree. The affinity coefficient (Matusita (1955); Bacelar-Nicolau (1981,1985)) is proposed for the choice of the hierarchical couples, at each level of the tree, among all possible forms of merging. For the combination of models we consider a single coefficient: a measure of the relative performance of models - the integrated likelihood coefficient (Ferreira et al., 1999)) and we evaluate its performance.

Intrinsic and extrinsic religious orientation in Portuguese Catholics

ABSTRACT The opposition between intrinsic (I) and extrinsic (E) religious motivation was operationalised by Allport and Ross through a Religious Orientation Scale (ROS). However, empirical studies using the ROS or other derived instruments have not always been able to confirm this clear opposition. This study presents the results of the Portuguese version of the Age-Universal I/E Scale and of a Current Religious Practice Scale in four convenience community samples of the Portuguese population (global N = 932). Exploratory factor analysis enables the definition of three factors. Factor 1 groups I and Extrinsic Personal (Ep) items and is similar to the first factor obtained in studies on European non-Protestant populations. However, confirmatory analysis suggests that the I and Ep dimensions can be distinguished from each other, although they are very closely related. The difference between these two dimensions was clearer in the subgroup of practising Catholics.

The effect of color on the production of responses to Rorschach cards VIII, IX, and X in age groups of 11-12 and 15-16 years.

The effect of color on the production of responses to the Rorschach task has been considered by investigators from 2 different positions: (a) that color has little effect on the production of responses, and (b) that color increases the number of responses. Some previous results found by the current investigators have supported the first position for the last 3 fully colored Rorschach cards (VIII, IX, and X), in children from 5 to 12 years old. Other studies of ours, however, have confirmed the second position for these same cards with a group of young adults 17 to 23 years old. As there was no increase of responses up to age 12, for this study we hypothesized a developmental effect in adolescence such that there would be an increase in the production of responses to the colored Rorschach cards at the age of 15 to 16 years, and this is what the results indicate. From a pragmatic standpoint, these results imply a revision of interpretive meaning for the Color and Affective Ratio variables in childrens protocols. Our results also indicate that color cannot be regarded as a means of expression of affect at age 11 to 12 like it will be from age 15 to 16 and on.

Selection of variables in Discrete Discriminant Analysis

Summary In Discrete Discriminant Analysis one often has to deal with dimensionality problems. In fact, even a moderate number of explanatory variables leads to an enormous number of possible states (outcomes) when compared to the number of objects under study, as occurs particularly in the social sciences, humanities and health-related elds. As a consequence, classi cation or discriminant models may exhibit poor performance due to the large number of parameters to be estimated. In the present paper, we discuss variable selection techniques which aim to address the issue of dimensionality. We speci cally perform classi cation using a combined model approach. In this setting, variable selection is particularly pertinent, enabling the handling of degrees of freedom and reducing computational cost.

Comparison of Multivariate Analysis Methodologies in a Palliative Care Setting

Summary This study is focused on measuring the quality and the satisfaction with the palliative care provided to oncology patients in domicile. The SERVQUAL methodology adapted for the Portuguese context was used to evaluate the quality of palliative care and patient satisfaction. The Portuguese SERVQUAL questionnaire is composed of five perception scales and two questionnaires, one about the patient and another about the caregiver. The data analysis presented is the analysis of the answers to the five perception scales, composed of partial ordered variables, evaluating different aspects of quality and satisfaction.The data was analysed comparing metric and symbolic approaches, using Principal Component Analysis Methods and Agglomerative Hierarchical Cluster Analysis Models. The results suggest that a symbolic approach provides a more comprehensive analysis for this kind of data.

Discriminant Analysis in Career Studying “Decision/Indecision”: The Career Factors Inventory (CFI) as a Diagnostic Measure

Literature has shown that, nowadays, a multidimensional approach to decision-making has become prioritized. The Careers Factor Inventory (CFI) is, in fact, a multidimensional measurement instrument for evaluating career indecision, which may be useful in the diagnosis of adaptation behaviors in terms of career decision versus indecision. This study emerges as a follow-up to a previous study which used the CFI on a sample of university students in which this measurement instrument was found to be capable of distinguishing Low decided vs. Highly decided groups and to evaluate the discriminatory capacity of the CFI scales. It is the aim, here, to further analyse the results obtained in such study with a view to grounding the importance of the use of this Inventory as an instrument for distinguishing people who present different decision levels in relation to their careers. In this study, 494 university students from a number of higher education establishments and courses are part of the afore mentioned Low decided and Highly decided groups. The collected data were analysed by means of Discrete Discriminant Analysis models and corroborate the discriminant power of the Inventory and its use as a diagnostic instrument in the psychological intervention of career counseling and development.

Depressive vulnerability in women with Alzheimer's disease: Relationship with personality traits and abnormal personality dimensions

BACKGROUND This study sought to determine the evaluation of current and pre-morbid depressive vulnerability dimensions in Alzheimers disease. Sidney Blatt´s personality developmental perspective, the Five-Factor model and Axis II personality disorders were taken as references. METHODS The study was conducted with two groups which were assessed using the Depressive Experiences Questionnaire, the NEO-FFI and the Personality Diagnostic Questionnaire-4+, in the form of individual interview sessions. Current personality measure: Alzheimers disease Group, consisting of 44 female participants (MAge = 81.36 years); Pre-morbid personality measure: Alzheimers disease Group Informants (n = 40). RESULTS Self-Criticism personality vulnerability is a general indicator of psychopathology. In pre-morbidity, Neuroticism (β = 0.41), Agreeableness (β = -0.63) and Conscientiousness (β = -0.08) predicted Self-Criticism, explaining 64% of the variance; additionally, Self-Criticism (β = 0.72) and Neediness (β = 2.05) predicted the PDQ-4+ total, explaining 58% of the variance. In terms of current personality, the PDQ-4+ total was predicted by Self-Criticism (β = 0.55), explaining 30% of the variance. LIMITATIONS The small size of the samples, especially since it is difficult to access individuals diagnosed with AD at the onset or in its early stages; measuring personality changes by means of retrospective assessment by proxies may have introduced some memory bias. CONCLUSIONS These findings are relevant to research relating depressive vulnerability to personality traits and psychopathology in Alzheimers disease.