Multiple Imputation of missing values in exploratory factor analysis of multidimensional scales: estimating latent trait scores

ABSTRACT Researchers frequently have to analyze scales in which some participants have failed to respond to some items. In this paper we focus on the exploratory factor analysis of multidimensional scales (i.e., scales that consist of a number of subscales) where each subscale is made up of a number of Likert-type items, and the aim of the analysis is to estimate participants' scores on the corresponding latent traits. We propose a new approach to deal with missing responses in such a situation that is based on (1) multiple imputation of non-responses and (2) simultaneous rotation of the imputed datasets. We applied the approach in a real dataset where missing responses were artificially introduced following a real pattern of non-responses, and a simulation study based on artificial datasets. The results show that our approach (specifically, Hot-Deck multiple imputation followed of Consensus Promin rotation) was able to successfully compute factor score estimates even for participants that have missing data.

Factor analysis applied to genome prediction for high-dimensional phenotypes in pigs.

The aim of the present study was to propose and evaluate the use of factor analysis (FA) in obtaining latent variables (factors) that represent a set of pig traits simultaneously, for use in genome-wide selection (GWS) studies. We used crosses between outbred F2 populations of Brazilian Piau X commercial pigs. Data were obtained on 345 F2 pigs, genotyped for 237 SNPs, with 41 traits. FA allowed us to obtain four biologically interpretable factors: ?weight?, ?fat?, ?loin?, and ?performance?. These factors were used as dependent variables in multiple regression models of genomic selection (Bayes A, Bayes B, RR-BLUP, and Bayesian LASSO). The use of FA is presented as an interesting alternative to select individuals for multiple variables simultaneously in GWS studies; accuracy measurements of the factors were similar to those obtained when the original traits were considered individually. The similarities between the top 10% of individuals selected by the factor, and those selected by the individual traits, were also satisfactory. Moreover, the estimated markers effects for the traits were similar to those found for the relevant factor.

Quinn’s Leadership Roles: A Confirmatory Factor Analysis Study in Portuguese Health Services

Purpose: To evaluate psychometric properties of Quinn’s leadership questionnaire (CFV questionnaire; 1988) to the Portuguese health services. Design: Cross-sectional study, using the Quinn’s leadership questionnaire, administered to registered nurses and physicians in Portuguese health care services (N = 687). Method: Self-administered survey applied to two samples. In the first (of convenience; N = 249 Portuguese health professionals) were performed exploratory factor and reliability analysis to the CFV questionnaire. In the second sample (stratified; N = 50 surgical units of 33 Portuguese hospitals) was performed confirmatory factor analysis using LISREL 8.80. Findings: The first sample supported an eight-factor solution accounting for 65.46% of the variance, in an interpretable factorial structure (loadings> .50), with Cronbach’s α upper than .79. This factorial structure, replicated with the second sample, showed reasonable fit for each of the 8 leadership roles, quadrants, and global model. The models evidenced, generally, nomological validity, with scores between good and acceptable (.235 < x2/df < 2.055 e .00 < RMSEA < .077). Conclusions: Quinn’s leadership questionnaire presented good reliability and validity for the eight leadership roles, showing to be suitable for use in hospital health care context. Key-Words: Leadership; Quinn’s CVF questionnaire; health services; Quinn’s competing values.

Test of Emotion Comprehension: Exploring the underlying structure through Confirmatory Factor Analysis and Similarity Structure Analysis

Some decades of research on emotional development have underlined the contribution of several domains to emotional understanding in childhood. Based on this research, Pons and colleagues (Pons & Harris, 2002; Pons, Harris & Rosnay, 2004) have proposed the Test of Emotion Comprehension (TEC) which assesses nine domains of emotional understanding, namely the recognition of emotions, based on facial expressions; the comprehension of external emotional causes; impact of desire on emotions; emotions based on beliefs; memory influence on emotions; possibility of emotional regulation; possibility of hiding an emotional state; having mixed emotions; contribution of morality to emotional experiences. This instrument was administered individually to 182 Portuguese children aged between 8 and 11 years, of 3rd and 4th grades, in public schools. Additionally, we used the Socially in Action-Peers (SAp) (Rocha, Candeias & Lopes da Silva, 2012) to assess TEC’s criterion-related validity. Mean differences results in TEC by gender and by socio-economic status (SES) were analyzed. The results of the TEC’s psychometric analysis were performed in terms of items’ sensitivity and reliability (stability, test-retest). Finally, in order to explore the theoretical structure underlying TEC a Confirmatory Factor Analysis and a Similarity Structure Analysis were computed. Implications of these findings for emotional understanding assessment and intervention in childhood are discussed.

An Analysis of Work Related Stress Factor in Selected Industries in Kerala ,India

Occupational stress is becoming a major issue in both corporate and social agenda .In industrialized countries, there have been quite dramatic changes in the conditions at work, during the last decade ,caused by economic, social and technical development. As a consequence, the people today at work are exposed to high quantitative and qualitative demands as well as hard competition caused by global economy. A recent report says that ailments due to work related stress is likely to cost India’s exchequer around 72000 crores between 2009 and 2015. Though India is a fast developing country, it is yet to create facilities to mitigate the adverse effects of work stress, more over only little efforts have been made to assess the work related stress.In the absence of well defined standards to assess the work related stress in India, an attempt is made in this direction to develop the factors for the evaluation of work stress. Accordingly, with the help of existing literature and in consultation with the safety experts, seven factors for the evaluation of work stress is developed. An instrument ( Questionnaire) was developed using these seven factors for the evaluation of work stress .The validity , and unidimensionality of the questionnaire was ensured by confirmatory factor analysis. The reliability of the questionnaire was ensured before administration. While analyzing the relation ship between the variables, it is noted that no relationship exists between them, and hence the above factors are treated as independent factors/ variables for the purpose of research .Initially five profit making manufacturing industries, under public sector in the state of Kerala, were selected for the study. The influence of factors responsible for work stress is analyzed in these industries. These industries were classified in to two types, namely chemical and heavy engineering ,based on the product manufactured and work environment and the analysis is further carried out for these two categories.The variation of work stress with different age , designation and experience of the employees are analyzed by means of one-way ANOVA. Further three different type of modelling of work stress, namely factor modelling, structural equation modelling and multinomial logistic regression modelling was done to analyze the association of factors responsible for work stress. All these models are found equally good in predicting the work stress.The present study indicates that work stress exists among the employees in public sector industries in Kerala. Employees belonging to age group 40-45yrs and experience groups 15-20yrs had relatively higher work demand ,low job control, and low support at work. Low job control was noted among lower designation levels, particularly at the worker level in these industries. Hence the instrument developed using the seven factors namely demand, control, manager support, peer support, relationship, role and change can be effectively used for the evaluation of work stress in industries.

Diversity and commonality in national identities: an exploratory analysis of cross-national patterns

Issues of boundary maintenance are implicit in all studies of national identity. By definition, national communities consist of those who are included but surrounded (literally or metaphorically) by those who are excluded. Most extant research on national identity explores criteria for national membership largely in terms of official or public definitions described, for example, in citizenship and immigration laws or in texts of popular culture. We know much less about how ordinary people in various nations reason about these issues. An analysis of cross-national (N = 23) survey data from the 1995 International Social Science Program reveals a core pattern in most of the countries studied. Respondents were asked how important various criteria were in being 'truly' a member of a particular nation. Exploratory factor analysis shows that these items cluster in terms of two underlying dimensions. Ascriptive/objectivist criteria relating to birth, religion and residence can be distinguished from civic/voluntarist criteria relating to subjective feelings of membership and belief in core institutions. In most nations the ascriptive/objectivist dimension of national identity was more prominent than the subjective civic/voluntarist dimension. Taken overall, these findings suggest an unanticipated homogeneity in the ways that citizens around the world think about national identity. To the extent that these dimensions also mirror the well-known distinction between ethnic and civic national identification, they suggest that the former remains robust despite globalization, mass migration and cultural pluralism. Throughout the world official definitions of national identification have tended to shift towards a civic model. Yet citizens remain remarkably traditional in outlook. A task for future research is to investigate the macrosociological forces that produce both commonality and difference in the core patterns we have identified.

Does independent component analysis play a role in unmixing hyperspectral data?

Independent component analysis (ICA) has recently been proposed as a tool to unmix hyperspectral data. ICA is founded on two assumptions: 1) the observed spectrum vector is a linear mixture of the constituent spectra (endmember spectra) weighted by the correspondent abundance fractions (sources); 2)sources are statistically independent. Independent factor analysis (IFA) extends ICA to linear mixtures of independent sources immersed in noise. Concerning hyperspectral data, the first assumption is valid whenever the multiple scattering among the distinct constituent substances (endmembers) is negligible, and the surface is partitioned according to the fractional abundances. The second assumption, however, is violated, since the sum of abundance fractions associated to each pixel is constant due to physical constraints in the data acquisition process. Thus, sources cannot be statistically independent, this compromising the performance of ICA/IFA algorithms in hyperspectral unmixing. This paper studies the impact of hyperspectral source statistical dependence on ICA and IFA performances. We conclude that the accuracy of these methods tends to improve with the increase of the signature variability, of the number of endmembers, and of the signal-to-noise ratio. In any case, there are always endmembers incorrectly unmixed. We arrive to this conclusion by minimizing the mutual information of simulated and real hyperspectral mixtures. The computation of mutual information is based on fitting mixtures of Gaussians to the observed data. A method to sort ICA and IFA estimates in terms of the likelihood of being correctly unmixed is proposed.

Unmixing hyperspectral data: independent and dependent component analysis

The development of high spatial resolution airborne and spaceborne sensors has improved the capability of ground-based data collection in the fields of agriculture, geography, geology, mineral identification, detection [2, 3], and classification [4–8]. The signal read by the sensor from a given spatial element of resolution and at a given spectral band is a mixing of components originated by the constituent substances, termed endmembers, located at that element of resolution. This chapter addresses hyperspectral unmixing, which is the decomposition of the pixel spectra into a collection of constituent spectra, or spectral signatures, and their corresponding fractional abundances indicating the proportion of each endmember present in the pixel [9, 10]. Depending on the mixing scales at each pixel, the observed mixture is either linear or nonlinear [11, 12]. The linear mixing model holds when the mixing scale is macroscopic [13]. The nonlinear model holds when the mixing scale is microscopic (i.e., intimate mixtures) [14, 15]. The linear model assumes negligible interaction among distinct endmembers [16, 17]. The nonlinear model assumes that incident solar radiation is scattered by the scene through multiple bounces involving several endmembers [18]. Under the linear mixing model and assuming that the number of endmembers and their spectral signatures are known, hyperspectral unmixing is a linear problem, which can be addressed, for example, under the maximum likelihood setup [19], the constrained least-squares approach [20], the spectral signature matching [21], the spectral angle mapper [22], and the subspace projection methods [20, 23, 24]. Orthogonal subspace projection [23] reduces the data dimensionality, suppresses undesired spectral signatures, and detects the presence of a spectral signature of interest. The basic concept is to project each pixel onto a subspace that is orthogonal to the undesired signatures. As shown in Settle [19], the orthogonal subspace projection technique is equivalent to the maximum likelihood estimator. This projection technique was extended by three unconstrained least-squares approaches [24] (signature space orthogonal projection, oblique subspace projection, target signature space orthogonal projection). Other works using maximum a posteriori probability (MAP) framework [25] and projection pursuit [26, 27] have also been applied to hyperspectral data. In most cases the number of endmembers and their signatures are not known. Independent component analysis (ICA) is an unsupervised source separation process that has been applied with success to blind source separation, to feature extraction, and to unsupervised recognition [28, 29]. ICA consists in finding a linear decomposition of observed data yielding statistically independent components. Given that hyperspectral data are, in given circumstances, linear mixtures, ICA comes to mind as a possible tool to unmix this class of data. In fact, the application of ICA to hyperspectral data has been proposed in reference 30, where endmember signatures are treated as sources and the mixing matrix is composed by the abundance fractions, and in references 9, 25, and 31–38, where sources are the abundance fractions of each endmember. In the first approach, we face two problems: (1) The number of samples are limited to the number of channels and (2) the process of pixel selection, playing the role of mixed sources, is not straightforward. In the second approach, ICA is based on the assumption of mutually independent sources, which is not the case of hyperspectral data, since the sum of the abundance fractions is constant, implying dependence among abundances. This dependence compromises ICA applicability to hyperspectral images. In addition, hyperspectral data are immersed in noise, which degrades the ICA performance. IFA [39] was introduced as a method for recovering independent hidden sources from their observed noisy mixtures. IFA implements two steps. First, source densities and noise covariance are estimated from the observed data by maximum likelihood. Second, sources are reconstructed by an optimal nonlinear estimator. Although IFA is a well-suited technique to unmix independent sources under noisy observations, the dependence among abundance fractions in hyperspectral imagery compromises, as in the ICA case, the IFA performance. Considering the linear mixing model, hyperspectral observations are in a simplex whose vertices correspond to the endmembers. Several approaches [40–43] have exploited this geometric feature of hyperspectral mixtures [42]. Minimum volume transform (MVT) algorithm [43] determines the simplex of minimum volume containing the data. The MVT-type approaches are complex from the computational point of view. Usually, these algorithms first find the convex hull defined by the observed data and then fit a minimum volume simplex to it. Aiming at a lower computational complexity, some algorithms such as the vertex component analysis (VCA) [44], the pixel purity index (PPI) [42], and the N-FINDR [45] still find the minimum volume simplex containing the data cloud, but they assume the presence in the data of at least one pure pixel of each endmember. This is a strong requisite that may not hold in some data sets. In any case, these algorithms find the set of most pure pixels in the data. Hyperspectral sensors collects spatial images over many narrow contiguous bands, yielding large amounts of data. For this reason, very often, the processing of hyperspectral data, included unmixing, is preceded by a dimensionality reduction step to reduce computational complexity and to improve the signal-to-noise ratio (SNR). Principal component analysis (PCA) [46], maximum noise fraction (MNF) [47], and singular value decomposition (SVD) [48] are three well-known projection techniques widely used in remote sensing in general and in unmixing in particular. The newly introduced method [49] exploits the structure of hyperspectral mixtures, namely the fact that spectral vectors are nonnegative. The computational complexity associated with these techniques is an obstacle to real-time implementations. To overcome this problem, band selection [50] and non-statistical [51] algorithms have been introduced. This chapter addresses hyperspectral data source dependence and its impact on ICA and IFA performances. The study consider simulated and real data and is based on mutual information minimization. Hyperspectral observations are described by a generative model. This model takes into account the degradation mechanisms normally found in hyperspectral applications—namely, signature variability [52–54], abundance constraints, topography modulation, and system noise. The computation of mutual information is based on fitting mixtures of Gaussians (MOG) to data. The MOG parameters (number of components, means, covariances, and weights) are inferred using the minimum description length (MDL) based algorithm [55]. We study the behavior of the mutual information as a function of the unmixing matrix. The conclusion is that the unmixing matrix minimizing the mutual information might be very far from the true one. Nevertheless, some abundance fractions might be well separated, mainly in the presence of strong signature variability, a large number of endmembers, and high SNR. We end this chapter by sketching a new methodology to blindly unmix hyperspectral data, where abundance fractions are modeled as a mixture of Dirichlet sources. This model enforces positivity and constant sum sources (full additivity) constraints. The mixing matrix is inferred by an expectation-maximization (EM)-type algorithm. This approach is in the vein of references 39 and 56, replacing independent sources represented by MOG with mixture of Dirichlet sources. Compared with the geometric-based approaches, the advantage of this model is that there is no need to have pure pixels in the observations. The chapter is organized as follows. Section 6.2 presents a spectral radiance model and formulates the spectral unmixing as a linear problem accounting for abundance constraints, signature variability, topography modulation, and system noise. Section 6.3 presents a brief resume of ICA and IFA algorithms. Section 6.4 illustrates the performance of IFA and of some well-known ICA algorithms with experimental data. Section 6.5 studies the ICA and IFA limitations in unmixing hyperspectral data. Section 6.6 presents results of ICA based on real data. Section 6.7 describes the new blind unmixing scheme and some illustrative examples. Section 6.8 concludes with some remarks.

High-Content Analysis of Breast Cancer Using Single-Cell Deep Transfer Learning

High-content analysis has revolutionized cancer drug discovery by identifying substances that alter the phenotype of a cell, which prevents tumor growth and metastasis. The high-resolution biofluorescence images from assays allow precise quantitative measures enabling the distinction of small molecules of a host cell from a tumor. In this work, we are particularly interested in the application of deep neural networks (DNNs), a cutting-edge machine learning method, to the classification of compounds in chemical mechanisms of action (MOAs). Compound classification has been performed using image-based profiling methods sometimes combined with feature reduction methods such as principal component analysis or factor analysis. In this article, we map the input features of each cell to a particular MOA class without using any treatment-level profiles or feature reduction methods. To the best of our knowledge, this is the first application of DNN in this domain, leveraging single-cell information. Furthermore, we use deep transfer learning (DTL) to alleviate the intensive and computational demanding effort of searching the huge parameter's space of a DNN. Results show that using this approach, we obtain a 30% speedup and a 2% accuracy improvement.

Cluster analysis and segmentation of Global M&A transactions

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Finance from the NOVA – School of Business and Economics

Exploring the factor structure of neurocognitive measures in older individuals

Here we focus on factor analysis from a best practices point of view, by investigating the factor structure of neuropsychological tests and using the results obtained to illustrate on choosing a reasonable solution. The sample (n=1051 individuals) was randomly divided into two groups: one for exploratory factor analysis (EFA) and principal component analysis (PCA), to investigate the number of factors underlying the neurocognitive variables; the second to test the "best fit" model via confirmatory factor analysis (CFA). For the exploratory step, three extraction (maximum likelihood, principal axis factoring and principal components) and two rotation (orthogonal and oblique) methods were used. The analysis methodology allowed exploring how different cognitive/psychological tests correlated/discriminated between dimensions, indicating that to capture latent structures in similar sample sizes and measures, with approximately normal data distribution, reflective models with oblimin rotation might prove the most adequate.

Dimensionality of the Rosenberg self-esteem scale and its relationships with the three- and five-factor personality models

The authors investigated the dimensionality of the French version of the Rosenberg Self-Esteem Scale (RSES; Rosenberg, 1965) using confirmatory factor analysis. We tested models of 1 or 2 factors. Results suggest the RSES is a 1-dimensional scale with 3 highly correlated items. Comparison with the Revised NEO-Personality Inventory (NEO-PI-R; Costa, McCrae, & Rolland, 1998) demonstrated that Neuroticism correlated strongly and Extraversion and Conscientiousness moderately with the RSES. Depression accounted for 47% of the variance of the RSES. Other NEO-PI-R facets were also moderately related with self-esteem.

Quantitative analysis of image factors in a cultural heritage tourist destination

The tourism consumer’s purchase decision process is, to a great extent, conditioned by the image the tourist has of the different destinations that make up his or her choice set. In a highly competitive international tourist market, those responsible for destinations’ promotion and development policies seek differentiation strategies so that they may position the destinations in the most suitable market segments for their product in order to improve their attractiveness to visitors and increase or consolidate the economic benefits that tourism activity generates in their territory. To this end, the main objective we set ourselves in this paper is the empirical analysis of the factors that determine the image formation of Tarragona city as a cultural heritage destination. Without a doubt, UNESCO’s declaration of Tarragona’s artistic and monumental legacies as World Heritage site in the year 2000 meant important international recognition of the quality of the cultural and patrimonial elements offered by the city to the visitors who choose it as a tourist destination. It also represents a strategic opportunity to boost the city’s promotion of tourism and its consolidation as a unique destination given its cultural and patrimonial characteristics. Our work is based on the use of structured and unstructured techniques to identify the factors that determine Tarragona’s tourist destination image and that have a decisive influence on visitors’ process of choice of destination. In addition to being able to ascertain Tarragona’s global tourist image, we consider that the heterogeneity of its visitors requires a more detailed study that enables us to segment visitor typology. We consider that the information provided by these results may prove of great interest to those responsible for local tourism policy, both when designing products and when promoting the destination.

Zuckerman's reivsed alternative five-factor model: Validation of the Zuckerman-Kuhlman-Aluja Personality Questionnaire in four French-speaking countries

The aim of this study was to analyze the replicability of Zuckerman's revised Alternative Five-factor model in a French-speaking context by validating the Zuckerman-Kuhlman-Aluja Personality Questionnaire (ZKA-PQ) simultaneously in 4 French-speaking countries. The total sample was made up of 1,497 subjects from Belgium, Canada, France, and Switzerland. The internal consistencies for all countries were generally similar to those found for the normative U.S. and Spanish samples. A factor analysis confirmed that the normative structure replicated well and was stable within this French-speaking context. Moreover, multigroup confirmatory factor analyses have shown that the ZKA-PQ reaches scalar invariance across these 4 countries. Mean scores were slightly different for women and men, with women scoring higher on Neuroticism but lower on Sensation Seeking. Globally, mean score differences across countries were small. Overall, the ZKA-PQ seems an interesting alternative to assess both lower and higher order personality traits for applied or research purposes.

Further insights on the French WISC-IV factor structure through Bayesian structural equation modeling

The interpretation of the Wechsler Intelligence Scale for Children-Fourth Edition (WISC-IV) is based on a 4-factor model, which is only partially compatible with the mainstream Cattell-Horn-Carroll (CHC) model of intelligence measurement. The structure of cognitive batteries is frequently analyzed via exploratory factor analysis and/or confirmatory factor analysis. With classical confirmatory factor analysis, almost all crossloadings between latent variables and measures are fixed to zero in order to allow the model to be identified. However, inappropriate zero cross-loadings can contribute to poor model fit, distorted factors, and biased factor correlations; most important, they do not necessarily faithfully reflect theory. To deal with these methodological and theoretical limitations, we used a new statistical approach, Bayesian structural equation modeling (BSEM), among a sample of 249 French-speaking Swiss children (8-12 years). With BSEM, zero-fixed cross-loadings between latent variables and measures are replaced by approximate zeros, based on informative, small-variance priors. Results indicated that a direct hierarchical CHC-based model with 5 factors plus a general intelligence factor better represented the structure of the WISC-IV than did the 4-factor structure and the higher order models. Because a direct hierarchical CHC model was more adequate, it was concluded that the general factor should be considered as a breadth rather than a superordinate factor. Because it was possible for us to estimate the influence of each of the latent variables on the 15 subtest scores, BSEM allowed improvement of the understanding of the structure of intelligence tests and the clinical interpretation of the subtest scores.