Standard Factor Analysis Research Articles

Sparse coding representation of emotional brain states in fMRI data

Modern computer systems can deal with tremendous amounts of information, and these systems are becoming more and more complex. Still, there is no machine that develops emotions when processing complex stimuli. In this respect, processing in the human brain seems to differ from processing in machines not so much in the amount of data dealt with, but especially in terms of the global integration of parallel (local) processes as a whole [1]. FMRI (functional magnetic resonance imaging) is a method that gets us behind the scenes even if participants perform complex tasks. As “complex” refers to tasks that cannot described by activity in a single locus, multivariate techniques are the first choice on the way to break the code underlying these responses. Standard factor analysis is used to determine, in which of the brain regions activity is correlated (PCA) or which voxels are showing statistical independent activity (ICA) [2,3]. But on the way to understand such patterns, we are especially interested in the intrinsic organization of these correlated or statistical dependent modules. In this context, the use of Sparse Coding (SC) is twofold: We could try to find class-separating feature vectors that are sparse but still discriminative for the given classes [4]. But just the same, we can learn a set of base functions – alternatively to PCs and ICs – that resembles the task-specific patterns by a linear combination with as few as possible non-zero coefficients [5]. We analyzed an fMRI study to examine the brain responses to emotional conditions (anger, fear, surprise, joy, and sadness) and focused on the impact of sparse coding to the pattern characterization task. We show how the structure of global brain activity and how the complexity of sparse patterns is changing during different emotional states and that different affective states of the system can be well discriminated using SC. Finally, we will address the question of how many voxels are needed to discriminate these emotional states.

Measurement of post‐operative cognitive dysfunction after cardiac surgery: a systematic review

Post-operative cognitive dysfunction (POCD) is a decline in cognitive function from pre-operative levels, which has been frequently described after cardiac surgery. The purpose of this study was to examine the variability in the measurement and definitions for POCD using the framework of a 1995 Consensus Statement on measurement of POCD. Electronic medical literature databases were searched for the intersection of the search terms 'thoracic surgery' and 'cognition, dementia, and neuropsychological test.' Abstracts were reviewed independently by two reviewers. English articles with >50 participants published since 1995 that performed pre-operative and post-operative psychometric testing in patients undergoing cardiac surgery were reviewed. Data relevant to the measurement and definition of POCD were abstracted and compared with the recommendations of the Consensus Statement. Sixty-two studies of POCD in patients undergoing cardiac surgery were identified. Of these studies, the recommended neuropsychological tests were carried out in less than half of the studies. The cognitive domains measured most frequently were attention (n=56; 93%) and memory (n=57; 95%); motor skills were measured less frequently (n=36; 60%). Additionally, less than half of the studies examined anxiety and depression, performed neurological exam, or accounted for learning. Four definitions of POCD emerged: per cent decline (n=15), standard deviation decline (n=14), factor analysis (n=13), and analysis of performance on individual tests (n=12). There is marked variability in the measurement and definition of POCD. This heterogeneity may impede progress by reducing the ability to compare studies on the causes and treatment of POCD.

Does the CES-D measure a continuum from depression to happiness? Comparing substantive and artifactual models

The Center for Epidemiologic Studies-Depression scale (CES-D) is one of the five most frequently used measures of depressive experiences. Previous research has suggested that the scale may consist of two separate factors of happiness and depression, respectively. However, recent methodological research has demonstrated that standard factor analysis cannot be used in this situation to demonstrate such factors are substantive. The substantive factor structure of the CES-D was therefore tested with two samples of younger ( N = 8857; age range 27–35) and older ( N = 6125; age range 64–65) people. Using a recent correction to CFA, we demonstrate that a two factor structure arises through purely artifactual reasons, and that the CES-D actually has only one substantive factor, providing evidence for a single continuum ranging from happiness to depression.

Severe Impairment Battery Language scale: A language-assessment tool for Alzheimer's disease patients

Background Communication problems are common in Alzheimer's disease (AD) patients, but instruments to assess these symptoms are limited. Our objective was to create a new scale, based on the language subscale of the Severe Impairment Battery (SIB), as a sensitive and reliable measurement of treatment effects on language performance. Methods All 24 items of the SIB language subscale were chosen for analysis. Baseline scores of 1320 moderate-to-severe patients (Mini-Mental State Examination [MMSE] score, <15), from a combined AD database of four Memantine clinical trials (Study Codes: IE-2101, MEM-MD-01, MEM-MD-02, and MRZ-9605), were used for item reduction according to a standard principal components factor analysis. All items with loadings >0.5 on the identified factors were selected for inclusion in the new language scale. Correlations with existing AD scales were examined. Results The analysis indicated six factors, with 21 of 24 items showing loadings >0.5. The resulting 21-item SIB Language (SIB-L) scale exhibited high internal consistency (Cronbach's α = 0.809). The maximal SIB-L score was 41 points, with a measurement error of 3.7 points. The stratification of baseline SIB-L scores (mean, 31.7; SD, 8.4) by MMSE scores (mean, 9.7; SD, 3.3) showed a high variance in SIB-L scores. This confirms that patients with a low MMSE score can possess preserved language abilities. The SIB-L scale did not exhibit substantial floor-and-ceiling effects. Conclusions The new SIB-L is a fast (<15 minutes) and easily administered scale with favorable psychometric characteristics for assessing language impairment and treatment effects on the language performance of patients with moderate to severe AD.

실제체형과 이상체형에 대한 남녀 대학생들의 인식과 선호체형에 대한 연구

The purpose of this study was to identify the perception between real and ideal body shapes of college students and to investigate the preferred body shape of college students. The research subjects numbered one hundred forty five male and female students, aged 20 to 29, who lived in Gwangju and Chonnam province. The anthropometric data was collected including both direct and indirect measurements. The data was analyzed by mean and standard deviation, t-test, and factor analysis. The results of t-test showed the significant difference() between real body size and ideal body size. The result showed that male students want to have bigger chest circumference and a taller height than their real body, the research also showed that the female students want to have a narrow bust and hip width along with a taller height than real body. Regarding ideal body shape, male students pursued bigger height and want an inverted-triangle body shape. On the other hand, female students pursued bigger height and slim body shape. This study established the factors(dimension of torso, height, the side shape of torso, and shoulder shape) as the perception between real and ideal body shapes. In terms of real body, the factor analysis shows two contrasting results in which the height is the most important factor for female students, while the torso dimension is the most important factor for male students. In terms of ideal body, the height factor is the most important for both the male and female students.

Correlation between damage distribution and ambient noise H/V spectral ratio: the SESAME project results

In the framework of the SESAME project one of the tasks was the compilation of all available ambient noise measurements within urban environments affected by historical or/and recent strong earthquakes in Europe. The aim of such a task was to give an answer to the question; “How does horizontal-to-vertical ambient noise spectral ratio compare with damage in modern cities?”. For this purpose five European urban areas, namely, Angra do Heroismo (Portugal), Fabriano and Palermo (Italy), Thessaloniki and Kalamata (Greece) were selected for which spatial damage information was available either in terms of modified Mercalli intensity or in EMS98 damage grades. The geological setting of the examined sites as well as the causative earthquakes are satisfactorily known. Ambient noise recordings compiled for all examined sites have been homogeneously processed by a technique developed and agreed upon SESAME project. Using a standard multivariate statistical analysis, namely, factor analysis and canonical correlation, the horizontal-to-vertical ambient noise spectral ratio (HVNSR) is correlated with damage pattern observed within examined urban areas. Results show that, in some cases (Thessaloniki, Palermo), the HVNSR seems to be able to differentiate between areas previously shown to be associated with higher damage. In other cases however (Angra do Heroismo, Fabriano, Kalamata), the correlation is not statistically significant indicating thus the complex character of the parameters involved, implying that currently there is no a straightforward way that a value of HVNSR can correctly predict the extent to which a given region will be associated with increased damage.

Improvement of residual bilinearization by particle swarm optimization for achieving the second‐order advantage with unfolded partial least‐squares

AbstractThe combination of unfolded partial least‐squares (U‐PLS) with residual bilinearization (RBL) provides a second‐order multivariate calibration method capable of achieving the second‐order advantage. RBL is performed by varying the test sample scores in order to minimize the residues of a combined U‐PLS model for the calibrated components and a principal component model for the potential interferents. The sample scores are then employed to predict the analyte concentration, with regression coefficients taken from the calibration step. When the contribution of multiple potential interferents is severe, particle swarm optimization (PSO) helps in preventing RBL to be trapped by false minima, restoring its predictive ability and making it comparable to the standard parallel factor (PARAFAC) analysis. Both simulated and experimental systems are analyzed in order to show the potentiality of the new technique. Copyright © 2007 John Wiley &amp; Sons, Ltd.

TEACHER SELF-EFFICACY BELIEF

This study presents development and validation of a new measurement instrument to explore student-teachers' self-efficacy beliefs toward teaching. We developed and administered a survey to 346 student teachers at Hacettepe University, Ankara, Turkey in the Department of Elementary Education in the spring term of the 2003–2004 academic year. The nature of the study is descriptive. The aim is to describe what the real situation is. Standard scale development methods and factor analysis were used. The results of the study were strongly supported by the validity and reliability of the survey. Cronbach's alpha was calculated and the reliability coefficient was 0.92. For purposes of examining content validity, the opinions of experts on 5 subject matters were taken. Factor analysis was made to elicit the fundamental dimensions of the survey. As a result of the Kalse-Meyer-Olkin and Bartlett test (0.93), factor analysis was administered to the survey. A single-factor model was specified for the structure of the survey as anticipated.

Validation of the SWAP-200 for Diagnosing Psychostructural Organization in Personality Disorders

Background: The aim of the study was to investigate the validity of the prototype-matching, empirically based 200-item Shedler-Westen Assessment Procedure (SWAP-200) and its clinical utility for describing underlying dimensions of psychostructural organization and functioning. Sampling and Methods: Patients (n = 306) from two psychoanalytic out-patient departments were included. Replicatory and exploratory factor analysis, correlation and discriminant validity statistics, and canonical correlation analysis were performed. Results: Replicatory factor analysis failed to reproduce the identical original factorial structure. Standard factor analysis revealed an eight-factor solution displaying a dimensional description of psychostructural personality organization (high functioning – neurotic/inhibited – borderline/emotionally dysregulated – psychotic/dissocial). Discriminant validity exists across the sample owing to high/poor psychological functioning. Canonical correlation analysis does not support the replacement of the Structured Clinical Interview for DSM-IV, but provides relevant implications for refining DSM-IV axis II. Conclusions: Support is given for the SWAP instrument in describing dimensional higher-order personality organization and psychostructural functioning.

Factor Analysis of Seattle Fine Particles

Ambient particulate matter ≤2.5 μm in aerodynamic diameter (PM2.5) samples were collected at a centrally located urban monitoring site in Seattle, WA on Wednesdays and Saturdays using Interagency Monitoring of Protected Visual Environments (IMPROVE) samplers. Particulate carbon was analyzed using the thermal optical reflectance method that divides carbon into four organic carbon (OC), pyrolyzed organic carbon (OP), and three elemental carbon (EC) fractions. A total of 384 samples that were analyzed for 36 species were collected between March 1996 and February 2000. These data were analyzed with the standard factor analysis model using the Multilinear Engine (ME). Eleven sources were identified: sulfate-rich secondary aerosol (26%), diesel emissions (22%), wood smoke (16%), gasoline vehicle (10%), aged sea salt (8%), airborne soil (7%), nitrate-rich secondary aerosol (5%), sea salt (4%), oil combustion (3%), paper mill (2%), and ferrous metal processing (1%). The use of ME provided enhanced source separati...

Bayesian Factor Analysis for Mixed Ordinal and Continuous Responses

Many situations exist in which a latent construct has both ordinal and continuous indicators. This presents a problem for the applied researcher because standard measurement models are not designed to accommodate mixed ordinal and continuous data. I address this problem by formulating a measurement model that is appropriate for such mixed multivariate responses. This model unifies standard normal theory factor analysis and item response theory models for ordinal data. I detail a Markov chain Monte Carlo algorithm for model fitting. I apply the model to cross-national data on political-economic risk and find that the model works well. Software for fitting this model is publicly available in theMCMCpack(Martin and Quinn 2004, “MCMCpack 0.4–8”)Rpackage.

Diagnosing Manufacturing Variation Using Second-Order and Fourth-Order Statistics

This article discusses a method that can aid in diagnosing root causes of product and process variability in complex manufacturing processes, when large amounts of multivariate in-process measurement data are available. A linear structured model, similar to the standard factor analysis model, is used to generically represent the variation patterns that result from the root causes. Blind source separation techniques form the basis for identifying the precise characteristics of each individual variation pattern in order to facilitate the identification of their root causes. The second-order and fourth-order statistics that are used in various blind separation algorithms are combined in an optimal manner to form a more effective and black-box method with wider applicability.

Confidence sets for high-dimensional empirical linear prediction (HELP) models with dependent error structure

In this paper, we provide asymptotic theory and use it to construct confidence sets for High-dimensional Empirical Linear Prediction (HELP) Models. HELP is a statistical prediction technique based on a model similar to a factor analysis model. The aim of HELP model, however, is to predict future observations, and is different from the usual factor analysis. We generalize HELP to the cases of non-iid errors, thus going beyond the standard factor analysis model. We studied an unusual asymptotic theory where the size of the covariance matrix goes to infinity. This kind of asymptotic theory is important for practical applications and leads to confidence sets with much better coverage probabilities than the ones derived from the typical asymptotic theory where the size of the covariance matrix remains fixed. Although the covariance matrix may not be estimated consistently, it is shown that the point estimates of HELP are consistent. Also, valid asymptotic confidences sets are constructed based on the inconsistently estimated covariance matrix.

Oligocene eustasy from two-dimensional sequence stratigraphic backstripping

Research Article| March 01, 2001 Oligocene eustasy from two-dimensional sequence stratigraphic backstripping Michelle A. Kominz; Michelle A. Kominz 1Department of Geosciences, Western Michigan University, 1187 Rood Hall, Kalamazoo, Michigan 49008-5150, USA Search for other works by this author on: GSW Google Scholar Stephen F. Pekar Stephen F. Pekar 2Lamont-Doherty Earth Observatory, Columbia University, Palisades, New York 10964-8000, USA Search for other works by this author on: GSW Google Scholar Author and Article Information Michelle A. Kominz 1Department of Geosciences, Western Michigan University, 1187 Rood Hall, Kalamazoo, Michigan 49008-5150, USA Stephen F. Pekar 2Lamont-Doherty Earth Observatory, Columbia University, Palisades, New York 10964-8000, USA Publisher: Geological Society of America Received: 27 May 1999 Revision Received: 20 Dec 1999 Accepted: 28 Feb 2000 First Online: 01 Jun 2017 Online ISSN: 1943-2674 Print ISSN: 0016-7606 Geological Society of America GSA Bulletin (2001) 113 (3): 291–304. https://doi.org/10.1130/0016-7606(2001)113<0291:OEFTDS>2.0.CO;2 Article history Received: 27 May 1999 Revision Received: 20 Dec 1999 Accepted: 28 Feb 2000 First Online: 01 Jun 2017 Cite View This Citation Add to Citation Manager Share Icon Share Facebook Twitter LinkedIn MailTo Tools Icon Tools Get Permissions Search Site Citation Michelle A. Kominz, Stephen F. Pekar; Oligocene eustasy from two-dimensional sequence stratigraphic backstripping. GSA Bulletin 2001;; 113 (3): 291–304. doi: https://doi.org/10.1130/0016-7606(2001)113<0291:OEFTDS>2.0.CO;2 Download citation file: Ris (Zotero) Refmanager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentBy SocietyGSA Bulletin Search Advanced Search Abstract Estimates of the magnitudes of changes in third-order (0.5−2 m.y.) eustasy were obtained for Oligocene sequences defined by a suite of largely onshore boreholes of the New Jersey coastal plain. Benthic foraminiferal biofacies and multiple age constraints in a sequence stratigraphic framework formed the database for this study. The geometry of the margin through time was determined using two-dimensional backstripping. The depth ranges of benthic foraminiferal biofacies were determined from a combination of standard factor analysis techniques and the backstripped geometries. Benthic foraminiferal biofacies were then used to determine the depths of the Oligocene margin profiles obtained from backstripping. The water depths of 16 of these horizons were confirmed by independent benthic biofacies determinations from at least two wells. This internal consistency indicates that the data and the two-dimensional backstripping approach were robust. Where benthic biofacies require a vertical shift of the horizons generated by two-dimensional backstripping, eustatic changes were required and were readily calculated.Results indicate a major eustatic fall from the end of the Eocene to the first record of Oligocene deposition. Subsequent long-term shoaling of sea level through the Oligocene was ∼30 m in 10 m.y. Superimposed on this long-term trend were higher frequency (third-order) variations in eustasy with amplitudes of ∼40 m or less. You do not have access to this content, please speak to your institutional administrator if you feel you should have access.

Factor structure and ammonia-related modulation of the human retinal oscillatory potentials

Objective: To investigate in man the factor structure of retinal oscillatory potentials (OPs) to full-field luminance stimulation (0.9–9.5 cd.s.m −2) and the correlation with the spontaneous fluctuations of plasma ammonia. Methods: Six male healthy volunteers were studied. Five OP recordings and ammonia determinations (GLDH method) were obtained for each subject at 2 h interval during an 8 h experimental session. A standard factor analysis was applied on the OP latency (time from stimulus to peak) and amplitudes values. Results: Two consecutive factors on latencies and two factors on amplitudes were identified, consistent with reported differences between the earlier and later OP waves. The model explained a large portion of the OP variance. Both factors on latencies and factor 1 on amplitudes were directly correlated to the stimulus intensity and the ammonia plasma concentration in the 15.8–39.5 μmol/l range. Factors 1 and 2 on latencies decreased and factor 1 on amplitude increased at increasing stimulus intensities. The latency factors decreased and the amplitude factor increased with increasing ammonia concentration. Factor 2 on amplitudes did not correlate with the stimulus intensity or ammonia concentration. Conclusions: The factor structure further supports the evidence of functional differences between early and late OP waves. The observed correlation conceivably reflects a role of ammonia in the modulation of retinal electrophysiology in physiological conditions and potentially accounts for spontaneous variability in otherwise controlled electrophysiological studies.

A Critique of Factor Analysis of Interest Rates

Term structure models typically attempt to explain the full range of observed fluctuation in the yield curve with a small number of independent factors. Factor analysis, a common tool in this effort, generally shows that three factors capture a large proportion of the variation in the curve. The first (most important) factor applies across all maturities and reflects the level of yields; the second affects the slope of the yield curve; and the third relates to its curvature. In this article, Lekkos argues that much of the apparent explanatory power of this factor structure may be an artifact induced by the arbitrage relationship that requires a given spot rate to equal the average of the forward rates over that maturity. Factor analysis on spot rates in four major countries shows that three factors explain about 97% of the variance in each case, but the fit with forward rates is distinctly less good. Lekkos then demonstrates that even in a simulated economy with completely independent forward rates, as long as spot rates are arbitrage-free and equal to averages of the relevant forward rates, standard factor analysis produces a factor structure that explains over 90% of overall yield variation, and loadings on the individual factors that closely resemble the patterns found for the actual markets.

Oxidation, Diffusion and Segregation in CuNi(Mn) Films Studied by AES

The surface and in-depth compositions of sputter-deposited Cu0.57Ni0.42Mn0.01 thin films were studied by Auger electron depth profiling after thermal treatment. The samples were thermally cycled to maximum temperatures of 300 °C to 550 °C in air, argon and forming gas (N2, 5 vol. % H2). Linear least-squares fit to standard spectra and factor analysis were applied to separate the overlapping Auger transitions of Cu and Ni. Under bombardment by 4 keV argon ions, CuNi(Mn) layers display bombardment-induced surface enrichment of Ni in the same extent as binary CuNi alloys. At sufficiently high oxygen partial pressures, a duplex oxide layer is formed and a thick surface copper oxide overgrows the initial nickel oxide. In reducing atmosphere selective oxidation of manganese takes place. A capping NiCr layer prevents CuNi(Mn) from being oxidized, but the film configuration is degraded with increasing annealing temperature due to formation of a surface chromium oxide and diffusion of Ni from the CuNi(Mn) layer into the NiCr/CuNi(Mn) interface.

A STATE‐SPACE APPROACH TO ESTIMATE AND TEST MULTIFACTOR COX‐INGERSOLL‐ROSS MODELS OF THE TERM STRUCTURE

AbstractThe objective of this paper is to estimate and test multifactor versions of the Cox‐Ingersoll‐Ross (CIR) model of the nominal term structure of interest rates. The proposed state‐space approach integrates time series and cross‐sectional aspects of the CIR model, is consistent with the underlying economic model, and can use information from all available points of the term structure. We recover estimates of the underlying factors that are consistent with the assumptions about the stochastic processes and compare them with factors obtained from standard factor analysis. We perform thorough diagnostic checking and thereby provide new evidence regarding conclusions about the adequacy of the CIR model. We present empirical results for U.S. Treasury market data. Although the specification of multifactor CIR models is sufficiently flexible for the shape of the term structure, we find strong evidence against the adequacy of the CIR model.

Some remarks on Scheiblechner's treatment of isop models

Scheiblechner (1995) proposes a probabilistic axiomatization of measurement called ISOP (isotonic ordinal probabilistic models) that replaces Rasch's (1980) specific objectivity assumptions with two interesting ordinal assumptions. Special cases of Scheiblechner's model include standard unidimensional factor analysis models in which the loadings are held constant, and the Rasch model for binary item responses. Closely related are the doubly-monotone item response models of Mokken (1971; see also Mokken & Lewis, 1982; Sijtsma, 1988; Molenaar, 1991; Sijtsma & Junker, 1996; and Sijtsma & Hemker, in press). More generally, strictly unidimensional latent variable models have been considered in some detail by Holland and Rosenbaum (1986), Ellis and van den Wollenberg (1993), and Junker (1990, 1993). The purpose of this note is to provide connections with current research in foundations and nonparametric latent variable and item response modeling that are missing from Scheiblechner's (1995) paper, and to point out important related work by Hemker, Sijtsma, Molenaar, & Junker (1996, 1997), Ellis and Junker (in press) and Junker and Ellis (1997). We also discuss counterexamples to three major theorems in the paper. By carrying out these three tasks, we hope to provide researchers interested in the foundations of measurement and item response modeling the opportunity to give the ISOP approach the careful attention it deserves.

A multinational study of the factorial structure and other characteristics of the Dartmouth COOP Functional Health Assessment Charts/WONCA.

The 'Dartmouth COOP Functional Health Assessment Charts/WONCA' constitute a relatively new derived instrument for assessing health status that is specifically intended for use in primary care on a world-wide basis. It needs further validation in its special area of use. Over a range of countries, social backgrounds and case mixes, our aim was (i) to examine the factorial structure of the instrument; (ii) to explore how well it was understood; (iii) to check its acceptability; and (iv) to assess the value of the pictures on the charts. The charts themselves, accompanied by a short questionnaire about the charts, were administered to 1719 patients at eight varied types of treatment centre in Canada, Japan, Nepal and Spain. The responses to the instrument were subjected to standard factor analysis and a special Q-type principal components analysis. The responses to direct questions about the charts were compared with the answers to open-ended questions. Factor analysis suggested a shared factorial pattern for all sites, with the first two factors accounting for 88.5% of the variability in correlations between the charts across the sites. The individual questions were understood by most patients, but a substantial minority did not appear to grasp the underlying purpose of the instrument. The instrument was well accepted. The pictures were considered to be helpful by most respondents, especially those at the Nepal sites. The variability in the scores for the individual charts across sites was less than expected and not always in the expected direction. The COOP/WONCA system continues to show promise, but needs more validation.