Factor Extraction Method Research Articles

The new version of a patient classification instrument: assessment of psychometric properties

This paper assessed the reliability and construct validity of the new version of a patient classification instrument. In the development of patient classification instruments, monitoring validity and reliability is essential to assure that patient care requirements and nursing staff workload are appropriately measured. The sample included 194 patients (construct validity test) and 60 patients (inter-rater reliability test) at medical, surgical, and specialized wards of a teaching hospital in the south east of Brazil. The study was conducted in 2009-2010. For analysis purposes, Spearman's correlation and Cronbach's alpha (internal consistency) were used, and weighted kappa (inter-rater reliability), factor analysis with principal axis factoring extraction method (construct validity) and ordinal regression (instrument's predictive ability). A high level of inter-rater agreement was found. The importance of all care areas and their contribution to distinguish patient care needs and category in the new instrument were demonstrated. Results also showed the instrument's high predictive ability (99·6%). The findings give the evidence that the new scale is a reliable and valid tool to assess patient care needs and care category and that it can be used to guide nursing management practice in determining the nursing staff workload.

Early maladaptive schema factors, pain intensity, depressiveness and pain disability: an analysis of biopsychosocial models of pain

Purpose: To test different biopsychosocial models of pain within two different samples. Method: Early maladaptive schemas, pain intensity, depressiveness and pain disability were assessed using questionnaire data from 271 first visit pain patients and 276 municipal employees as controls. Exploratory factor analysis was used as the early maladaptive schema factor extraction method and path analysis as the model specification and estimation method. Results: Cross-sectionally, early maladaptive schema factors were predictors of depressiveness in both groups. The effect size of depressiveness on pain disability was 11 times that of the pain intensity in the pain patient group. The situation was opposite in the control group, where effect size of pain intensity was 5.6 times that of depressiveness. In subgroups of pain duration, the effect size of pain intensity on pain disability became insignificant when pain duration was more than 2 years in pain patients. Conclusions: The study supported the importance of early emotional adversities in predicting depressiveness especially among pain patients. Depressiveness was the main predictor of pain disability in the pain patient group and as the pain duration increased, the significance of pain intensity on disability vanished. Pain intensity was the main predictor of pain disability in the control group.Implications for RehabilitationTo decrease disability among chronic pain patients is mainly to treat their depressiveness.To decrease disability among people with mild pain is mainly to treat their pain intensity.The focus of psychotherapy among depressive chronic pain patients should be a pattern of inadequacy, shame, submission, failure, social isolation and dependence.

Exploration and Validation of the Dimensions of Stigma

Stigma research is hampered by lack of consensus about the number of dimensions making up the stigma construct and what these dimensions measure. Two studies were conducted testing the dimensionality of stigma. Using 105 items proposed to measure stigma in previous research, the first study (N = 307) conducted an exploratory factor analysis using the maximum likelihood method of factor extraction. Results supported five factors that were designated as labeling, negative attribution, separation, status loss, and controllability. Using these factors, a second study (N = 263) demonstrated support for the goodness of fit of the proposed 5-dimensional stigma model.

Exploratory factor analysis revisited: How robust methods support the detection of hidden multivariate data structures in IS research

Exploratory factor analysis is commonly used in IS research to detect multivariate data structures. Frequently, the method is blindly applied without checking if the data fulfill the requirements of the method. We investigated the influence of sample size, data transformation, factor extraction method, rotation, and number of factors on the outcome. We compared classical exploratory factor analysis with a robust counterpart which is less influenced by data outliers and data heterogeneities. Our analyses revealed that robust exploratory factor analysis is more stable than the classical method.

Wafer Level Package with Y shaped TSV and Vacuum Sealing by Cu-Sn Isothermal Solidification for MEMS Resonator

A novel WL- CSP structure for MEMS device is proposed. Key features are: “Y-shaped” TSV is fabricated to reduce cost; Cu-Sn isothermal solidification is used to achieve lower temperature bonding; I/O interconnection and vacuum sealing are achieved simultaneously simplifying the whole process. Average shear strength of 25.5 MPa and excellent leak rate of around 1.9×10−9atm cc/s have been achieved, which meet the requirements of MIL-STD-883E. Four point probe setup is used to measure the resistance of the “Y shaped”-TSV and the contact resistance of the Cu/Sn IMC bond joint. “Q factor extraction method” is used to monitor the vacuum property of the packaging structure by integrating a MEMS resonator with a resonant frequency of 1.3 KHz. Reliability tests such as long-term and accelerated life testing are also performed both achieving good results.

Principal domains of behavioral psychopathology identified by the Bipolar Inventory of Signs and Symptoms Scale (BISS)

Current symptom rating scales and diagnostic categories for bipolar disorder (BD) do not provide dimensional profiles of the types of behavior disturbed in this complex disorder. To overcome these limitations we identified the principal domains of behavioral symptomatology in bipolar individuals, including all mood states, and used a more comprehensive rating scale for BD: the Bipolar Inventory of Signs and Symptoms Scale (BISS). A total of 246 patients with BD (196 with BD type I, and 50 with BD type II) were interviewed using the BISS. Exploratory factor analysis was performed on the BISS results using the maximum likelihood factor extraction method, followed by oblique rotation of the extracted factor loadings. We determined the strength of relationships between factor scores using the Pearson correlation coefficient. The following five factors were extracted: mania, depression, irritability, anxiety and psychosis. Anxiety was significantly correlated with depression and irritability. The mania factor score was only weakly associated with the other four factors. The domains of the BISS capture both the historical categories of depression and mania, plus irritability, psychosis, and an additional principal domain, anxiety. Despite the common occurrence of anxiety in BD, it has not been identified in most prior factor analyses, in part due to limited coverage of anxiety symptoms in the source scales.

The dependability of general-factor loadings: The effects of factor-extraction methods, test battery composition, test battery size, and their interactions

To understand the extent to which the general-factor loadings of tests are inherent in their characteristics or due to the sampling of tests, the number of tests in the correlation matrix, and the factor-extraction methods used to obtain them, test scores from a large sample of young adults were inserted into independent and overlapping batteries of varying sizes. Principal factors analysis, maximum-likelihood estimation, and principal components analysis yielded general-factor loadings for each test. Generalizability theory analyses revealed that the characteristics of the tests consistently contributed the largest percentage of variance. Variance attributable to the factor-extraction method and its interactions was sizeable when principal components analysis was included in the analysis but negligible when it was excluded. Psychometric sampling error produced sizeable variance components in some analyses, and its effects were magnified when test batteries diminished in size. When results from principal components analysis were excluded and when the effects of psychometric sampling error were reduced, general-factor loadings were highly dependable across varying conditions.

A SCALE EVALUATING THE EMOTIVITY AND WELL-BEING OF ELDERLY (ITALIAN ACRONYM: SVEBA): ANALYSIS OF PSYCHOMETRIC CHARACTERISTICS

The psychopathology in the aged is an increasing burden for the last decades of the life and a large source of expenditure. An early recognition and treatment could lead to reduce personal distress and improve prognosis. For the use in the general practitioner (GP) office and ward settings most of the short check-lists available are focused on depression symptoms. For this reason a 15 items check-list, oriented to cover a wider array of symptoms, has been designed for the Italian population in the ‘90 (called SVEBA abbreviated from its Italian name). This work intended to investigate the presence of symptomatological clusters in order to detect different profiles of symptoms in populations with different comorbidities, in 214 home-dwelling elderly, with a mean age 80.2 years, referred to the geriatric memory clinic. We used the Keiser-Meyer-Olkin and Bartlett tests to check for applicability of factorial analysis, then a principal axis factoring extraction method was applied. The analysis identified the following factors: the first, collected items related to lack of motivation and initiative The second is related to the perceived “locus of control”. The third, collected items related to sleep disturbance. The fourth, included items related to somatic complaints and anxiety. In the structure of SVEBA index is possible to identify three main symptom profiles related to motivation, anxiety and somatic symptoms and sleep disturbances.

A new method of diode ideality factor extraction from dark I–V curve

Most of the techniques have been developed to extract diode ideality factor utilize the one-exponential diode model. However, for a correct description of two linear regions in the logI–V (current–voltage) graph of unipolar devices, one-exponential diode model is not sufficient. We have derived a new model which is named Beta (β) model for the calculation of diode ideality factor from dark current–voltage characteristic of the device (p–i–n device). Results obtained from our model are considerably in compliance with the experimental data.

Peak load forecasting using Bayesian regularization, Resilient and adaptive backpropagation learning based artificial neural networks

Up to 7 days ahead electrical peak load forecasting has been done using feed forward neural network based on Steepest descent, Bayesian regularization, Resilient and adaptive backpropagation learning methods, by incorporating the effect of eleven weather parameters and past peak load information. To avoid trapping of network into a state of local minima, the optimization of user-defined parameters viz., learning rate and error goal has been performed. The sliding window concept has been incorporated for selection of training data set. It was then reduced as per relevant selection according to the day type and season for which the forecast is made. To reduce the dimensionality of input matrix, the Principal Component Analysis method of factor extraction or correlation analysis technique has been used and their performance has been compared. The resultant data set was used for training of three-layered neural network. In order to increase the learning speed, the weights and biases were initialized according to Nguyen and Widrow method. To avoid over fitting, early stopping of training was done at the minimum validation error.

Dynamic factor extraction of cross‐sectional dependence in panel unit root tests

AbstractRecently, considerable emphasis has been placed on the problems arising out of cross‐sectional dependence in panel unit root tests. This paper adopts the factor‐based cross‐sectional dependence paradigm of Bai and Ng (2005) but suggests alternative factor extraction methods. Some theoretical results for these methods are provided. Further, a detailed Monte Carlo study of these methods for multiple and persistent factors is undertaken. It is found that results are radically different from the serially uncorrelated single‐factor case. Tests perform much worse and in some cases it is preferable not to correct at all for cross‐sectional dependence. Copyright © 2007 John Wiley & Sons, Ltd.

Development from within: an evaluative research on economic development strategies

Research on the practice of adopting local economic development (LED) strategies is important to understand our local world as it is and what it might be made to be as a place for community. This article on economic development strategies (EDS) highlights the results from a survey of 82 small communities representing the Yukon Territory and ten provinces in Canada. The purpose was to evaluate the positive and additive effects of past local action and community initiatives so as to understand the variation in the adoption of local economic development strategies of Canada’s small towns and local municipalities. Using a questionnaire as instrument for data collection, the study employed hierarchical regression analysis and principal component analysis (PCA) as method for factor extraction and composite assessment on the effects of adopting EDS for community. The PCA solution was applied to evaluate the structure of correlation between the community characteristics as control variables in the baseline model for regression analysis and the past local action and community initiatives as independent variables. The results of the hierarchical regression analysis showed that local initiatives have significant and additive effects on the adoption of EDS by small communities. The study findings offer some insights into some perspectives of ‘development from within’ to mean the local economic development practice in Canadian communities.

The validity and reliability of the Tertiary Student Values Scale (TSVS)

To explore the factorial composition of an instrument developed to assess value orientations in tertiary students, the Tertiary Student Values Scale (TSVS), using data from culturally diverse undergraduate dental students. A 68-item questionnaire was used to collect the data. The questionnaire included 15 3-item subscales developed in a manner consistent with the Kluckhohn and Strodtbeck value orientation model. The psychometric properties were evaluated using a sample of students from 4 Australian dental schools. The questionnaire was administered to 364 students aged 18-50 years, mean age 21.3 years (SD 3.45 years), using a convenience sampling method. Scores on the 45 items were factor analysed using the maximum-likelihood estimation method for factor extraction with oblique rotation (oblimin). Internal consistency was examined on all of the 3-item subscales, using Cronbach's alpha. The analysis indicates that the TSVS reflects the hypothesised 15-dimension construct of value orientation. Furthermore, the analysis showed that the identified 15 factors were independent of one another and were sufficiently reliable for group comparisons. With 1 exception, all subscales yielded a Cronbach's alpha > or = 0.55, the exception being 1 subscale with alpha = 0.40 (range 0.40-0.80). Results indicated that value orientation is a complex construct, but that it is quantifiable along multiple dimensions in a psychometrically valid manner. Further refinement of this instrument would increase its value as a tool for policy makers designing educational programmes and services for culturally diverse student groups.

Exploratory Factor Analysis in Two Measurement Journals: Hegemony by Default

Exploratory factor analysis studies in two prominent measurement journals were explored. Issues addressed were: (a) factor extraction methods, (b) factor retention rules, (c) factor rotation strategies, and (d) saliency criteria for including variables. Many authors continue to use principal components extraction, orthogonal (varimax) rotation, and retain factors with eigenvalues greater than 1.0.

Modelling Core Inflation for the UK Using a New Dynamic Factor Estimation Method and a Large Disaggregated Price Index Dataset

Recent work in the macroeconometric literature considers the problem of summarising efficiently a large set of variables and using this summary for a variety of purposes including forecasting. This paper applies a new factor extraction method to the extraction of core inflation and forecasting of UK inflation in the recent past.

Development of a Fatigue Symptom Checklist for Commercial Drivers: An Experimental Trial

3 ) Objectives: Fatigue is a primary human factor for decreased job performance in the work place. It is well documented that drowsiness is a typical symptom of fatigue and is closely asso ciated with commercial drivers’safety and well-being. However, few studies have been con ducted to develop or validate fatigue symptom instruments for a working population. The main purpose of this study was to develop a general fatigue checklist and a driving fatigue checklist for Korean commercial drivers. Methods: A total of 287 bus drivers in a commercial transportation company participated in a self-administered survey that was designated Study 1. Based on the statistical results of Study 1, a focus meeting with 16 professional consultants was conducted to revise the fatigue symptom instrument for Study 2. In Study 2, 288 commercial drivers (156 bus drivers and 132 truck dri vers) participated in the revised questionnaire survey. All collected responses were entered into a SPSS worksheet and the data analysis was conducted using SPSS software 11.1. The exploratory factor analysis used in this study followed the principle component factoring rule and the varimax rotation method for factor extraction. The criteria for item selection were an Eigen value of 1.0 or greater, a communality score of .50 or greater, and no ‘fence rider’property over the extracted factors. Results: Through Study 1, the consultant meeting, and Study 2, a general fatigue checklist was developed with a total of 3 factors and 11 items, and a driving fatigue checklist was devel oped with 2 factors and 10 items. The 3 factors of the general fatigue checklist were physical fatigue, psychological fatigue, and chronic tiredness. The two factors of the driving fatigue

Replicability of first-order 16PF-5 factors: an analysis of three parcelling methods

In the present study, the primary factor structure of the 16PF-5 is analysed with both the items and parcels obtained through three different methods in a sample of 288 males and 347 females with a mean age of 25.09 years (SD: 9.20). Four factor extraction methods, Scree Test, Parallel Analysis, Eigenvalue One and Maximum Likelihood suggested different number of factors for the 16PF-5, with the Scree Test being the most adequate to represent the theoretical factor structure of this instrument. In regard to parcels, factor extraction methods pointed to between 8 and approximately 20 factors. The analysis of the items of the 16 PF-5 extracting 16 factors, achieved a 63% correct classification of the items in their theoretical factors, while the Single Factor (S) item parcelling method achieved a completely correct classification (100%) when fixing the δ parameter to −2.

Artificial neural network-based peak load forecasting using conjugate gradient methods

The daily electrical peak load forecasting (PLF) has been done using the feed forward neural network (FFNN)-based upon the conjugate gradient (CG) back-propagation methods, by incorporating the effect of 11 weather parameters, the previous day peak load information, and the type of day. To avoid the trapping of the network into a state of local minima, the optimization of user-defined parameters, namely, learning rate and error goal, has been performed. The training dataset has been selected using a growing window concept and is reduced as per the nature of the day and the season for which the forecast is made. For redundancy removal in the input variables, reduction of the number of input variables has been done by the principal component analysis (PCA) method of factor extraction. The resultant dataset is used for the training of a 3-layered NN. To increase the learning speed, the weights and biases are initialized according to the Nguyen and Widrow method. To avoid over fitting, an early stopping of training is done at the minimum validation error.

Artificial Neural Network-Based Peak Load Forecasting Using Conjugate Gradient Methods

Daily electrical peak load forecasting has been done using the feed forward neural network based upon the conjugate gradient back propagation methods by incorporating the effect of eleven weather parameters, the previous day's peak load information, and the type of day. To avoid the trapping of the network into a state of local minima, the optimization of user-defined parameters viz., leaming rate and error goal has been performed. The training data-set has been selected using a growing window concept and is reduced per the nature of the day and the season for which the forecast is made. For redundancy removal in the input variables, reduction of the number of input variables has been done using the principal component analysis method of factor extraction. The resultant data set is used for the training of a three-layered neural network To increase the leaming speed, the weights and biases are initialized according to the Nguyen and Widrow method. To avoid overfitting, an early training is stopped early at the minimum validation error.

The robustness of tests of structural change in equity returns using factor analysis

The objective of this paper is to perform various tests of structural change within the context of factor analysis and determine how robust the results of such tests are to; the security selection criteria in constructing portfolios, portfolio size, and methods of factor extraction. The question of a possible structural change is addressed by examining the Stock Market Crash of October 1987. Monthly returns on 257 securities listed on the London Stock Exchange covering the period January 1976 to December 1995 are used. The data period incorporates the Stock Market Crash of October 1987.