Binary Factor Analysis Research Articles

Pairwise likelihood estimation and limited-information goodness-of-fit test statistics for binary factor analysis models under complex survey sampling.

This paper discusses estimation and limited-information goodness-of-fit test statistics in factor models for binary data using pairwise likelihood estimation and sampling weights. The paper extends the applicability of pairwise likelihood estimation for factor models with binary data to accommodate complex sampling designs. Additionally, it introduces two key limited-information test statistics: the Pearson chi-squared test and the Wald test. To enhance computational efficiency, the paper introduces modifications to both test statistics. The performance of the estimation and the proposed test statistics under simple random sampling and unequal probability sampling is evaluated using simulated data.

Diagnostic models for predicting malignancy in thyroid nodules classified as Bethesda Category III in an endemic region.

This study aims to develop a diagnostic model to help physicians determine whether thyroid nodules categorized as atypia of undetermined significance (AUS) in category III of the Bethesda system are benign or malignant preoperatively. To create a diagnostic model for predicting thyroid nodules' benign or malignant with AUS cytology based on clinical, ultrasonographic, and cytopathological findings. This is a retrospective cohort study involving patients (>19) at risk of thyroid cancer who had thyroidectomy after an AUS cytology. The dataset consists of 53 variables 204 nodules from 183 patients. Binary logistic regression and factor analysis methods were used to identify risk factors for malignancy. Finally, four prediction models were developed using different approaches, based on clinical, pathological clinical + pathological, and the factors. A total of 88 (48.1%) of 183 patients diagnosed with AUS were benign and 95 (51.9%) the malignant. After determining risk factors, four prediction models were developed based on different approaches to assist physicians in deciding to detect AUS nodules early. It was seen that bilaterality was found to be a risk factor for malignancy in the clinical model (pbilaterality = .03) and it was also seen that the pathological variables pale chromatin and irregular contours in the oncocyte variables were risk factors for malignancy (ppalechromatin = .02, pirregularcontoursintheoncocyte = .04). The best model obtained sensitivity and specificity values are 73% and 87% based on clinical and pathological variables. This comprehensive study may provide a more in-depth understanding of AUS and make a notable contribution to healthcare professionals before surgery.

Formal and Informal Institutions in Farmers’ Withdrawal from Rural Homesteads in China: Heterogeneity Analysis Based on the Village Location

Withdrawal from rural homesteads (WRH) in China is mainly conducted under the guidance of government and follows the principle of farmers’ voluntary participation, in which both formal and informal institutions play essential roles. However, few studies have systematically analyzed the institutional factors in WRH. By introducing both formal and informal institutions into the analysis framework, the aim of this study was to explore the impacts of formal and informal institutions on farmers’ behavior to WRH, and the interaction between formal and informal institution in different villages. Based on survey data from farmers in Jinzhai, China, this study adopted a binary probit model and factor analysis. (1) The study revealed that farmers’ cognition of homesteads property rights and their trust in village cadres are the key formal institutional factors affecting farmers’ behavior to WRH, and farmers’ social networks, reciprocal norms, and trust in villagers are the key informal institutional factors affecting farmers’ WRH; (2) Both formal and informal institutions promote farmers’ WRH, and informal institutions play a more important role. However, there is no interaction between formal and informal institutions in the whole sample. (3) Furthermore, the effect of formal and informal institutions on farmers’ WRH have the heterogeneity of village location: there is a complementary relationship between formal and informal institutions in farmers’ WRH for villages with a medium proximity to the county seat, and a substitution relationship for villages far away from the county seat. Finally, this study discusses the implications of these findings on the new round of WRH policy.

Value of blood routine indexes and their ratios in judging the prognosis of adult patients with extensive burns

Objective: To investigate the value of neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and blood platelet count (BPC) in judging the prognosis of adult patients with extensive burns. Methods: From January 2012 to December 2018, 99 adult patients with extensive burns who met the inclusion criteria were admitted to Union Hospital of Fujian Medical University, including 76 males and 23 females, aged 18 to 75 (43±13) years. According to the prognosis, the patients were divided into survival group of 79 cases and death group of 20 cases. Their clinical data were retrospectively analyzed by the method of case-control study. The gender, age, total burn area, inhalation injury, use of mechanical ventilation and white blood cell count, neutrophil count, lymphocyte count, and BPC on post injury day (PID) 1, 3, and 7 were collected, and the NLR, PLR, difference value of BPC on PID 3 and PID 1 (ΔBPC3), difference value of NLR on PID 3 and PID 1 (ΔNLR3), difference value of PLR on PID 3 and PID 1 (ΔPLR3), difference value of BPC on PID 7 and PID 1 (ΔBPC7), difference value of NLR on PID 7 and PID 1 (ΔNLR7), difference value of PLR on PID 7 and PID 1 (ΔPLR7) of patients in the two groups were calculated. Data were statistically analyzed with Mann-Whitney U test, independent sample t test, chi-square test to screen the death-related factors of patients. Binary classification single factor and multifactor logistic regression analysis were used to analyze the death-related factors of patients. The receiver's operating characteristic (ROC) curve of the independent risk factor of death of patients predicting the prognosis of adult patients with extensive burns was drawn, and the area under the curve, the optimal threshold and its sensitivity and specificity were calculated. Results: (1) There were statistically significant differences in total burn area and use of mechanical ventilation of patients between the two groups (Z=-2.615, χ(2)=7.282, P<0.01). (2) On PID 1, there was statistically significant difference in NLR of patients between the two groups (Z=-2.414, P<0.05). On PID 3, there were statistically significant differences in BPC and ΔNLR3 of patients between the two groups (Z=-2.048, -2.780, P<0.05 or P<0.01). On PID 7, there were statistically significant differences in lymphocyte count, BPC, NLR, and ΔNLR7 of patients between the two groups (Z=-2.248, -2.231, -2.641, -3.669, P<0.05 or P<0.01). (3) Binary classification single factor logistic regression analysis showed that the total burn area, mechanical ventilation, BPC and NLR on PID 7, and ΔNLR7 were related to death of patients (odds ratio=1.038, 0.193, 0.990, 1.086, 1.105, 95% confidence interval=1.010-1.067, 0.062-0.598, 0.982-0.998, 1.012-1.165, 1.037-1.178, P<0.05 or P<0.01). Binary classification multifactor logistic regression analysis showed that ΔNLR7 was the independent risk factor of death of adult patients with extensive burns (odds ratio=1.090, 95% confidence interval=1.008-1.178, P<0.05). (4) The optimal threshold of ROC curve of ΔNLR7 for predicting the prognostic death of 97 adult patients with extensive burns was -0.073 4. The sensitivity under the optimal threshold was 65.0%, and the specificity was 78.5%. The area under the ROC curve was 0.776 (95% confidence interval=0.650-0.882, P<0.01). Conclusions: Dynamic monitoring of NLR and BPC is of great significance to assist in judging the prognosis of adult patients with extensive burns. ΔNLR7 is an independent predictor of death in adult patients with extensive burns, while PLR can not predict the death of adult patients with extensive burns.

Evaluation of Doctor-patient communication outcomes in two public hospitals in Enugu and Ebonyi States, Nigeria

Background: Patient-doctor communication is a critical success factor in ensuring accurate diagnosis and treatment. A patient’s satisfaction with such interaction can have positive impact on health outcomes. This study evaluated patient-doctor communication in two tertiary hospitals in two states in southeast Nigeria. Data Source & Methods: Data were collected with a structured questionnaire from 300 patients in two teaching hospitals. Data were analysed using simple percentages, chi-square test of independence, binary logistic regression and factor analysis. Results: Results indicated low level of satisfaction of patients with the quality of communication with their doctors, the main contributor to their dissatisfaction being ‘doctors’ authoritarian communication style’. Factors that positively predicted patients’ satisfaction were ‘doctors’ communication skills’ (p=.000), ‘patients’ religious, cultural and language anxiety influence on communication’ (p=.000), and ‘democratic communication’ (p=.009). Doctors adopted the paternalistic approach in interacting with patients. Conclusion: Patients reported low level of satisfaction with their doctors’ communicative behaviour. This would necessitate a shift from the paternalistic to the patient-centred communication approach in the two hospitals.

SQUAREM: An R Package for Off-the-Shelf Acceleration of EM, MM and Other EM-Like Monotone Algorithms

We discuss R package SQUAREM for accelerating iterative algorithms which exhibit slow, monotone convergence. These include the well-known expectation-maximization algorithm, majorize-minimize (MM), and other EM-like algorithms such as expectation conditional maximization, and generalized EM algorithms. We demonstrate the simplicity, generality, and power of SQUAREM through a wide array of applications of EM/MM problems, including binary Poisson mixture, factor analysis, interval censoring, genetics admixture, and logistic regression maximum likelihood estimation (an MM problem). We show that SQUAREM is easy to apply, and can accelerate any fixed-point, smooth, contraction mapping with linear convergence rate. Squared iterative scheme (Squarem) algorithm provides significant speed-up of EM-like algorithms. The margin of the advantage for Squarem is especially huge for high-dimensional problems or when EM step is relatively time-consuming to evaluate. Squarem can be used off-the-shelf since there is no need for the user to tweak any control parameters to optimize performance. Given its remarkable ease of use, Squarem may be considered as a default accelerator for slowly converging EM-like algorithms. All the comparisons of CPU computing time in the paper are made on a quad-core 2.3 GHz Intel Core i7 Mac computer. R Package SQUAREM can be downloaded at https://cran.r-project.org/web/packages/SQUAREM/index.html.

Analysis of CT characteristics in the diagnosis of Schistosoma japonicum associated appendicitis with clinical and pathological correlation: a diagnostic accuracy study

PurposeTo clarify unique non-contrast CT (NCCT) characteristics for early recognition of Schistosomal associated appendicitis (SAA) differentiating from Non-schistosomal associated appendicitis (NSA).Material and methodsClinical and pathological data of 50 cases with SAA and 60 cases with NSA who underwent emergency appendectomy were retrospectively compared to pre-surgical NCCT features such as direct and indirect signs of acute appendicitis as well as appendicoliths, colon calcifications as diagnostic criteria. Statistical methods such as Chi-square (χ2), t-tests, Principal component analysis (PCA), Binary Logistic regression (LR) and Factor Analysis (FA) were utilized to observe differences and isolate recognizable CT features of SAA. Pre and post hoc diagnostic performance of all criteria was calculated as sensitivity, specificity, and the Odds Ratio (OR).ResultsAge > 50 years, diameter > 13 mm, pneumatosis, peri appendiceal abscess, focal wall defect, perforation; Orbital, linear and point types of appendicular wall calcifications; sigmoid colon and cecal curvilinear calcifications were observed as unique characteristics with a sensitivity of 84–95% and specificity of 91–98% in predicting SAA by OR of 6.2 times. Pre and post hoc hypothetical analysis did not show any significance for all other factors.ConclusionFactors such as elderly age, CT features such as larger appendicular diameter, appendicular wall calcifications along with sigmoid colon, and cecal calcifications, signs of perforation or abscess are characteristic for early recognition of SAA.

Comparing unsupervised probabilistic machine learning methods for market basket analysis

We compare several unsupervised probabilistic machine learning methods for market basket analysis, namely binary factor analysis, two topic models (latent Dirichlet allocation and the correlated topic model), the restricted Boltzmann machine and the deep belief net. After an overview of previous applications of unsupervised probabilistic machine learning methods to market basket analysis we shortly present the methods which we investigate and outline their estimation. Performance is measured by tenfold cross-validated log likelihood values. Binary factor analysis vastly outperforms topic models. The restricted Boltzmann machine attains a similar performance advantage over binary factor analysis. Overall, a deep belief net with 45 variables in the first and 15 variables in the second hidden layers turns out to be the best model. We also compare the investigated machine learning methods with respect to ease of interpretation and runtimes. In addition, we show how to interpret the relationships between hidden variables and observed category purchases. To demonstrate managerial implications we estimate the effect of promoting each category both on purchase probability increases of other product categories and the relative increase of basket size. Finally, we indicate several possibilities to extend restricted Boltzmann machines and deep belief nets for market basket analysis.

TRUST VALUE OF A DIVIDEND : AN EVIDENCE FROM INDONESIA

Even though there are many issues surrounding dividend policy, dividend remains one of the main goals for investors to achieve. The aim of this study is to find out determinants of dividend policy in Indonesia. Most of the samples in observed period have varieties of dividend policies. Data for this study was collected from 258 business entities in the period between 2009 and 2012. For hypotheses testing, a binary logistic regression and factor analysis were used. The result from binary logistic regression showed that share price, earnings per share and current ratio are significant factors for dividend policy, while debt to equity ratio and corporate tax are insignificant. The insignificance of debt and tax was probably due to current ratio affected by accounting adjustments. Even though debt and tax are insignificant, they could not be ignored. Using factor analysis, it is confirmed that, most companies in this study have a similar objective through dividend policy, which is to maximize their share value in the stock market by considering profitability and liquidity on cash availability and also debt and tax. Dividends as a form of “trust value” offered by companies to their shareholders stimulate the trust of investors or shareholders and resulting the increase of share price.

TRUST VALUE OF A DIVIDEND : AN EVIDENCE FROM INDONESIA

Even though there are many issues surrounding dividend policy, dividend remains one of the main goals for investors to achieve. The aim of this study is to find out determinants of dividend policy in Indonesia. Most of the samples in observed period have varieties of dividend policies. Data for this study was collected from 258 business entities in the period between 2009 and 2012. For hypotheses testing, a binary logistic regression and factor analysis were used. The result from binary logistic regression showed that share price, earnings per share and current ratio are significant factors for dividend policy, while debt to equity ratio and corporate tax are insignificant. The insignificance of debt and tax was probably due to current ratio affected by accounting adjustments. Even though debt and tax are insignificant, they could not be ignored. Using factor analysis, it is confirmed that, most companies in this study have a similar objective through dividend policy, which is to maximize their share value in the stock market by considering profitability and liquidity on cash availability and also debt and tax. Dividends as a form of “trust value” offered by companies to their shareholders stimulate the trust of investors or shareholders and resulting the increase of share price. Keywords : dividend policy, share price, corporate tax, current ratio, earnings per share, debt equity ratio

Levels and Sources of Atmospheric Polycyclic Aromatic Hydrocarbons Surrounding an Oil Refinery in Cura&amp;#231;ao

This research measured ambient levels of polycyclic aromatic hydrocarbons (PAHs) surrounding a petrochemical complex on the island of Curacao using passive air sampling. In addition, source elucidation of PAHs was conducted using concentration profiles, distribution profiles, binary diagnostic ratios and factor analysis. Passive air samplers with polyurethane foam collection disks (PAS-PUFs) were deployed in 2011 (n = 43) and in 2014 (n = 30) to evaluate the extent of the emission plume as well as spatial and temporal differences in ambient PAH concentrations. In general, ambient PAH concentrations in Curacao were consistent with other urban and industrialized regions of the world; however, the levels measured downwind of Isla Refineria petrochemical complex were among some of the highest reported ambient PAHs globally. Ambient PAH concentrations ranged from 1.2 to 790 ng/m3 in 2011 and 27 to 660 ng/m3 in 2014, demonstrating no temporal differences. However, significant spatial differences were detected between samples collected upwind and downwind of the petrochemical complex. Significantly higher ambient PAH concentrations were found in the samples collected downwind of the petrochemical complex compared to those upwind in 2014 (p < 0. 0001). Source elucidation revealed the ambient PAHs downwind were dominated by petrogenic emission sources and to a lesser degree pyrogenic emissions, whereas, the upwind locations appear to be equally influenced by both petrogenic and pyrogenic emissions sources.

A Note on the Conversion of Item Parameters Standard Errors

The relations among alternative parameterizations of the binary factor analysis (FA) model and two-parameter logistic (2PL) item response theory (IRT) model have been thoroughly discussed in literature. However, the conversion formulas widely available are mainly for transforming parameter estimates from one parameterization to another. There is a lack of discussion about the standard error (SE) conversion among different parameterizations, when SEs of IRT model parameters are often of immediate interest to practitioners. This article provides general formulas for computing the SEs of transformed parameter values, when these parameters are transformed from FA to IRT models. These formulas are suitable for unidimensional 2PL, multidimensional 2PL, and bi-factor 2PL models. A simulation study is conducted to verify the formula by providing empirical evidence. A real data example is given in the end for an illustration.

The Nutrition Literacy Assessment Instrument is a Valid and Reliable Measure of Nutrition Literacy in Adults with Chronic Disease

ObjectiveTo test the reliability and validity of the Nutrition Literacy Assessment Instrument (NLit) in adult primary care and identify the relationship between nutrition literacy and diet quality. DesignThis instrument validation study included a cross-sectional sample participating in up to 2 visits 1 month apart. Setting/ParticipantsA total of 429 adults with nutrition-related chronic disease were recruited from clinics and a patient registry affiliated with a Midwestern university medical center. Main Outcome MeasuresNutrition literacy was measured by the NLit, which was composed of 6 subscales: nutrition and health, energy sources in food, food label and numeracy, household food measurement, food groups, and consumer skills. Diet quality was measured by Healthy Eating Index–2010 with nutrient data from Diet History Questionnaire II surveys. AnalysisThe researchers measured factor validity and reliability by using binary confirmatory factor analysis; test-retest reliability was measured by Pearson r and the intraclass correlation coefficient, and relationships between nutrition literacy and diet quality were analyzed by linear regression. ResultsThe NLit demonstrated substantial factor validity and reliability (0.97; confidence interval, 0.96–0.98) and test-retest reliability (0.88; confidence interval, 0.85–0.90). Nutrition literacy was the most significant predictor of diet quality (β = .17; multivariate coefficient = 0.10; P < .001). ConclusionsThe NLit is a valid and reliable tool for measuring nutrition literacy in adult primary care patients.

A structural equation modeling approach for examining position effects in large-scale assessments

Position effects may occur in both paper–pencil tests and computerized assessments when examinees respond to the same test items located in different positions on the test. To examine position effects in large-scale assessments, previous studies often used multilevel item response models within the generalized linear mixed modeling framework. Using the equivalence of the item response theory and binary factor analysis frameworks when modeling dichotomous item responses, this study introduces a structural equation modeling (SEM) approach that is capable of estimating various types of position effects. Using real data from a large-scale reading assessment, the SEM approach is demonstrated for investigating form, passage position, and item position effects for reading items. The results from a simulation study are also presented to evaluate the accuracy of the SEM approach in detecting item position effects. The implications of using the SEM approach are discussed in the context of large-scale assessments.

Day‐Ahead Global Solar Radiation Forecasting Using Binary Trees and Factor Analysis

SUMMARYA method is proposed for forecasting global solar radiation. The method is based on weather information using binary trees and factor analysis. The feature of this method is that it is possible to use a simple linear forecasting equation. The method has been tested on meteorological and global solar radiation data obtained at several observation sites, and the results show that it is a promising means of maintaining the balance between demand and supply of electric power in power systems of the near future with a large number of photovoltaic systems installed.

Consumer attitude toward using smart shopping carts: a comparative analysis of Italian and Croatian consumer attitudes

This paper aims to explore consumer attitudes toward using smart shopping cart, considering country of origin, gender, age, and intentions to use smart shopping carts while purchasing. Moreover, it investigates the influence of extracted factors on consumers' attitudes toward using smart shopping carts and the users' levels of digital competence. The data was collected through survey questionnaires using a purposive sample of 313 Croatian and Italian respondents. To this end, we applied statistical methodologies such as binary logistic regression, factor analysis, and analysis of variance. We found that, compared with Croatians, Italian respondents have a more positive attitude toward using smart shopping carts, regardless of age or gender. Moreover, we found that consumers are influenced by two major factors: functional and convenience. Consumers who purchase for functionality reasons will have preferences associated with faster product selection and speeding up the purchasing process without fearing that they lack the necessary expertise. If functionality has the tendency to increase, respondents will not lack ICT knowledge when purchasing with the smart cart.

Further advances on Bayesian Ying-Yang harmony learning

After a short tutorial on the fundamentals of Bayes approaches and Bayesian Ying-Yang (BYY) harmony learning, this paper introduces new progresses. A generic information harmonising dynamics of BYY harmony learning is proposed with the help of a Lagrange variety preservation principle, which provides Lagrange-like implementations of Ying-Yang alternative nonlocal search for various learning tasks and unifies attention, detection, problem-solving, adaptation, learning and model selection from an information harmonising perspective. In this framework, new algorithms are developed to implement Ying-Yang alternative nonlocal search for learning Gaussian mixture and several typical exemplars of linear matrix system, including factor analysis (FA), mixture of local FA, binary FA, nonGaussian FA, de-noised Gaussian mixture, sparse multivariate regression, temporal FA and temporal binary FA, as well as a generalised bilinear matrix system that covers not only these linear models but also manifold learning, gene regulatory networks and the generalised linear mixed model. These algorithms are featured with a favourable nature of automatic model selection and a unified formulation in performing unsupervised learning and semi-supervised learning. Also, we propose a principle of preserving multiple convex combinations, which leads alternative search algorithms. Finally, we provide a chronological outline of the history of BYY learning studies.

Willingness-to-Pay for Agronomic Soil Conservation Practices among Crop-based Farmers in Ekiti State, Nigeria

This study investigated the determinants of willingness-to-pay for agronomic soil conservation practices among crop-based farmers in Ekiti State, Nigeria. Multi-stage random sampling technique was employed to select 90 crop-based farmers from six communities across the three agricultural zones in the State. Data were collected with the used of structured questionnaire. The data collected were analysed using descriptive statistics, binary probit model and factor analysis. The results obtained from the analyses showed that the effects of soil degradation on agricultural production in the area include: Pollution, limited space for agricultural production, erosion, deteriorated environmental quality and reduced soil nutrients among others. The socio-economic attributes of the farmers that significantly influenced their willingness-to-pay for agronomic soil conservation measures include: age (p

Learning binary factor analysis with automatic model selection

Binary Factor Analysis (BFA) uncovers the independent binary information sources from observations with wide applications. BFA learning hierarchically nests three levels of inverse problems, i.e., inference of binary code for each observation, parameter estimation and model selection. Under Bayesian Ying-Yang (BYY) framework, the first level becomes an intractable Binary Quadratic Programming (BQP) problem, while model selection can be conducted automatically during parameter learning. We conduct extensive experiments to reveal that the performance order of four BQP methods is reversed from making BQP optimization to making BYY automatic model selection, which implies that learning is not merely optimization. Moreover, the BFA learning algorithm is further developed with priors over parameters to improve the performance. Finally, based on BFA, we empirically compare BYY with Variational Bayes (VB) and Bayesian information criterion (BIC).

Day Ahead Global Solar Radiation Forecasting Using Binary Trees and Factor Analysis

SUMMARY A method is proposed for forecasting global solar radiation. The method is based on weather information using binary trees and factor analysis. The feature of this method is that it is possible to use a simple linear forecasting equation. The method has been tested on meteorological and global solar radiation data obtained at several observation sites, and the results show that it is a promising means of maintaining the balance between demand and supply of electric power in power systems of the near future with a large number of photovoltaic systems installed.