Three-way Model Research Articles

Comparison of cecal microbiota composition in a three-way cross model in two hybrid pigs

Comparison of cecal microbiota composition in a three-way cross model in two hybrid pigs

Associations between change in labour market policies and work stressors: a comparative longitudinal survey data analysis from 27 European countries

BackgroundMany studies have shown that work stressors have a negative impact on health. It is therefore important to gain an understanding of how work stressors can be reduced. Recent studies have shown that employees in countries with high investments into labour market policies less often report exposure to work stressors. Although these studies are indicative of an influence of the political level on work stressors, they are based on cross-sectional cross-country analyses where causal assumptions are problematic. The aim of this study is to extend the existing evidence by longitudinally testing whether changes in labour market policies are related to changes in work stressors.MethodsWe used comparative longitudinal survey data from the European Working Conditions Survey (27 countries; for the years 2005, 2010, 2015). The measurement of work stressors is based on two established work stress models: effort-reward imbalance (ERI) and job demand-control (job strain). To measure labour market policies, we used information on active (ALMP) and passive labour market policies (PLMP). After excluding persons with missing data, 64,659 participants were eligible for the ERI and 67,114 for job strain analyses. Estimation results are provided by three-way multilevel models (individuals, country-years, country), which allow us to estimate longitudinal and cross-country macro-effects.ResultsAn increase in ALMP leads to a decrease of ERI. The analyses for the subcomponents ‘effort’ and ‘reward’ showed that mainly the ‘reward’ component is positively associated with ALMP. The association between ALMP and ‘reward’ shows that an increase in ALMP investments is related to an increase in rewards. Yet, no significant longitudinal associations between ALMP and job strain, and between PLMP and the work stressors, were observed.ConclusionsThe study extends the current knowledge with longitudinal information by showing that an increase in ALMP is associated with an increase in rewards and a decrease of ERI. These longitudinal analyses may support a causal interpretation. The findings of this study have important policy implications. Our main result suggests that investments into ALMP can lead to better working conditions.

Factor Uniqueness of the Structural Parafac Model

Factor analysis is a well-known method for describing the covariance structure among a set of manifest variables through a limited number of unobserved factors. When the observed variables are collected at various occasions on the same statistical units, the data have a three-way structure and standard factor analysis may fail. To overcome these limitations, three-way models, such as the Parafac model, can be adopted. It is often seen as an extension of principal component analysis able to discover unique latent components. The structural version, i.e., as a reparameterization of the covariance matrix, has been also formulated but rarely investigated. In this article, such a formulation is studied by discussing under what conditions factor uniqueness is preserved. It is shown that, under mild conditions, such a property holds even if the specific factors are assumed to be within-variable, or within-occasion, correlated and the model is modified to become scale invariant.

Clustering Protein Super Secondary Structure with Artificial Neural Network Based Self Organizing Map Machine Learning Approach Using In-Memory Computing Environment

Protein’s super secondary structure knowledge is important to understand protein functions which is vital for all living organisms. In this research, an in-memory computing approach is created to identify the super secondary structure of protein on primary protein sequences. The Artificial Neural Network (ANN) based Self Organizing Map (SOM) algorithm was used to develop a three-way predictive model. The developed clustering model helps to assign protein super secondary structures mainly into â-Turns. Also this model is implemented in an in-memory computing environment—SPARK. The analysis results using ANN-SOM approach in clustering protein super secondary structures provide better high accuracy in the in-memory computing environment.

A multiple attribute decision making three-way model for intuitionistic fuzzy numbers

In order to use three-way decision (TWD) to solve multiple attribute decision making (MADM) problems, in this article, a new TWD model with intuitionistic fuzzy numbers (IFNs) is proposed. First of all, we define the relative loss functions to demonstrate some features of loss functions in TWDs, which is the basis for future research. Then, based on the correlation between the loss functions and the IFNs, we get the relative loss functions based on IFNs. At the same time, the classification rules of the TWDs are discussed from different viewpoints, including the thresholds and their properties. Aiming at MADM problems with unreasonable values, a new integrated method of relative loss functions is established to obtain a fairer loss integration result of alternatives. In addition, considering that there are no decision attributes and only condition attributes in MADM, we use grey relational degree to calculate the condition probability. In the end, a novel TWD model is proposed to solve MADM problems with IFNs, and a practical example on selecting suppliers is used to demonstrate its effectiveness and practicability.

Characteristics and source apportionment of ambient single particles in Tianjin, China: The close association between oxalic acid and biomass burning

Abstract A single particle source analysis was conducted for particulate matter and oxalic acid using a single particle aerosol mass spectrometer during a typical biomass burning period in Tianjin, China. The adaptive resonance theory 2 neural network algorithm was applied to analyze mass spectra data and generate 20 particle clusters. Size-resolved time series of the particle classes were put into an advanced three-way model (ABB, multi-size three-way model) for source apportionment. Seven sources were identified, including crustal dust, biomass burning, fossil fuel combustion, secondary organic, secondary nitrate and secondary sulfate. Oxalic acid containing particles accounted for 1.4% of the total detected particles during the overall sampling period, and the fraction increased to 2.6% during the biomass burning period. Oxalic acid was predominantly observed in the Na-K-EC, EC, EC-K, EC-aged, K, Levoglucosan and Fe particle classes. The mixing fraction of oxalic acid in these particle types, and their diurnal variation and size distribution patterns are related to different formation mechanisms. Source contributions to oxalic acid were apportioned, and secondary sulfate (49%), biomass burning (25%), vehicle exhaust (17%), and secondary organic sources (8%) may have contributed to the amount of oxalic acid-containing particles. The contribution of secondary sulfate sources follows the O3 concentration during the sampling period. This is likely because strong photochemical oxidation activity during the sampling period produces more oxalic acid precursors from Volatile organic compounds. Biomass burning also clearly contributed the number of oxalic acid particles, because precursors emitted by biomass burning can be quickly oxidized into oxalic acid, and more oxalic acid was formed during transportation. Fe particles may also play important role in oxalic acid deposition.

Collaborative Approach to Management Using a Three-Way Management Model

Collaborative Approach to Management Using a Three-Way Management Model

Considering the effectiveness of philanthropic collective action: a community ecology perspective

PurposeThe purpose of this paper is to explore the relationship between social capital and collective action at the county level in the US while incorporating the moderating effects of community racial diversity and urbanity and to find the changing effects of social capital on philanthropic collective action for community education.Design/methodology/approachThis paper employs a quantitative research design. The dependent variable measures philanthropic collective action for community education while the independent variable for social capital is measured as a community level index. Moderating variables include a community racial diversity index and urbanity. This analysis tests and interprets interaction effects using moderated multiple regression (MMR), with the baselines of MMR being grounded to multivariate ordinary least squares (OLS) regression. Analyses are carried out in the context of the USA during 2006 and 2010, with US counties employed as the unit of analysis.FindingsThe effects of social capital on philanthropic contributions decline in counties with low- and mid-levels of racial diversity. On the contrary, the effects of social capital increase in highly racially diverse counties. The three-way interaction model result suggests that racial diversity positively moderates social capital on philanthropic collective action for community education where the effect of social capital is strong and positive in highly racially diverse urban communities.Originality/valueThis research complicates the notion that social capital and racial diversity are negatively associated when exploring collective action and community education, and suggests effects of social capital varies with moderating effects on philanthropic collective action for community education.

Local Agency and Complex Power Shifts in the Era of Belt and Road: Perceptions of Chinese Aid in the South Pacific

ABSTRACTBeijing’s ambitious Belt and Road Initiative (BRI) has exacerbated a longstanding concern about the power shift from the West to China. The existing debate, however, is both motivated by, and fixated on, the strategic concerns of and about great powers (and to a lesser extent, middle powers). What is often overlooked is the concerns and voices of smaller countries and contested regions where some of the power-shift symptoms allegedly unfold, such as the South Pacific. To traditional donors such as Australia, the power dynamism in the South Pacific is largely a linear, two-way model of power shift from Western donors to Beijing. Challenging this model, this article proposes a complex, three-way model to bring small and seemingly passive actors into the power shift equation. To illustrate, the article uses Papua New Guinea’s (PNG) perceptions of China’s aid vis-à-vis Australia’s aid as a case study. Relying mostly on primary (interview) sources, this study not only reveals some nuanced attitudes of local actors toward the great-power interactions, but also highlights the hitherto neglected role and agency of Pacific Island nations and their domestic politics in the inherently complex power shifts.

An advanced three-way factor analysis model (SDABB model) for size-resolved PM source apportionment constrained by size distribution of chemical species in source profiles

Source samples including crustal dust, cement dust, coal combustion were sampled and ambient samples of PM2.5 and PM10 were synchronously collected in Hefei from April to December 2014. The size distributions of the markers in the measured source profiles were incorporated into ME-2 solution to develop a new method, called the SDABB model (an advanced ABB three-way factor analysis model incorporating size distribution information). The performance of this model was investigated using three-way synthetic and ambient dataset. For the synthetic tests, the size distributions of markers estimated by the SDABB model were more consistent with true condition. The AAEs between estimated and observed contributions of the SDABB ranged from 15.2% to 29.0% for PM10 and 19.9%–31.6% for PM2.5, which is lower than those of PMF2. For the ambient PM, six source categories were identified by SDABB for both sizes, although the profiles were different. The source contributions were sulphate (33.33% and 24.53%), nitrate and SOC (22.33% and 18.16%), coal combustion (19.01% and 18.23%), vehicular exhaust (12.99% and 12.07%), crustal dust (10.69% and 19.40%) and cement dust (1.65% and 5.39%) for PM2.5 and PM10 respectively. In addition, the estimated ratios of Al, Si, Ti and Fe in CRD were 0.76, 0.84, 1.10 and 0.85; those of Al and Si in CC were 0.42 and 0.66; Ca and Si in CD were 0.95 and 1.10; NO3− and NH4+ in nitrate were 1.11 and 1.01; and SO42− and NH4+ in sulphate were 0.96 and 1.16. These modeled ratios were consistent with the measured ratios. The size distribution of contributions also came close to reality. Thus, the advanced SDABB three-way model can better capture the characteristics of sources between sizes by effectively incorporating the size distributions of the markers as physical constraints.

Do employees actually intend to turnover when betrayed? Evidence from China and the USA

PurposeThe main purpose of present study is to investigate how familial collectivism and gender affect the psychological contract violation–turnover intention relationship by comparing Chinese with American samples.Design/methodology/approachIn total, 688 and 892 full-time workers were recruited, respectively, from China and the USA to form the two samples. Then, three-way interaction regression models were used to test the hypotheses.FindingsThe results indicate that familial collectivism will negatively moderate the psychological contract violation–turnover intention relationship in the Chinese sample and positively moderate their relationship in the American sample. Moreover, the moderating effect of familial collectivism on the relationship between psychological contract violation and turnover intention is significant among the male employees and insignificant among the female employees for Chinese sample. Whereas for the American sample, the moderating effects are significant among both the male and the female employees.Originality/valueThis study improves the theoretical model of Turnley and Feldman (1999) by examining the moderating effect of familial collectivism and gender differences on the relationship between psychological contract violation and turnover intention. And two samples (China vs the USA) are used in the study, which helps to explain the possible difference in influencing the relationship between psychological contract violation and turnover intention between two nations. The main practical implication for managers is that organizations should recognize the importance of the gender role and individuals’ culture orientation when implementing different human resource management policies.

Mortality salience and prejudice towards ethno-religion minorities: Results and implications of a Nigerian study

The present study examined mortality salience (MS) effect on prejudice towards an ethno-religion minority group of Northern Nigeria. Participants were 120 undergraduate students (females = 41.67%) with an age range between 17 and 38 years. The students completed a Distance-(relationship)-Situation (DS) measure under alternative conditions: with MS priming and a control condition. Following a three-way mixed model ANOVA, results showed MS to predict prejudice across relationship situations of secret disclosure, business partnership, and cooperating to get a task done. Consistent with terror management theory, MS effects on ethno-cultural prejudice expression apply across relationship situations.

19p13.3-GADD45B common variants and 19q13.3-PPP1R13L and 19q13.3-CD3EAP in lung cancer risk among Chinese

Lung cancer is the most common cause of cancer-related mortality worldwide. The GADD45 gene family plays important roles in a variety of the responses to cell injury including cell cycle checkpoints, apoptosis, DNA repair and anti-tumor immunity. The 19p13.3-GADD45B encoded protein product is involved in apoptosis and inhibiting tumor growth. To evaluate the association of 19p13.3-GADD45B common variants and lung cancer risk, the present study containing 544 Chinese lung cancer cases and 550 cancer-free controls was conducted. Three htSNPs (haplotype-tagging single nucleotide polymorphism) (rs7354, rs14384, and rs3783501) covering 95% of the common haplotype diversity in 19p13.3-GADD45B and interaction of 19p13.3-GADD45B and 19q13.3-PPP1R13L and 19q13.3-CD3EAP variants and smoking-duration were explored. Genotype and allele frequencies and haplotype distributions of the 19p13.3-GADD45B 3 htSNPs were not associated with lung cancer risk after adjustment for smoking status. 19p13.3-GADD45B rs7354 was associated with lung cancer risk among ≤20 (years) smokers [C/A-A/A versus CC, OR (95% CI) = 3.20 (1.11–9.20), P = 0.025] in a dominant model stratified by smoking duration. MDR (multifactor dimensionality reduction) analyses showed that smoking history as main effect and three-way models (smoking duration, 19p13.3-GADD45B rs3783501, 19q13.3-CD3EAP rs967591) (P = 0.001–0.002) indicated statistically significant association with lung cancer risk. The study identified evidence implicating DNA damage response genes on chromosome 19 in etiology of smoke-exposed lung cancer. In conclusion, our findings demonstrate that 19p13.3-GADD45B rs7354 variant and interaction between 19p13.3-GADD45B rs3783501 and 19q13.3-CD3EAP rs967591 may play a role in association with smoke-exposed lung cancer among Chinese. 19p13.3-GADD45B variants should be further evaluated in large prospective studies with molecular pathological annotations of lung cancer.

Physical activity, body mass index and waist circumference change, and normal-range glycated hemoglobin on incident diabetes: Jackson Heart Study

ABSTRACTObjectives: The purpose of this study was to 1) evaluate whether physical activity has a protective effect on incident diabetes among African Americans across combinations of body mass index (BMI) and waist circumference (WC), 2) evaluate the effect of changes on BMI and WC on incident diabetes, and 3) evaluate the effect of ‘normal range’ glycated hemoglobin (A1C) on incident diabetes.Methods: Data from the prospective Jackson Heart Study were evaluated, with baseline data assessed between 2001 and 2004 and follow-up data occurring between 2009 and 2013. Physical activity was assessed via a validated questionnaire, with measured BMI, WC and A1C assessed via standard procedures.Results: The sample included 2,450 adults who did not have evidence of diabetes at the baseline assessment, with 286 incident diabetes cases occurring at the follow-up assessment. Physical activity did not have a protective effect against incident diabetes across different BMI and WC combinations. Notably, BMI change from baseline to follow-up was associated with incident diabetes (HR = 1.08; 95% CI: 1.03–1.13). Further, higher levels of A1C within the ‘normal-range’ was associated with incident diabetes (HR = 7.51, 95% CI = 2.66–21.25).Conclusion: Increases in BMI over time and higher A1C within the normal range were associated with incident diabetes. Serial monitoring of BMI, as well as A1C, even among those with a ‘normal’ A1C, may be warranted by clinicians. Future work evaluating this novel three-way model (physical activity, BMI and WC) should consider utilizing an objective measure of physical activity.

A new statistical model for analyzing rating scale data pertaining to word meaning.

The concrete-abstract categorization scheme has guided several research programs. A popular way to classify words into one of these categories is to calculate a word's mean value in a Concreteness or Imageability rating scale. However, this procedure has several limitations. For instance, results can be highly distorted by outliers, ascribe differences among words when none may exist, and neglect rating trends in participants. We suggest using an alternative procedure to analyze rating scale data called median polish analysis (MPA). MPA is tolerant to outliers and accounts for information in multiple dimensions, including trends among participants. MPA performance can be readily evaluated using an effect size measure called analog R 2 and be integrated with bootstrap 95% confidence intervals, which can prevent assigning inexistent differences among words. To compare these analysis procedures, we asked 80 participants to rate a set of nouns and verbs using four different rating scales: Action, Concreteness, Imageability, and Multisensory. We analyzed the data using both two-way and three-way MPA models. We also calculated 95% CIs for the two-way models. Categorizing words with the Action scale revealed a continuum of word meaning for both nouns and verbs. The remaining scales produced dichotomous or stratified results for nouns, and continuous results for verbs. While the sample mean analysis generated continua irrespective of the rating scale, MPA differentiated among dichotomies and continua. We conclude that MPA allowed us to better classify words by discarding outliers, focusing on main trends, and considering the differences in rating criteria among participants.

A comprehensive assessment of exposures to respirable dust and silica in the taconite mining industry

ABSTRACTThis study assessed the present-day levels (year 2010–2011) of exposure to respirable dust (RD) and respirable silica (RS) in taconite mines and evaluated how the mining process influences exposure concentrations. Personal samples (n = 679) were collected to assess exposure levels of workers to RD and RS at six mines in the Mesabi Iron Range of Minnesota. The RD and RS concentrations were measured using the National Institute for Occupational Safety and Health (NIOSH) 0600 and NIOSH 7500, respectively. Between-mine, between-SEG (similar exposure groups), within-SEG, and within-worker components of variability for RD and RS exposures were estimated using a two- or three-way nested random-effects ANOVA model. The majority of RD concentrations across all mines were below the Mine Safety and Health Administration (MSHA) Permissible Exposure Limit (PEL). The highest concentrations of RD were often observed in either the Pelletizing or Crushing departments, which are inherently dusty operations. With a few exceptions, the concentrations of RS in the crushing and concentrating processes were higher than those in the other mining processes, as well as higher than the American Conference of Governmental Industrial Hygienists (ACGIH) Threshold Limit Value (TLV) for RS. The magnetic separation and flotation processes in the concentrating department reduced the levels of RS significantly, and lowered the percentage of quartz in RD in the pelletizing department. There was little variability among the six mines or between the two mineralogically distinct zones for either RD or RS exposures. The between-SEG variability for RS did not differ substantially across most of the mines and was a major component of exposure variance. The within-SEG (or between-worker) variance component was typically the smallest because in many instances one worker from a SEG within a mine was monitored multiple times. Some of these findings were affected by the degree of censoring in each SEG and mine, characteristics of the taconite rock, seasonal effects during sampling, or the tasks assigned to each job in that mine.

Generalized three-way decision models based on subset evaluation

The notion of three-way decisions was originally introduced based on the need to explain the three regions of probabilistic rough sets. In a three-way decision model, every object can be evaluated by a function and according to the evaluation value, the object can be arranged in one of the three regions (i.e., positive, negative, and boundary regions). In this study, we generalize Yao's three-way decision models to a case where every subset in the universe can be evaluated by the evaluation function, and we then propose generalized three-way models. The properties and examples of these new models are presented, as well as extensions of these models. We also give some remarks regarding Hu's three-way decision spaces. Three-way matroids are introduced based on Hu's axiomatic approach and our generalized three-way models. Furthermore, three-way matroids are generalized to three fuzzy matroids as an application of our new model. Finally, we suggest future research related to our new models and three-way fuzzy matroids.

Access to Debt Finance: Which Policies Work? Empirical Evidence from Sub-Saharan Africa

Are the structural policy reforms effective in reducing debt financing constraints on formal sector enterprises in sub-Saharan Africa? We do not know. And the reason is the relatively limited research on the effectiveness of policies in the credit market. Using policy variables from the World Bank and the Enterprise Surveys data, the analysis involves three-way error component models. The results are indicative that taken together; structural policy reforms reduce debt financing constraints, at least, as it pertains to working capital needs. There is heterogeneity in the results. Changes in the business regulatory environment benefit large firms more than small ones. Financial sector reforms affect enterprises of all sizes relatively equally. For all the twelve countries, together, trade sector reforms initially increase the likelihood of access to debt finance by 20 percent until a policy threshold, beyond which progressive reforms in the trade sector reduce the probability by as much as 13 percent. Also, not all countries experience the same effects from trade sector reforms. The result is robust to different indicators of credit constraint and measures of structural reforms. The results have implications on the World Bank's push towards reforms on trade policy across countries.

Size distribution, directional source contributions and pollution status of PM from Chengdu, China during a long-term sampling campaign

Long-term and synchronous monitoring of PM10 and PM2.5 was conducted in Chengdu in China from 2007 to 2013. The levels, variations, compositions and size distributions were investigated. The sources were quantified by two-way and three-way receptor models (PMF2, ME2-2way and ME2-3way). Consistent results were found: the primary source categories contributed 63.4% (PMF2), 64.8% (ME2-2way) and 66.8% (ME2-3way) to PM10, and contributed 60.9% (PMF2), 65.5% (ME2-2way) and 61.0% (ME2-3way) to PM2.5. Secondary sources contributed 31.8% (PMF2), 32.9% (ME2-2way) and 31.7% (ME2-3way) to PM10, and 35.0% (PMF2), 33.8% (ME2-2way) and 36.0% (ME2-3way) to PM2.5. The size distribution of source categories was estimated better by the ME2-3way method. The three-way model can simultaneously consider chemical species, temporal variability and PM sizes, while a two-way model independently computes datasets of different sizes. A method called source directional apportionment (SDA) was employed to quantify the contributions from various directions for each source category. Crustal dust from east-north-east (ENE) contributed the highest to both PM10 (12.7%) and PM2.5 (9.7%) in Chengdu, followed by the crustal dust from south-east (SE) for PM10 (9.8%) and secondary nitrate & secondary organic carbon from ENE for PM2.5 (9.6%). Source contributions from different directions are associated with meteorological conditions, source locations and emission patterns during the sampling period. These findings and methods provide useful tools to better understand PM pollution status and to develop effective pollution control strategies.

Asymptotic posterior distributions for balanced nested multi-way models with a large number of main effect levels

ABSTRACTWe derive the explicit form for the asymptotic posterior distribution of the balanced nested multi-way variance components model with the assumption that the number of the main factor levels tends to infinity while the number of any specific effect factor levels remains fixed. Under the multi-way model, we also study two different parameterizations, called the standard and the centering, and the relationship between certain quadratic forms of random effects and the variance component parameters. The asymptotic results are illustrated by a three-way model and by a simulation study under a two-way case.