Multiple Indicator Model Research Articles

Impact of Demographic Backgrounds by Humanities and Social Sciences Students on Their Psychological of Emotional Intelligence Skill: Structural Equation Multiple Cause and Multiple Indicator (SEM-MIMIC) Model

Impact of Demographic Backgrounds by Humanities and Social Sciences Students on Their Psychological of Emotional Intelligence Skill: Structural Equation Multiple Cause and Multiple Indicator (SEM-MIMIC) Model

Psychometric properties of the Persian version of the Reinforcement Sensitivity Theory Personality Questionnaire (RST-PQ)

BackgroundThe Reinforcement Sensitivity Theory of Personality Questionnaire (RST-PQ) originated from the Revised Reinforcement Sensitivity Theory of Personality. This study was conducted to assess the psychometric properties of the Persian version of the RST-PQ among a group of Iranian adults. MethodThe cross-sectional study was carried out among 600 Iranian adults utilizing a convenient sampling method, following specific participant selection criteria to enhance the study methodology's transparency (including the age range between 18 and 35 years' participants without major psychiatric diagnoses). Participants completed both the Iranian version of the Reinforcement Sensitivity Theory Personality Questionnaire (RST-PQ) and the Five-Factor NEO-FFI questionnaire. Confirmatory factor analysis, employing the multiple indicators model (MIMIC) approach, was utilized in this study to control for demographic variables such as age and gender. ResultsThe confirmatory factor analysis results showed an acceptable fit of the proposed six-factor model based on the English version of RST-PQ (CFI = 0.905; RMSEA = 0.053). Also, Cronbach's alpha values confirmed the internal consistency of the proposed structure. In addition, competing models were also used to select the best-proposed model. In this way, different models were evaluated, assuming a change in the correlation intensity between BIS and the Fight-Flight-Freeze System (FFFS). ConclusionsThe convergent validity results with the Five-Factor Personality measure provided further support and were consistent with previous research findings. It is crucial to have an Iranian-language version of the RST-PQ to promote RST research and show how this theoretical framework aids in explaining and predicting various actions, whether they are abnormal or healthy.

Lifting urban mobility for the poor: Cable-cars, travel satisfaction and subjective well-being

Studies on travel and life satisfaction in vulnerable Global South contexts are scarce. This paper contributes by addressing how travel satisfaction, neighborhood satisfaction, and social capital relate to life satisfaction among a low-income community in Bogotá (Colombia) as a case study. Building on the available literature, we propose six hypotheses to understand such relationships before and after a cable car implementation, considering control and treatment groups. We defined seven latent variables and three objective indicators. We tested the hypotheses using a multiple-cause multiple-indicator modeling approach, which allowed us to identify how the comprehensive cable car intervention impacts perceptions and life satisfaction. Results showed that the principal factors associated with life satisfaction were neighborhood satisfaction as well as leisure activity participation, while travel time and transport affordability had negative effects. Positive changes in satisfaction regarding the travel experience can trigger significant improvements in life satisfaction in low-income communities in Latin America.

Personal noise exposure during daily commutes and subjectively reported stress: A trip stage level analysis of MobiliSense data

BackgroundThe auditory and non-auditory health effects of noise have long been established in the literature but previous studies have mainly been in the context of occupational risk. Recent research suggests that daily noise exposures occurring during social activities and commute may be associated with higher psychological stress. Our aim was to explore the association between modes of transportation and noise on the one hand and noise exposures and reported stress on the other hand. Although existing literature shows that noise exposure is especially high during commutes, studies on the topic have been sparse due to cost and logistic constraints; furthermore, sample sizes have been small. MethodsThe present study uses data collected on the daily commutes of 253 participants of the Mobilisense cohort study between 2018 and 2020. Personal dosimeters were used to measure noise exposure by frequency bands over a period of 4 days, resulting in a sample of 7800 trip stage windows. Participants reported trip stress levels during an a posteriori phone mobility survey on a scale from 1 (no stress) to 7 (significantly stressful conditions). Modes of transportation (metro, car, walking, etc.) were collected from the same mobility survey based on Global Positioning System (GPS) receivers. ResultsWhile all transport modes resulted in higher exposure to low frequency noise compared to walking, all modes but tramway and driving or being the passenger of a car were associated with an increased exposure to high frequency noise. The LAeq noise indicator (overall noise) was associated with reported stress: for every 10 dB(A) increase in LAeq, individuals reported experiencing 1.118 times (95% confidence interval: 1.067, 1.172) higher levels of stress. Multiple noise indicator models did not show evidence that specific frequency components were associated with stress beyond overall noise. ConclusionOur findings suggest that noise exposure during commutes vary according to modes of transportation. Given that noise exposure resulted in higher reported levels of stress, future research should examine transportation noise effects on physiological variables.

Value of the ABCD3 Score Combined with a Multiple Indicators Model in the Evaluation of the Prognosis of Non-Disabling Ischemic Cerebrovascular Events

Value of the ABCD3 Score Combined with a Multiple Indicators Model in the Evaluation of the Prognosis of Non-Disabling Ischemic Cerebrovascular Events

A Bayesian Probabilistic Framework for Identification of Individuals with Dyslexia

ABSTRACT Purpose Bayesian-based models for diagnosis are common in medicine but have not been incorporated into identification models for dyslexia. The purpose of the present study was to evaluate Bayesian identification models that included a broader set of predictors and that capitalized on recent developments in modeling the prevalence of dyslexia. Method Model-based meta-analysis was used to create a composite correlation matrix that included common predictors of dyslexia such as decoding, phonological awareness, oral language, but also included response to intervention (RTI) and family risk for dyslexia. Bayesian logistic regression models were used to predict poor reading comprehension, unexpectedly poor reading comprehension, poor decoding, and unexpectedly poor decoding, all at two levels of severity. Results Most predictors made independent and substantial contributions to prediction, supporting models of dyslexia that rely on multiple rather than single indicators. RTI was the strongest predictor of poor reading comprehension and unexpectedly poor reading comprehension. Phonological awareness was the strongest predictor of poor decoding and unexpectedly poor decoding, followed closely by family risk. Conclusion Bayesian-based models are a promising tool for implementing multiple-indicator models of identification. Ideas for improving prediction and implications for theory and practice are discussed.

Assessment of Path Model Fit: Evidence of Effectiveness and Recommendations for use of the RMSEA-P

We review the development of path model fit measures for latent variable models and highlight how they are different from global fit measures. Next, we consider findings from two published simulation articles that reach different conclusions about the effectiveness of one path model fit measure (RMSEA-P). We then report the results of a new simulation study aimed at resolving the questions of whether and how the RMSEA-P should be used by organizational researchers. These results show that the RMSEA-P and its confidence interval is very effective with multiple indicator models at identifying misspecifications across large and small sample sizes and is effective at identifying true models at moderate to large sample sizes. We conclude with recommendations for how the RMSEA-P can be incorporated along with other information into model evaluation.

Psychometric evaluation of the tinnitus impact questionnaire using patients seeking help for tinnitus or tinnitus with hyperacusis

Objective To evaluate the psychometric properties of the Tinnitus Impact Questionnaire (TIQ), whose questions focus on assessing the impact of tinnitus on the patient’s day to day activities, mood, and sleep, and not on hearing difficulties. Design This was a retrospective cross-sectional study. Study sample Data were included for 172 adult patients who attended a tinnitus and hyperacusis clinic in the UK within a six-month period and who had completed the TIQ. Results Two items whose scores were very highly correlated with those for other items were removed, leaving seven items. Exploratory factor analysis suggested a single factor for the TIQ. A multiple causes multiple indicator model showed significant but very small direct effects of age on TIQ scores for two items, after adjustment for gender. The TIQ had excellent internal consistency, with Cronbach’s alpha = 0.89. The total TIQ score was moderately to strongly correlated with scores for the Tinnitus Handicap Inventory, Screening for Anxiety and Depression-Tinnitus questionnaire, Hyperacusis Questionnaire, and Hyperacusis Impact Questionnaire, indicating convergent validity. The TIQ score was weakly correlated with the pure-tone average hearing threshold, indicating discriminant validity. Conclusions The TIQ is a brief, valid and internally consistent questionnaire for assessing the impact of tinnitus.

Factors Affecting Employee Engagement Based on an Employee Attitude Survey in Japan

Japanese companies are beginning to recognize the importance of employee engagement. However, many companies have not been able to leverage employee engagement to increase their corporate value. This is possibly because it is difficult to determine and utilize the factors affecting employee engagement. To clarify the relationship between engagement and its influencing factors, we constructed a multiple indicator model and performed a covariance structure analysis. Data for the analyses were obtained from the 2019 “Survey on Work Styles and the Current Conditions Related to Labor Shortage,” conducted by the Japan Institute for Labour Policy and Training. We then extracted four factors to create an "engagement model". The study identified two factors that influence engagement: empowerment and loyalty. The results can be used to inform policies on improving employee engagement by leveraging these factors.  

Development and validation of the DISCUS scale: A reliable short measure for assessing experienced discrimination in people with mental health problems on a global level

BackgroundThe Discrimination and Stigma Scale (DISC-12) was specifically developed to measure experienced and anticipated discrimination reported by people with mental health problems. However, the length of the DISC-12 may represent a disadvantage especially in country settings with limited human capacity and infrastructure. The purpose of the study was to develop a short version of DISC-12 (DISCUS) to address these limitations. MethodsData from 1087 participants with major depressive disorder and 732 patients with schizophrenia were collected as part of two research network studies across 35 countries - Anti Stigma Programme European Network (ASPEN) and International Study of Discrimination and Stigma (INDIGO). We used a Meta Exploratory Factor Analysis (meta-EFA) and a Multiple Causes Multiple Indicators (MIMIC) Model to reduce the number of items in the DISC-12 scale. The validity and reliability of the reduced scale (DISCUS) was tested in 202 people with the full spectrum of mental disorders recruited in a cross-sectional study conducted in South London. Psychometric validation for the reduced scale used confirmatory factor analysis and measures of Cronbach's alpha and Pearson's correlation coefficient. Resultsmeta-EFA reduced twenty-one items to twelve items. An additional item was discarded with the use of the MIMIC model. The 11-item DISCUS demonstrated excellent reliability (Cronbach's alpha >0.85), good fit (Tucker Lewis Index and Comparative Fit Index value>0.9) and weak to moderate construct validity. ConclusionsThe DISCUS scale is a consistent and valid instrument to measure experienced and anticipated discrimination predominantly in personal and social relationships in global settings.

A method to nourished beach stability assessment: The case of China

Beach nourishment is an effective method for maintaining shoreline position, and it has been preferred to restore beaches in China. However, in the post-nourishment assessment, there are only some single-indicator models (e.g. beach durability, sediment loss rate) which could not fully reflect the actual performance of a nourished beach. This study presents a multiple-indicator model of nourished beach stability assessment, aiming at quantitatively assessing the physical performance of nourished beaches. Geomorphic factors affecting the physical performance of nourished beaches were analyzed and summarized through critical review of literature. An indicator system for assessing the stability of nourished beaches was established by integrating oceanographic parameter (i.e. wave energy, storm intensity, and storm frequency), design parameter (i.e. beach length, grain size, volume density, beach planform, and beach protection structure) and adaptability parameter (i.e. intertidal width, dry beach width, and erosional hot spot). Based on data collecting, each indicator was graded into five classes from 1 to 5, and the associated weight of each indicator was given by the method of variation coefficient. Finally, a multi-indicator and indicator-weighted assessment model for the stability of nourished beaches was established and a new index called Nourished Beach Stability Index (NBSI) was proposed. The physical performances of sixteen nourished beaches representative of China were then quantitatively assessed. The results showed this assessment model could better assess the physical performance of nourished beaches than the single-indicator assessment models for taking beach's characteristics into account. The results can help scientists and managers make appropriate management strategies. This multiple-indicator assessment model can be used to both quantitatively assess the actually physical performance of the beach nourishment projects and to choose the design scheme from multiple alternatives for beach nourishment project.

Effect of critical incidents on public transport satisfaction and loyalty: an Ordinal Probit SEM-MIMIC approach

Supplying public transport systems with high levels of service quality is fundamental for retaining users and attracting new ones. Policies that improve transit service quality will ultimately lead to more sustainable travel patterns. Measuring overall service quality implies measuring the quality of several specific attributes and is prevalently evaluated through the perceptions of users, using satisfaction rates. In this study, we demonstrate that there is a further element that can influence users’ perceptions, the so-called critical incidents (CI), defined as encounters that are particularly satisfying or dissatisfying. The concept is not restricted to ratings of the predefined product or service attributes, because customers who experience CI remember them well and can usually describe the experience. We implement a framework that includes CI and is innovative for several reasons. Firstly, we introduce attribute-specific (e.g. reliability, safety, comfort) CI to explain attribute-specific satisfaction levels, and then we model these with latent constructs allowing for measurement error in recalling the CI. We also demonstrate that using an Ordinal-Probit approach leads to more accurate results than its numerical counterpart, the latter possibly presenting biased results. Finally, we present a full Structural Equation Multiple Cause Multiple Indicator (SEM-MIMIC) model, which corrects for heterogeneity in the perceptions of users regarding satisfaction with the various service attributes, with the overall service, and with loyalty. For these purposes, we analyse an extensive database (96,763 interviewed passengers) derived from Customer Satisfaction Surveys in the railway services offered in the hinterland of Milan. Our main contribution to the literature is that we show that the occurrence of a CI has a substantial negative impact on passenger satisfaction for all service attributes. As it is a policy-related variable, it can be managed directly by the public transport (PT) administrators. To better plan and improve PT services, avoiding CI in specific items should be the strategy to follow. On the other hand, reliability, and added-value services are the primary service attributes that have a positive effect on satisfaction with the overall service and, in turn, on loyalty. Our model can be useful for PT administrators as it sheds light on how to improve the service according to users’ preferences, and by considering the differences among user categories.

Influence of Firm Size on Cost of Capital Through Corporate Social Responsibility Disclosure of the Listed Companies in the Stock Exchange of Thailand

The aim of this research is to investigate the relationship between corporate social responsibility disclosure and cost of capital of different firm sizes listed on the stock exchange of Thailand. This was achieved through the multiple indicator and multiple cases model (MIMIC) of 370 companies listed on the stock exchange of Thailand. The analysis of firm size in this study indicates that small-sized (SIZES) medium (SIZEM) and large-sized (SIZEL) firms have effect on the cost of capital in terms of debts (COD) only with through corporate social responsibility disclosure. The statistical result indicates that the effect of size on corporate social responsibility disclosure and cost of capital in small companies has an indirect, positive effect on the cost of capital in terms of debts (COD) through corporate social responsibility disclosure, with a significance level of .01 and correlation coefficient of 0.17. In comparison the medium and large companies has a negative effect, with a significance level of .05 and correlation coefficient of 0.05 of the medium companies and large companies has a negative with a significance level of .01 and correlation coefficient of 0.09.

Influence of Firm Size on Cost of Capital through Corporate Social Responsibility Disclosure of the Listed Companies in the Stock Exchange of Thailand

The aim of this research is to investigate the relationship between corporate social responsibility disclosure and cost of capital of different firm sizes listed on the stock exchange of Thailand. This was achieved through the multiple indicator and multiple cases model (MIMIC) of 370 companies listed on the stock exchange of Thailand. The analysis of firm size in this study indicates that small-sized (SIZES) medium (SIZEM) and large-sized (SIZEL) firms have effect on the cost of capital in terms of debts (COD) only with through corporate social responsibility disclosure. The statistical result indicates that the effect of size on corporate social responsibility disclosure and cost of capital in small companies has an indirect, positive effect on the cost of capital in terms of debts (COD) through corporate social responsibility disclosure, with a significance level of .01 and correlation coefficient of 0.17. In comparison the medium and large companies has a negative effect, with a significance level of .05 and correlation coefficient of 0.05 of the medium companies and large companies has a negative with a significance level of .01 and correlation coefficient of 0.09.

The Genetic and Environmental Association Between Parental Monitoring and Risk of Cannabis, Stimulants, and Cocaine Initiation in a Sample of Male Twins: Does Parenting Matter?

Our aim was to test the direction of causation between self-report parental monitoring (PM) and the liability to illicit drug initiation (DI) as indicated by cannabis, cocaine, and stimulants. We fitted a multiple indicator model to test causal and non-causal models based on a large, genetically informative cross-sectional sample of male twins. The sample comprised 1,778 males aged 24-62 years from the Virginia Adult Twin Study of Psychiatric and Substance Use Disorders. Data came from self-report measures of lifetime cannabis, stimulants, and cocaine initiation, and retrospective assessment of PM between ages 8-17 years. Multivariate modeling showed that familial aggregation in PM and DI were both explained by a combination of additive genetic and shared environmental effects. Moreover, the significant association between PM and DI was best explained by a correlated liability model versus causal models. PM has typically been assumed to be an environmental, causal risk factor for drug use and has been shown to be among the more salient environmental risk factors for illicit DI. Our data were not consistent with this causal hypothesis. Instead, a correlated liability model in which PM and risk of DI share common genetic and environmental risks provided a better fit to the data.

Comparison of Shadow Economies: The Case of Ghana, Nigeria and UK

This study seeks to assess the size and the trend of the shadow economies of Ghana, Nigeria and the United Kingdom. The multiple indicator and multiple causes model (MIMIC) is employed for this analysis. The model consists of two parts; the structural equation aspect and the measurement aspect. The structural equation model estimates the impact of the observed variables in determining the level of shadow economic activities. The measurement model estimates the coefficients of the indicator variables. Results from the study show variation in the causal factors of shadow economic activities in the various countries. The size of Ghana’s shadow economy stands at 36.73%, Nigeria 47.75% and UK, 15.05% at the end of the 2012 fiscal year. The average level of such activities for the past three decades is 30.20% of the official economy in Ghana, 50.36% in Nigeria and 14.07% in UK. DOI: 10.5901/mjss.2016.v7n1p248

A reduced factor structure for the PROQOL–HIV questionnaire provided reliable indicators of health-related quality of life

ObjectivesTo identify a simplified factor structure for the PROQOL–human immunodeficiency virus (HIV) questionnaire to improve the measurement of the health-related quality of life (HRQL) of HIV-positive patients in clinical care and research settings. Study Design and SettingHRQL data were collected using the eight-dimension PROQOL-HIV questionnaire from 2,537 patients (VESPA2 study). Exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) validated a simpler four-factor structure and assessed measurement invariance (MI). Multigroup analysis assessed the effect of sex, age, and antiretroviral therapy (ART) on the resulting factor scores. Correlations with symptom and Short Form (SF)-12 self-reports assessed convergent validity. ResultsItem analysis, EFA, and CFAs confirmed the validity [comparative fit index (CFI), 0.948; root mean square error of approximation, 0.064] and reliability (α's ≥ 0.8) of four dimensions: physical health and symptoms, health concerns and mental distress, social and intimate relationships, and treatment-related impact. Strong MI was demonstrated across sex and age (decrease in CFI <0.01). A multiple-cause multiple-indicator model indicated that HRQL correlated as expected with sex, age, and the ART status. Correlations of HRQL, symptom reports, and SF-12 scores evidenced convergent validity criterion. ConclusionThe simplified factor structure and scoring scheme for PROQOL-HIV will allow clinicians to monitor with greater reliability the HRQL of patients in clinical care and research settings.

A multiple indicator model for panel data: An application to ICT area-level variation

Consider the case in which we have data from repeated surveys covering several geographic areas, and our goal is to characterize these areas on a latent trait that underlies multiple indicators. This characterization occurs, for example, in surveys of information and communication technologies (ICT) conducted by statistical agencies, the objective of which is to assess the level of ICT in each area and its variation over time. It is often of interest to evaluate the impact of area-specific covariates on the ICT level of the area. This paper develops a methodology based on structural equations models (SEMs) that allows not only the ability to estimate the level of the latent trait in each of the areas (building an ICT index) but also to assess the variation of this index in time, as well as its association with the area-specific covariates. The methodology is illustrated using the ICT annual survey data collected in the Spanish region of Catalonia for the years 2008–2011.

Efficiency, effectiveness, equity (E3). Evaluating hospital performance in three dimensions

There are well-established frameworks for comparing the performance of health systems cross-nationally on multiple dimensions. A sub-set of such comprehensive schema is taken up by criteria specifically applied to health service delivery, including hospital performance.We focus on evaluating hospital performance, using the New Zealand public hospital sector over the period 2001–2009 as a pragmatic and illustrative case study for cross-national application. We apply a broad three-dimensional matrix – efficiency, effectiveness, equity – each based on two measures, and we undertake ranking comparisons of 35 hospitals.On the efficiency dimension – relative stay, day surgery – we find coefficients of variation of 10.8% and 8.5% respectively in the pooled data, and a slight trend towards a narrowing of inter-hospital variation over time. The correlation between these indicators is low (.20). For effectiveness – post-admission mortality, unplanned readmission – the coefficient of variation is generally higher (24.1% and 12.2%), and the trend is flat. The correlation is again low (.21). The equity dimension is assessed by quantifying the degree of ethnic and socio-economic variation for each hospital. The coefficient of variation is much higher – 40.7–66.5% for ethnicity, 55.8–84.4% for socio-economic position – the trend over time is mixed, and the correlation is moderate (.41). On averaging the rank of hospitals across all measures it is evident that there is limited consistency across the three constituent dimensions.While it is possible to assess hospital performance across three dimensions using an illustrative set of standard measures derived from routine data, there appears to be little consistency in hospital rankings on these New Zealand data for the period 2001–2009. However, the methodology of using rankings derived from readily available data – possibly allied with multiple or composite indicator models – has potential for the cross-national comparison of hospital profiles, and assessments in three dimensions provide a more holistic and rounded account of performance.

Multiple indicators model of long-term mortality in traumatic brain injury

Objective: To examine the prognostic ability of protein S100B, neuron-specific enolase (NSE) and glial fibrillary acid protein (GFAP) for prediction of 1-year mortality in patients with traumatic brain injury (TBI) in relation to clinical and radiological characteristics of TBI.Methods: Brain injury was quantified in 84 patients (Glasgow Coma Scale [GCS] ≤ 12) using clinical (GCS, pupils), radiological (computed tomography [CT] classification and individual CT characteristics) and biochemical (S100B, NSE and GFAP) data at admission and in the acute post-injury period.Results: Initial and peak S100B, NSE and GFAP concentrations were higher in non-survivors (n = 26) than in survivors (p-value range: <0.001–0.018). Cox regression showed that GFAP and S100B concentration and the temporal profile of S100B were more powerful independent predictors of mortality than baseline clinical and radiological characteristics or clinical and radiological indicators of neurological deterioration. The prognostic models containing admission variables and those available during the subsequent clinical course showed the same discrimination ability (area under receiver characteristic curve 0.92), but the model based on variables available in the acute post-injury period calibrated better (p = 0.428).Conclusion: Mortality at 1-year post-TBI is accurately predicted by the combination of GFAP and S100B concentration and clinical and radiological characteristics at admission or in the acute post-injury period.