Covariance Structure Models Research Articles

Effect of Food Consumption Values of Vietnamese Consumers on the Reliability and Purchase Intention of Korean Home Meal Replacements

The Vietnamese home meal replacement (HMR) market is expected to face intensified competition due to economic development and urbanization. This study analyzes how the food consumption values of Vietnamese consumers affect the perceived reliability and intention to purchase Korean food in the form of HMRs and provides basic data to establish strategies for Korean HMRs to secure an advantage in an intensely competitive market. A survey was conducted with Vietnamese consumers who had used Korean HMRs before and are constantly using HMRs on a regular basis. To analyze the relationships between food consumption values, the reliability of Korean HMR, and the intention to purchase Korean HMRs, exploratory factor analysis, reliability analysis, confirmatory factor analysis, and covariance structural models were used. Among the factors of food consumption value, health, safety, time saving, and convenience have a positive effect on the reliability of Korean HMRs, while family and cost-effectiveness do not. Moreover, this reliability has a positive effect on the purchase intention of Korean HMRs. This study is significant in that while investigating Korean HMRs, it is pioneering research on Vietnamese consumers regarding HMRs. Therefore, the results of this study can be used to secure the competitiveness of Korean HMRs in the Vietnamese market.

The Effect of Witnessed Incivility on Instigated Incivility: Focused on Mediating Effect of Stress

Purpose Although the research stream of incivility consistently has focused on this concept for about twenty years, researchers’ interests have merely reached at the witnessed incivility. Because of the lack of studies on the witnessed incivility, this study tries to identify the relationship witnessed incivility has with the other variables. Design/Methodology/Approach In detail, the research model examined the bad outcome that an employee who witnessed incivility gets stresses that make the employee instigates incivility. To analyze the research model, the sample data was composed of 210 respondents who work for Korean companies, and the data analyzed by the covariance structural equation modeling method. Findings As a result, it is examined that witnessed incivility has positive effect on workplace stress, and workplace stress had positive effect on the outcome variable, instigated incivility. it is also analyzed that witnessed incivility has significant indirect positive effect on the outcome variable via the bootstrapping method. The result means incivility at workplace can spread out thorough the way of witnessed incivility to the other colleagues. Research Implications The most important implication is that this study found out the new possible bad consequence of incivility, which implies the more studies needs to be focused on the witnessed incivility. Moreover, this study also commits to examine the empirical possibility of incivility spiral.

Supplemental Material for Assessing an Alternative for “Negative Variance Components”: A Gentle Introduction to Bayesian Covariance Structure Modeling for Negative Associations Among Patients With Personalized Treatments

Supplemental Material for Assessing an Alternative for “Negative Variance Components”: A Gentle Introduction to Bayesian Covariance Structure Modeling for Negative Associations Among Patients With Personalized Treatments

Testing Mean and Covariance Structures with Reweighted Least Squares

ABSTRACT Chi-square tests based on maximum likelihood (ML) estimation of covariance structures often incorrectly over-reject the null hypothesis: when the sample size is small. Reweighted least squares (RLS) avoids this problem. In some models, the vector of parameter must contain means, variances, and covariances, yet whether RLS also works in mean and covariance structures remains unexamined. This research extends RLS to mean and covariance structures, evaluating a generalized least squares function with ML parameter estimates. A Monte Carlo simulation study was carried out to examine the statistical performance of ML vs RLS with multivariate normal data. Based on empirical rejection frequencies and empirical averages of test statistics, this study shows that RLS performs much better than ML in mean and covariance structure models when sample sizes are small, whereas it does not perform better than ML to reject misspecified models.

Gene-by-Crisis Interaction for Optimism and Meaning in Life: The Effects of the COVID-19 Pandemic

The corona virus disease 2019 (COVID-19) pandemic and the restrictions to reduce the spread of the virus has had a large impact on daily life. We investigated the individual differences in the effect of the COVID-19 pandemic and first lockdown on optimism and meaning in life in a sample from the Netherlands Twin Register. Participants completed surveys before (N = 9964, Mean age: 48.2, SD = 14.4) and during the first months of the pandemic (i.e. April–May 2020, N = 17,464, Mean age: 44.6 SD = 14.8), with a subsample completing both surveys (N = 6461, Mean age T1: 48.8, SD = 14.5). We applied genetic covariance structure models to twin data to investigate changes in the genetic architecture of the outcome traits due to the pandemic and the interaction of genes with the environmental exposure. Although 56% and 35% of the sample was negatively affected by the pandemic in their optimism and meaning in life, many participants were stable (32% and 43%) or even showed increased optimism and meaning in life (11% and 22%). Subgroups, specifically women, higher educated people, and people with poorer health, experienced larger negative effects. During the first months of the pandemic, slightly lower heritability estimates for optimism and meaning in life (respectively 20% and 25%) were obtained compared to pre-pandemic (respectively 26% and 32%), although confidence intervals overlap. The lower than unity genetic correlations across time (.75 and .63) suggest gene-environment interactions, where the expression of genes that influence optimism and meaning in life differs before and during the pandemic. The COVID-19 pandemic is a strong exposure that leads to imbalanced effects on the well-being of individuals. Some people decrease in well-being, while others get more optimistic and consider their lives as more meaningful during the pandemic. These differences are partly explained by individual differences in genetic sensitivity to extreme environmental change. More knowledge on the person-specific response to specific environmental variables underlying these individual differences is urgently needed to prevent further inequality.

How do digital natives perceive and react toward online advertising? Implications for SMEs

ABSTRACT Advertising was once touted as a ‘big boys’ marketing tool, but the advent of the Internet has led to the emergence of online advertising, which has benefitted marketing organizations of all sizes, especially small and medium enterprises (SMEs), for 20 years since the new millennium. However, the emergence and proliferation of digital natives as a new generation of consumers necessitate further research to ensure the continued attractiveness, effectiveness, and relevance of online advertising. Furthermore, there is a need to consolidate the multifaceted nature of technology and media in online advertising and the corresponding behavior enacted by consumers, particularly digital natives, today. In this regard, this paper endeavors to examine the perceptions and reactions of digital natives toward online advertising using the theory of planned behavior, technology acceptance model, and uses and gratifications theory as an integrated theoretical lens to guide this examination. Using covariance structural equation modeling on a sample of 380 digital natives, this paper finds that the ease of use, usefulness, entertainment gratification, credibility, design, and personalization of online advertisement positively influence the attitude of digital natives toward online advertisement. However, assurance from online advertisement did not produce any significant effect, a unique finding that exemplifies the confidence that digital natives exhibit in digital environments as a self-assured generation. Finally, this paper finds that the attitude and subjective norms among digital natives toward online advertisement and the security and responsiveness of the website of the online advertised product positively influence the intention of digital natives to purchase the online advertised product. The implications of these findings for theory and practice as well as its limitations and future research directions conclude the paper.

Antecedents of University Performance: Does Strategy Matter?

In a bid to contribute to the increasing body of extant interdisciplinary research within the antecedents of university performance and strategic management domains, this study investigates the role of generic strategies in the perceived performance of universities. Using a case study of eight Nigerian universities and survey responses from 380 academics and administrative staff from these universities, the study tested four succinct hypotheses using the covariance structural equation modeling (CB-SEM) technique. Findings revealed that while there was a limited link between differentiation strategy and performance, there was a substantially strong link between focus strategy and performance according to the findings. Similarly, findings revealed that respondents from public-private universities perceived their institutions as having the strongest generic strategy-performance connection, followed by respondents from the public sector. The cost leadership-performance path demonstrated no significant effect.

Social desirability bias as an influencing factor of ethical consumer behavior

Consumers usually consider themselves as more ethical than their peers, manifesting a need to appear more socially orientated than they actually are. The main objective of this study was to analyze the influence of social desirability bias on ethical consumer behavior considered at a component level. Data were collected from a sample of 332 Romanian individuals from the 18-26 age group. The data analysis process involved co-variance structural equation modeling performed with the help of AMOS. Results show that both the positive and negative sides of social desirability significantly influence the three dimension of ethical consumer behavior. Therefore, based on results from this study, researchers can better understand the complex structure of ethical consumer behavior form a different point of view.

Incremental Model Fit Assessment in the Case of Categorical Data: Tucker–Lewis Index for Item Response Theory Modeling

The Tucker–Lewis index (TLI; Tucker & Lewis, 1973), also known as the non-normed fit index (NNFI; Bentler & Bonett, 1980), is one of the numerous incremental fit indices widely used in linear mean and covariance structure modeling, particularly in exploratory factor analysis, tools popular in prevention research. It augments information provided by other indices such as the root-mean-square error of approximation (RMSEA). In this paper, we develop and examine an analogous index for categorical item level data modeled with item response theory (IRT). The proposed Tucker–Lewis index for IRT (TLIRT) is based on Maydeu-Olivares and Joe's (2005) M_2 family of limited-information overall model fit statistics. The limited-information fit statistics have significantly better Chi-square approximation and power than traditional full-information Pearson or likelihood ratio statistics under realistic situations. Building on the incremental fit assessment principle, the TLIRT compares the fit of model under consideration along a spectrum of worst to best possible model fit scenarios. We examine the performance of the new index using simulated and empirical data. Results from a simulation study suggest that the new index behaves as theoretically expected, and it can offer additional insights about model fit not available from other sources. In addition, a more stringent cutoff value is perhaps needed than Hu and Bentler's (1999) traditional cutoff criterion with continuous variables. In the empirical data analysis, we use a data set from a measurement development project in support of cigarette smoking cessation research to illustrate the usefulness of the TLIRT. We noticed that had we only utilized the RMSEA index, we could have arrived at qualitatively different conclusions about model fit, depending on the choice of test statistics, an issue to which the TLIRT is relatively more immune.

Is Sustainable Consumption Translated into Ethical Consumer Behavior?

Nowadays, sustainability is assumed to have high potential for promoting ethical consumer behavior. The aim of this study was to analyze the influence of sustainable behavior on consumer intention to be ethical when it comes to political, social, and environmental dimensions. Therefore, insightful results can be brought forward to explain consumer ethical behavior from a different perspective. Covariance structural equation modelling in AMOS was used for data analysis. Three antecedents, namely environmental, social, and economic dimensions of sustainable consumption, are found to have a significant and positive impact on intention to engage in ethically consumer behavior. In this context, companies seeking to proactively approach eco-friendly consumers will need to understand the complexity of the decision-making process of ethically minded consumers.

Метод Монте-Карло для оцінювання опціонів у субдифузійних моделях арифметичного броунівського руху

This paper focuses on applying the Monte Carlo approach to option pricing in markets with illiquid assets. Anomalous sub-diffusion is a well-known model for describing such markets when relatively long periods without any trading are observed. For constructing sub-diffusive models we need to replace a calendar time t with some stochastic processes S(t), which is called inverse subordinator. The inverse subordinator S(t) means first hitting time and is based on subordinator processes. In this paper, we propose to use the gamma process as a subordinator for Bashelie sub-diffusion model. Using well-known properties for gamma and inverse gamma processes we find the covariance structure of fractional Bachelier model with FBM time-changed by gamma process and then explore the asymptotic behavior of it. Then we apply the Monte-Carlo method and propose a procedure of option pricing for the Bashelie sub-diffusion model. For this aim, we use iterative schemes for simulating N scenarios of stock prices for our models. Finally, we demonstrate numerical results.

Genetically Informed Regression Analysis: Application to Aggression Prediction by Inattention and Hyperactivity in Children and Adults

We present a procedure to simultaneously fit a genetic covariance structure model and a regression model to multivariate data from mono- and dizygotic twin pairs to test for the prediction of a dependent trait by multiple correlated predictors. We applied the model to aggressive behavior as an outcome trait and investigated the prediction of aggression from inattention (InA) and hyperactivity (HA) in two age groups. Predictions were examined in twins with an average age of 10 years (11,345 pairs), and in adult twins with an average age of 30 years (7433 pairs). All phenotypes were assessed by the same, but age-appropriate, instruments in children and adults. Because of the different genetic architecture of aggression, InA and HA, a model was fitted to these data that specified additive and non-additive genetic factors (A and D) plus common and unique environmental (C and E) influences. Given appropriate identifying constraints, this ADCE model is identified in trivariate data. We obtained different results for the prediction of aggression in children, where HA was the more important predictor, and in adults, where InA was the more important predictor. In children, about 36% of the total aggression variance was explained by the genetic and environmental components of HA and InA. Most of this was explained by the genetic components of HA and InA, i.e., 29.7%, with 22.6% due to the genetic component of HA. In adults, about 21% of the aggression variance was explained. Most was this was again explained by the genetic components of InA and HA (16.2%), with 8.6% due to the genetic component of InA.

Specification tests for covariance structures in high-dimensional statistical models

Summary We consider testing the covariance structure in statistical models. We focus on developing such tests when the random vectors of interest are not directly observable and have to be derived via estimated models. Additionally, the covariance specification may involve extra nuisance parameters which also need to be estimated. In a generic additive model setting, we develop and investigate test statistics based on the maximum discrepancy measure calculated from the residuals. To approximate the distributions of the test statistics under the null hypothesis, new multiplier bootstrap procedures with dedicated adjustments that incorporate the model and nuisance parameter estimation errors are proposed. Our theoretical development elucidates the impact due to the estimation errors with high-dimensional data and demonstrates the validity of our tests. Simulations and real data examples confirm our theory and demonstrate the performance of the proposed tests.

The Bayesian Covariance Structure Model for Testlets

Standard item response theory (IRT) models have been extended with testlet effects to account for the nesting of items; these are well known as (Bayesian) testlet models or random effect models for testlets. The testlet modeling framework has several disadvantages. A sufficient number of testlet items are needed to estimate testlet effects, and a sufficient number of individuals are needed to estimate testlet variance. The prior for the testlet variance parameter can only represent a positive association among testlet items. The inclusion of testlet parameters significantly increases the number of model parameters, which can lead to computational problems. To avoid these problems, a Bayesian covariance structure model (BCSM) for testlets is proposed, where standard IRT models are extended with a covariance structure model to account for dependences among testlet items. In the BCSM, the dependence among testlet items is modeled without using testlet effects. This approach does not imply any sample size restrictions and is very efficient in terms of the number of parameters needed to describe testlet dependences. The BCSM is compared to the well-known Bayesian random effects model for testlets using a simulation study. Specifically for testlets with a few items, a small number of test takers, or weak associations among testlet items, the BCSM shows more accurate estimation results than the random effects model.

Bayesian covariance structure modelling for measurement invariance testing

In a Bayesian Covariance Structure Model (BCSM) the dependence structure implied by random item parameters is modelled directly through the covariance structure. The corresponding measurement invariance assumption for an item is represented by an additional correlation in the item responses in a group. The BCSM for measurement invariance testing is defined for mixed response types, where the additional correlation is tested with the Bayes factor. It is shown that measurement invariance can be tested simultaneously across items and thresholds for multiple groups. This avoids the risk of capitalization on chance that occurs in multiple-step procedures and avoids cumbersome procedures where items are examined sequentially. The proposed measurement invariance procedure is applied to PISA data, where the advantages of the method are illustrated.

Differences between strawberry cultivars based on principal component analysis

Strawberry culture is of extreme economic importance, especially for small producers, as it has the capacity to add value to small family farms, in addition to absorbing family labor. Principal component analysis (PCA) is a multivariate technique for modeling covariance structure, where a basic idea is to find latent variables that represent linear combinations of a group of variables under study, which in turn are related between itself. In this way, the objective of the work was estimated, through the analysis of main components (PCA), as relationships between development variables, products and fruit quality in different strawberry cultivars. The design used was a randomized block with 11 treatments, consisting of strawberry cultivars of Italian and American origins, with four replications. During the culture cycle, the following variables were evaluated: phyllochron, number of commercial (FC) and non-commercial (FNC) fruits, mass of commercial (MFC) and non-commercial (MFNC) fruits, total titratable acidity (AT), total soluble quantities (SST) and total soluble ratio, titratable acidity (SST / AT). The relationships between the variables were evaluated by the PCA analysis and the results were plotted on the Biplot graph. From the analysis, it was possible to identify the relationships between the variables that show how to cultivate the same photoperiod and the same characteristic origin. Growing short photoperiods are more productive, for example, as the neutral photoperiod has less phyllochron and less acidity. The increase in soluble solids can cause a reduction in acidity, which is one of the characteristics that add flavor to the fruit.

Ratio F test for testing simultaneous hypotheses in models with blocked compound symmetric covariance structure

This article deals with testing simultaneous hypotheses about the mean structure and the covariance structure in models with blocked compound symmetric (BCS) covariance structure. Considered models are used for double multivariate data, which means that m-variate vector of observation is measured repeatedly over u levels of some factor on each of n individual. Additionally, the assumption of multivariate normality for this type of data is made. We use framework of ratio of positive and negative parts of best unbiased estimators to obtain simultaneous F test. The test statistic is constructed as a ratio of test statistics for testing single hypotheses about the mean vector and the covariance matrix. In simulation study power of obtained test is compared with powers of three other F tests—two for testing single hypotheses and one for testing simultaneous hypotheses, whose test statistic is convex combination of test statistics of these two single F tests. The problem of simultaneous testing of the mean vector and covariance matrix was also consider in paper (Hyodo and Nishiyama, Commun Stat Theory Methods, https://doi.org/10.1080/03610926.2019.1639751, 2019).

Effects of Family-Centered Media Literacy Training on Family Nutrition Outcomes

Parents frustrated about food marketing influences need media management skills to challenge marketing messages and interpret factual content. We tested a media literacy-based, family-centered intervention to reduce effects of appealing, but unrealistic, food marketing. We hypothesized that participation would facilitate family discussion that improves the home dietary environment and increases youth consumption of fruits and vegetables. Parent-child (age 9-14) dyads (N = 189) participated in a matched-group, pretest/posttest field experiment testing a 6-week media literacy-based curriculum. Hypothesis testing employed multiple analysis of covariance and Bayesian multigroup structural equation modeling (MGSEM). Improved nutrition outcomes for parents included talk with youth about food nutrition labels (d = 0.343) and ratio of healthy to unhealthy food in home (d = 0.232); youth improved talk with parent about food nutrition labels (d = 0.211), vegetables eaten yesterday (d = 0.264), and fruit eaten yesterday (d = 1.386). Bayesian MGSEM revealed that in the intervention group, 12 of 17 tested paths were significant (p < .05), compared with only 4 in the control group, with average effect size magnitudes of 0.236 and 0.113, respectively. Media literacy education can empower parents and improve youths' critical thinking to reduce negative effects of food marketing on families and improve use of media to obtain nutrition information that aids dietary choices. This approach reduces the risk for reactance from youth who like media and resist limiting media use, while helping families use media together to make better nutrition decisions.

Inferring trait-specific similarity among individuals from molecular markers and phenotypes with Bayesian regression

Modeling covariance structure based on genetic similarity between pairs of relatives plays an important role in evolutionary, quantitative and statistical genetics. Historically, genetic similarity between individuals has been quantified from pedigrees via the probability that randomly chosen homologous alleles between individuals are identical by descent (IBD). At present, however, many genetic analyses rely on molecular markers, with realized measures of genomic similarity replacing IBD-based expected similarities. Animal and plant breeders, for example, now employ marker-based genomic relationship matrices between individuals in prediction models and in estimation of genome-based heritability coefficients. Phenotypes convey information about genetic similarity as well. For instance, if phenotypic values are at least partially the result of the action of quantitative trait loci, one would expect the former to inform about the latter, as in genome-wide association studies. Statistically, a non-trivial conditional distribution of unknown genetic similarities, given phenotypes, is to be expected. A Bayesian formalism is presented here that applies to whole-genome regression methods where some genetic similarity matrix, e.g., a genomic relationship matrix, can be defined. Our Bayesian approach, based on phenotypes and markers, converts prior (markers only) expected similarity into trait-specific posterior similarity. A simulation illustrates situations under which effective Bayesian learning from phenotypes occurs. Pinus and wheat data sets were used to demonstrate applicability of the concept in practice. The methodology applies to a wide class of Bayesian linear regression models, it extends to the multiple-trait domain, and can also be used to develop phenotype-guided similarity kernels in prediction problems.

The moderating role of SES on genetic differences in educational achievement in the Netherlands

Parental socioeconomic status (SES) is a strong predictor of children’s educational achievement (EA), with an increasing effect throughout development. Inequality in educational outcomes between children from different SES backgrounds exists in all Western countries. It has been proposed that a cause of this inequality lies in the interplay between genetic effects and SES on EA, which might depend on society and the equality of the education system. This study adopted two approaches, a classical twin design and polygenic score (PGS) approach, to address the effect of parental SES on EA in a large sample of 12-year-old Dutch twin pairs (2479 MZ and 4450 DZ twin pairs with PGSs for educational attainment available in 2335 children) from the Netherlands Twin Register (NTR). The findings of this study indicated that average EA increased with increasing parental SES. The difference in EA between boys and girls became smaller in the higher SES groups. The classical twin design analyses based on genetic covariance structure modeling pointed to lower genetic, environmental, and thus phenotypic variation in EA at higher SES. Independent from a child’s PGS, parental SES predicted EA. However, the strength of the association between PGS and EA did not depend on parental SES. In a within-family design, the twin with a higher PGS scored higher on EA than the co-twin, demonstrating that the effect of the PGS on EA was at least partly independent from parental SES. To conclude, EA depended on SES both directly and indirectly, and SES moderated the additive genetic and environmental components of EA. Adding information from PGS, in addition to parental SES, improved the prediction of children’s EA.