Latent Growth Curve Modeling

Dewaele and MacIntyre. [2016. ‘Foreign language enjoyment and foreign language classroom anxiety: The right and left feet of the language learner.’ In Positive psychology in SLA, edited by T. Gregersen, P. D. MacIntyre, and S. Mercer, 215–236. Bristol: Multilingual Matters] asserted that foreign language classroom anxiety (FLCA) and foreign language enjoyment (FLE) are the learners’ metaphorical left and right feet on their journey to acquiring the foreign language. The purpose of this longitudinal study was to investigate the growth as well as changing trends of university students’ FLE and FLCA in a course of general English using latent growth curve modeling (LGCM) as well as a triangulation of data collection. To do this, we analyzed data collected from 367 undergraduate students during a semester in a course of general English in the LGCM phase and four participants in the qualitative phase. The findings indicated that while the participants’ FLE increased significantly, their level of FLCA decreased during the semester. However, the significance of the intercept and slope variances for both variables implied heterogeneity in the participants’ growth in FLE and FLCA over the semester. In addition, the initial levels of both FLE and FLCA could not predict their growth during the semester. Furthermore, at the beginning of the semester, the significant negative correlation between students’ FLE and FLCA was low but during the semester the negative correlation between the two variables turned out to be high; however, the qualitative findings indicated moments of experiencing high levels of FLE and FLCA and moments of going through low levels of FLE and FLCA at the same time by the learners. The pedagogical implications of the findings are discussed.

This article presents a combined motivational and volitional intervention based on the theory of planned behavior aimed at promoting expansion-oriented job crafting behaviors. Participants were employees working in different companies, assigned to either an intervention (n = 53) or a control group (n = 55). Results of a field study (including premeasure, postmeasure, and weekly diaries) indicated that the intervention enhanced participants’ perceptions of behavioral control referred to job crafting and awareness regarding others’ engagement in job crafting. Latent change growth modeling showed that participation in the intervention led to participants shaping their job crafting intentions during the weeks, which translated into more frequent job crafting behaviors at the end of the study period. Besides, the intervention served to trigger weekly work-related flow experiences in terms of high absorption while working. Findings suggest that job crafting interventions can benefit from the inclusion of self-regulatory strategies complementing goal setting.

Purpose: This project examines the relationship between police enforcement of driving under the influence (DUI) and fatal alcohol related crashes.

Method: This article merged data from several sources to fit several 3-level growth curve models that assess the relationship between DUI arrests and fatal alcohol related crashes in U.S. counties from 1985-2015.

Results: The findings indicate that increases in DUI arrests are related to decreased fatal alcohol related crashes during the period. However, the two are not linearly related and the relationship varies across states.

Conclusions: The non-linearity indicates there is a point of diminished returns where increased arrests are no longer related to reductions in fatalities. These findings suggest that policy makers should explore alternative methods of reducing crashes to supplement enforcement efforts such as addressing problems of alcoholism and traffic safety.

La teoria classica è stata condizionata dal pensiero di Pitagora, che proponeva l’associazione di 7 colori alle note musicali e quindi dell’armonia del colore alla sinfonia del moto dei pianeti, influenzando Platone ed Aristotele. Nel medioevo Alberto Magno (1206-1280) osservò che nel bianco sono contenuti tutti i colori, per i quali riconosceva tre mescolanze possibili: quella reale della miscelazione dei pigmenti, usata dai pittori, quella dei mezzi trasparenti legata alla natura della luce, quella visiva che deriva dalla mescolanza di piccole macchie di colore diverso.
Il modello di Aristotele sopravvive nell’interpretazione che ne dà Leonardo omettendo il viola, e trova nuova vitalità, quando il fisico belga Aguilonius  che studia la mescolanza dei colori per Rubens, introduce il concetto di colori semplici e compositi con un nuovo allineamento di cinque colori fondamentali (bianco, giallo, rosso, blu, nero) dai quali derivano per mescolanza i tre colori secondari (arancio, verde e porpora). S. Forsius disegnò un cerchio cromatico di 16 colori e la prima sfera cromatica, che prevedeva 3 copie di complementari agli opposti dei tre diametri ortogonali: bianco/nero sull’asse polare, giallo/verde e rosso/blu sul piano equatoriale . Intorno al 1630 l’alchimista inglese Robert Fludd richiuse invece la linea dei colori aristotelica congiungendo il bianco e il nero in un cerchio di 7 colori (nero, blu, verde, rosso, ocra, giallo, bianco) ordinati secondo la loro luminosità, nel quale la posizione di equilibrio tra luce ed ombra è espressa dal verde e dal rosso. Come è noto, Newton si occupa del colore come effetto dell’assorbimento differenziato delle lunghezze d’onda della luce bianca e sottolinea le analogie con la propagazione del suono; nello spettro individua 7 colori come gli intervalli dell’ottava musicale di Pitagora. I due colori estremi della gamma sono accostabili in un’organizzazione circolare solo con un’astrazione, che sottolinea la gradualità della mescolanza tra due colori senza che vi sia alcuna continuità spettrale.
Nessuno di questi modelli presenta finalità che vadano oltre la volontà di rappresentare la continuità della variazione dei colori per dare un ordine visibile al fenomeno. Nel 1766 l’inglese Moses Harris individua la terna di colori primari (giallo, rosso e blu) e i tre secondari composti in una costruzione radiale divisa in 18 colori, dalla quale sviluppa un sistema di 360 toni. Harris, interessato alla produzione materiale dei colori, disegna due ruote basate rispettivamente sui colori prismatici e sulla miscelazione dei pigmenti, visualizzando la sintesi sottrattiva che produce il nero con la sovrapposizione di tre triangoli equilateri. Il chimico dirigeva le manifatture di Gobelin ed era responsabile del controllo della tintura dei tessuti. Il primo (1846) individua i colori composti dalla sovrapposizione di 6 cerchi coi primari e secondari, all’interno di una bussola graduata che scandisce la parte dei colori caldi e quella dei colori freddi. I medesimi primari (con il violetto al posto del blu) caratterizzano la figura circolare del pittore canadese M. Jacobs, nella quale le sovrapposizioni di archi di circonferenza definiscono i complementari (blu, giallo, cremisi) e 6 colori miscelati.

Bibliografia

  François d’Aguilon, Opticorum libri sex, 1613.
  N. Silvestrini, E. P. Fisher, www.colorsystem.com
  J.W. von Goethe, Zur Farbenlehre, 1810, trad.it a cura di R. Troncon, Milano, 1981.
  P. O. Runge, Die Farbenkügel, Zurich, 1810. I  François d’Aguilon, Opticorum libri sex, 1613.
  Athanasius Kircher, Ars magna lucis et umbrae, 1646. Il gesuita, che si occupò tra l’altro dello studio degli specchi e dell’anamorfosi è l’inventore della lanterna magica.
  L. Wittgenstein, Bemerkungen über die Farben, Frankfurt, 1979.
  R. G. Kuehni, Color. An introduction to practice and systems, Wiley-Interscience, 2004, pag. 136

The aim of the current article is to provide a brief introduction to Bayesian statistics within the field of health psychology. Bayesian methods are increasing in prevalence in applied fields, and they have been shown in simulation research to improve the estimation accuracy of structural equation models, latent growth curve (and mixture) models, and hierarchical linear models. Likewise, Bayesian methods can be used with small sample sizes since they do not rely on large sample theory. In this article, we discuss several important components of Bayesian statistics as they relate to health-based inquiries. We discuss the incorporation and impact of prior knowledge into the estimation process and the different components of the analysis that should be reported in an article. We present an example implementing Bayesian estimation in the context of blood pressure changes after participants experienced an acute stressor. We conclude with final thoughts on the implementation of Bayesian statistics in health psychology, including suggestions for reviewing Bayesian manuscripts and grant proposals. We have also included an extensive amount of online supplementary material to complement the content presented here, including Bayesian examples using many different software programmes and an extensive sensitivity analysis examining the impact of priors.

Paper aims to conceptually, graphically and mathematically present principles of latent growth modeling (LGM). Model is
presented as a part of more general approach of structural equation modeling (SEM). Application of LGM is presented through examples of result structures. Extensions and limitations of basic model are thoroughly discussed. Review also gives information about previous study results in which latent factors are used for data modeling, since it is presumed that latent factors are base for both general and specific developmental trajectories.

This study investigated the desensitization to violence over a short period of time. Participants watched nine violent movie scenes and nine comedy scenes, and reported whether they enjoyed the violent or comedy scenes and whether they felt sympathetic toward the victim of violence. Using latent growth modeling, analyses were carried out to investigate how participants responded to the different scenes across time. The findings of this study suggested that repeated exposure to media violence reduces the psychological impact of media violence in the short term, therefore desensitizing viewers to media violence. As a result, viewers tended to feel less sympathetic toward the victims of violence and actually enjoy more the violence portrayed in the media. Additionally, desensitization to media violence was better represented by a curvilinear pattern, whereas desensitization to comedy scenes was better represented by a linear pattern. Finally, trait aggression was not related to the pattern of change over time, although significant effects were found for initial reports of enjoyment and sympathy. Aggr. Behav. 35:179–187, 2009. © 2009 Wiley-Liss, Inc.

Most research regarding the timing of first sex with a new romantic partner finds that delaying the onset of sex is associated with greater relationship satisfaction and stability. Although some studies suggest that this association can be explained by selection effects or mediating variables, all of these studies have relied on retrospective reports of the timing of sex, and most studies were based on cross-sectional data. Therefore, the current study used inertia theory and sexual scripting theory to investigate the direct, selection, and indirect effects between the timing of first sex in a new relationship and four relationship outcomes: relationship satisfaction, sexual satisfaction, perceived relationship stability, and actual relationship stability, using a five-wave longitudinal study spanning three months. Individuals in premarital relationships, who had not yet had sex with their current partner, were recruited to participate in this longitudinal study. Several indicators of the timing of first sex were entered into a latent class analysis to generate homogenous sex-timing groups. Latent growth curve modeling was used to test whether membership in sex-timing groups predicted relationship outcomes and whether associations were explained by selection effects or mediation. There was little support that the timing of sex was associated with changes in relationship satisfaction or commitment. However, there was some evidence that having had sex with one’s partner early in the relationship increased feelings of passionate love, which was associated with increases in relationship satisfaction. Findings are discussed in light of theory and prior research, and directions for future research are provided.

The cross-classified multiple membership latent variable regression (CCMM-LVR) model is a recent extension to the three-level latent variable regression (HM3-LVR) model which can be utilized for longitudinal data that contains individuals who changed clusters over time (for instance, student mobility across schools). The HM3-LVR model can include the initial status on growth effect as varying across those clusters and allows testing of more flexible hypotheses about the influence of initial status on growth and of factors that might impact that relationship, but only in the presence of pure clustering of participants within higher-level units. This Monte Carlo study was conducted to evaluate model estimation under a variety of conditions and to measure the impact of ignoring cross-classified data when estimating the incorrectly specified HM3-LVR model in a scenario in which true values for parameters are known. Furthermore, results from a real-data analysis were used to inform the design of the simulation. Overall, it would be recommended for researchers to utilize the CCMM-LVR model over the HM3-LVR model when individuals are cross-classified, and to use a bare minimum of more than 100 clustering units in order to avoid overestimation of the level-3 variance component estimates.

We investigated the utility of a dynamic approach to risk factors for early to middle childhood maternal corporal punishment. Archival data from Fragile Families and Child Wellbeing Study mothers (N = 4,364) were used to model the associations of several risk factors (maternal depression, maternal substance use, parental burden, child negative affect, and intimate partner violence victimization), repeatedly measured at child ages 1 and 3, with both the age 3 level of and age 3-9 linear change in corporal punishment. Unlike most previous research, we distinguished between two types of variation in risk factors, reflecting occasion specific fluctuations as well as their absolute levels. We concentrate herein on the potential role of occasion specific variation in the above risk factors at age 3 – variability that is not a carryover effect from a risk factor’s past level. Mothers who reported perturbations of (i.e., occasion specific variation in) depression, substance use, parenting stress, and child negative affect between ages 1 and 3 reported higher age 3 corporal punishment. Yet age 3 to 9 change in corporal punishment was not successfully predicted. The results underscore the importance of considering occasion specific fluctuations in risk factors, alongside their absolute levels, in the development and prevention of corporal punishment.

In this study we explored changes in motivation and engagement factors through the self-system, attribution, and self-efficacy theories. We analyzed how change in locus of control and self-belief related to change in disengagement and how change in all three influenced high school grade point average and attendance in a sample of students from the Pacific Northwest in the U.S. during grades 8–10. Our results revealed a cycle where lower self-belief influenced an increase in disengagement, increased disengagement influenced heightened uncertain control, and heightened uncertain control further stunted self-belief. Results suggest that disengagement alone may not lead to a negative orientation to school, and that schools should develop self-belief for each student during the high school transition years.

Social dominance orientation (SDO) has been theorized as a stable, early-emerging trait influencing outgroup evaluations, a view supported by evidence from cross-sectional and two-wave longitudinal research. Yet the limitations of identifying causal paths with cross-sectional and two-wave designs are increasingly being acknowledged. This paper presents the first use of multi-wave data to test the over-time relationship between SDO and outgroup affect among young people. We use cross-lagged and latent growth modeling of a three-wave dataset employing Norwegian adolescents (over 2 years, N = 453) and a five-wave dataset with American university students (over 4 years, N = 748). Overall, SDO exhibits high temporal rank-order stability and predicts changes in outgroup affect. This research represents the strongest test to date of SDO’s role as a stable trait that influences the development of prejudice, while highlighting latent growth modeling as a valuable tool for social and political psychology.

Objectives. To assess the impact of a mental simulation intervention designed to reduce student alcohol consumption by asking participants to imagine potential positive outcomes of and/or strategic processes involved in not drinking during social occasions. Design. English university students aged 18-25 years (n = 211, M.Age = 20 years) were randomly allocated to one of four intervention conditions. The dependent variables were weekly alcohol consumption, heavy episodic drinking (HED) and frequency of social occasions at which participants did not drink alcohol when others were drinking alcohol ('episodic non-drinking'). Measures of alcohol-related prototypes (i.e., prototypical non-drinker, prototypical regular drinker) were used to compute sociability prototype difference scores as a potential mediator of any intervention effects. All measures were taken at baseline and at two- and four-week follow-up. Methods. Participants completed one of four exercises involving either: imagining positive outcomes of non-drinking during a social occasion (outcome condition); imagining strategies required for non-drinking during a social occasion (process condition); imagining both positive outcomes and required strategies (combined condition); or completing a drinks diary task (control condition). Results. Latent growth curve analyses revealed a more substantial rate of decrease in weekly unit consumption and HED frequency among outcome condition and process condition participants, relative to control condition participants. Non-significant differences were found between the combined condition and the control condition. Across the whole sample, an inverted U-shape trend indicated an initial increase in episodic non-drinking before it returned to baseline levels. Conclusion. This study provides preliminary evidence that mental simulation interventions focused on non-drinking can successfully promote behaviour change.

Background: Elevated blood pressure in childhood is a risk factor for adult hypertension which is a global health problem. Excess adiposity in childhood creates a predisposition to develop adult hypertension. Our aim was to explore distinct sex-specific adiposity trajectories from childhood to late adolescence and examined their association with blood pressure.

Theories of threat appeals have been rightly concerned with the form of the  relationship between fear and persuasion: Linear or curvilinear. They have not, however, clearly distinguished the question as a between- or within-persons phenomenon. In fact, the literature often treats these two perspectives as if they were interchangeable. We show that between- versus within-person questions about functional form are distinct from one another. Previous research, which is the product of between-persons designs, shows a linear relationship between fear and persuasion. Between-persons studies cannot address the question of how changes in fear over time produce persuasion. Consequently, a major piece of the fear appeals-persuasion puzzle may have been overlooked. Reanalysis of an existing data set shows curvilinearity of fear in within-persons data and demonstrates that the curve predicts persuasion. Audience segmentation reveals different curves for different groups as well as differential associations between those curves and persuasion. Overall, the argument and the empirical results suggest that a great deal less is known about fear appeals than it is currently believed.

The Rosenberg Self-Esteem Scale is the most utilized measure of global self-esteem. Although psychometric studies have generally supported the uni-dimensionality of this 10-item scale, more recently, a stable, response-bias has been associated with the wording of the items (Marsh, Scalas, & Nagengast, 2010). The purpose of this report was to replicate Marsh et al.’s findings in a sample of older adults and to test for invariance across time, gender and levels of education. Our results indicated that indeed a response-bias does exist in esteem responses. Researchers should investigate ways to meaningfully examine and practically overcome the methodological challenges associated with the RSE scale.

Western Europe has recently experienced the emergence of successful new parties, but while single parties or countries have been extensively studied, insufficient attention has been devoted to this phenomenon from a comparative and long-term perspective. By relying on an original data set covering 20 countries and 344 parliamentary elections, this article presents the first analysis of West European 'genuinely new parties' (GNPs) across time, countries and party families. We hypothesize that the parties differ not only in terms of their short-and long-term success but have a range of distinct development paths. Through a latent growth model, we provide a classification of GNPs in terms of their breakthrough and initial performance. According to the specific trajectory followed by new parties in the first five elections they contest, the model suggests five different classes of new parties in Western Europe: 'explosive', 'meteoric', 'contender', 'f...

Background: Variation in the relationship between education and health has been studied intensely over the past few decades. Although there is research on gender disparity and cohort variations in educational effect on health using samples from the U.S. and Europe, research about China’s is limited. Given the specific social changes in China, our study is designed to analyze the gender and cohort patterns in the education-health gradient.
Method: The latent growth-curve modeling was used to analyze the gender and cohort variations in the education gradient in self-rated health among Chinese respondents. The study employed longitudinal and nationally representative data from the Chinese Family Panel Studies from the years 2010 to 2016. Each cohort is specified according to their distinct periods of social change in China. Following the analysis, we used latent growth-curve model to illustrate gender and cohort differences in the age-graded education and health trajectories.
Results: Although Chinese men have reported to have better health than women in general, women reported 1.6 percentage points higher in self-reported health for each additional year of schooling compared to that of men
(P < 0.001). The latent growth curve model showed women’s extra education benefits were persistent overtime. Compared to the people born during the “Old China” (1908–1938), the education gradient in self-rated health did not change for cohorts born before 1955 and after 1977, but the education-health gap changed significantly in the 1956–1960 (O.R. = 1.038, P < 0.05), 1967–1976 (O.R. = 1.058, P < 0.001), and 1977–1983 (O.R. = 1.063, P < 0.001) cohorts. There was a gender difference for the cohort variations in the education-health gradient. For women, the education effect in the 1956–1960 (O.R. = 1.063, P < 0.05), 1967–1976 (O.R. = 1.088, P < 0.001) and 1977–1983 (O.R. = 1.102, P < 0.001) cohorts was significantly higher than that of the 1908–1938 cohort. On the contrary, the education- health gradient remained the same across all cohorts for men.
Conclusion: Our study suggests that the education-health gradient varies across cohorts for women, but the size of education effect remains consistent for men across cohorts. The findings support the resource-substitution hypothesis and not the rising-importance hypothesis in China. We discussed the potential influences of the unique, social transformation and educational expansion in China.

Increasing evidence has indicated that people might be differentially influenced by intervention programs. The purpose of this secondary analysis was to identify groups of women who responded differently to a walking intervention. Data used in this secondary analysis were collected in a longitudinal study of a counseling intervention to increase walking among 248 initially sedentary women. A latent growth-mixture modeling approach was used to assess treatment effects on growth in physical activity and mood over time. Subgroups of participants who were responsive versus those who were nonresponsive to intervention were also identified. Logistic-regression analysis was conducted to confirm group membership and identify predictors associated with the identified subgroups. Two subgroups (responders, nonresponders) were identified separately for physical activity and mood. Using several variables as predictors of group memberships, 92%-95% of the cases were correctly classified. The curr...

This study evaluated the adolescent tobacco-use trajectories that predict nicotine dependence in early adulthood and when these trajectories start to diverge. As part of a follow-up to a large prevention trial, the present study evaluated 1,017 individuals from early adolescence (age 12) to early adulthood (age 28). Participants were recruited from eight middle schools in Kansas City, Missouri. Students were entering 6th grade or 7th grade at baseline. Smoking was evaluated at baseline, 6 months, at annual follow-ups through high school, and every 18 months thereafter until age 28. The study goals were to determine (a) whether distinct weekly tobacco-use trajectories could be identified between early adolescence and emerging adulthood (ages 12-24); (b) when during development these trajectories diverged; and (c) which trajectories could predict nicotine dependence in early adulthood (ages 26-28). A four-trajectory mixed model (abstainers, low users, late stable users, and early stab...

ABSTRACT This chapter presents Infosys’ approach to leader development that includes the practical benefits of psychometric and statistical methods commonly used by other disciplines, such as Rasch measurement and latent growth modeling. Infosys is beginning to use these with other individualized leader development practices such as coaching, intervention bundling, and evaluation. When combined, these elements have the potential to personalize developmental processes to each leader and improve microlevel leadership theory with the overarching purpose of enhancing global leadership at Infosys and promoting the science of individual leader development.

We illustrate the use of the parallel latent growth curve model using data from OCTO-Twin. We found a significant intercept-intercept and slope-slope association between processing speed and visuospatial ability. Within-person correlations among the occasion-specific residuals were significant, suggesting that the occasion-specific fluctuations around individual’s trajectories, after controlling for intraindividual change, are related between both outcomes. Random and fixed effects for visuospatial ability are reduced when we include structural parameters (directional growth curve model) providing information about changes in visuospatial abilities after controlling for processing speed. We recommend this model to researchers interested in the analysis of multivariate longitudinal change, as it permits decomposition and directly interpretable estimates of association among initial levels, rates of change, and occasion-specific variation.

Background Many young people in Korea today experience deprivation in various areas of life. The social determinants of health approach maintains that social factors play an important role in an individual’s physical and mental health. This study aimed to investigate the problem drinking trajectory of young Korean people and identify the effects of multidimensional deprivation on problem drinking. Methods The study used data from 2012 to 2018 found in the Korea Welfare Panel Study. Latent class growth analysis was performed to determine the number of trajectories of problem drinking. After identifying latent classes, a multinomial logistic regression analysis was utilized to examine multidimensional deprivation as a predictor of class membership. Results Latent class analysis yielded three groups: (1) a low-level maintenance group (low level of alcohol use maintained at the low level), (2) a moderate-level increasing group (moderate level of problem drinking with a moderate increase...