Latent Class Factor Research Articles

Cross sectional analysis of the effect of alcohol on pulmonary function in a cohort of men and women living with HIV.

People living with HIV (PLWH) are at increased risk for noncommunicable diseases such as lung disease in part due to opportunistic infections including pneumonia. HIV infection is associated with increased prevalence of impaired lung function and abnormal gas exchange. Alcohol use disorder (AUD) is exceedingly common in PLWH and is associated with higher risk of pneumonia in PLWH. Alcohol use may lead to lung damage through several mechanisms. Data on the long-term effect of AUD on pulmonary function in PLWH are sparse and conflicting. To evaluate this relationship, we conducted a cross-sectional analysis of adult PLWH in care in Louisiana. We hypothesized that chronic alcohol use would be associated with subsequent pulmonary dysfunction in a dose-dependent fashion. All participants performed standardized spirometry on study entry. In total, 350 participants with acceptable spirometry were included in this analysis. Thirty-one percent of participants were female. Women reported less lifetime alcohol use and less smoking; however, they reported more chronic respiratory symptoms. In adjusted models, total lifetime alcohol use was not associated with spirometry measures of pulmonary function. HIV-related variables (CD4 count and viral load) were also not associated with measures of pulmonary function. We then conducted sex-stratified analyses to eliminate residual confounding of sex and similarly found no association of total lifetime alcohol use and pulmonary function. We found no association of AUDIT score or early life alcohol use and pulmonary function. In latent class factor analysis, current heavy alcohol use was associated with lower measures of pulmonary function as compared to former heavy alcohol use. In summary, in this cohort of New Orleanian men and women living with HIV with robust measures of alcohol use, though total lifetime alcohol use and early life alcohol use were not associated with pulmonary function, current heavy alcohol use was associated with impaired pulmonary function.

Exploring the Dimensions of Movement-Specific Reinvestment From Personal Characteristics Perspectives.

The purposes of the present study were three-fold: to examine (a) if the movement-specific reinvestment responses should be represented as two dimensional constructs, (b) whether dichotomization of the movement-specific reinvestment responses are appropriate, and (c) how the two dimensions are associated with relevant psychological concepts. To conduct a comparative examination of the MSRS structure in two Asian samples, participants were 236 Japanese university students (136 men, 100 women; Mage = 18.0, SD = 1.6) and 328 Singaporeans (167 men, 161 women; Mage = 21.8, SD = 1.8). After examining the factor structure of the movement-specific reinvestment responses for the first purpose, latent class factor analysis was conducted for both samples for the second purpose. For the third purpose, correlation analysis and mediation analysis were conducted for a part of the Singaporean sample. Through a series of latent class factor analysis, four and three classes were identified for the Japanese and Singaporean samples, respectively. For both samples, the patterns of the item-average scores for the two movement-specific reinvestment dimensions were parallel among the classes. Conscious Motor Processing was positively associated with mental toughness, intrinsic regulation, integrated regulation, mastery-approach and task goal orientations, and dispositional flow, whereas Movement Self-Consciousness was positively related with stress and mastery-avoidance goal orientation. The findings of the study supported (a) the two-dimensional representation of the movement-specific reinvestment responses, but did not fully support (b) the practice of dichotomization of the movement-specific reinvestment responses, and indicated that (c) at the trait level, Conscious Motor Processing and Movement Self-Consciousness were associated with positive and negative psychological constructs, respectively.

The Alcohol Use Disorders Identification Test (AUDIT) in Adolescents: Using a Model-Based Approach to Identify Patterns of Alcohol Misuse

Objective To explore the latent structure of the Alcohol Use Disorders Identification Test (AUDIT) among adolescents of different school grades (age strata). Methods: Data derived from two simultaneous run cohort studies from the “Adolescent Nutritional Assessment Longitudinal Study-ELANA” conducted in private and public schools of Rio de Janeiro/Brazil. Participants comprised 564 seventh-graders and 419 ninth-graders, respectively sampled in 2011 and 2013 from cohort 1, and 730 eleventh-graders sampled in 2011 from cohort 2. Latent class factor analytical (LCFA) models were applied to the AUDIT items to identify internally homogeneous latent groups of individuals representing distinct patterns of alcohol use, and optimal group-separating cutoffs. The classification agreement was also evaluated. Results: Three and two groups (classes) were found for the eleventh and the earlier grades, respectively. These best-fitting models held a very high degree of class separation (entropy >0.9). By contrasting the AUDIT’s raw scores (0–10) with the model-based latent classes, the cutoff separating the base (milder) category was found between scores 0 and 1 in all grades. The eleventh-graders differed from the others by showing a third and more intense category of alcohol use (cutoff between 4 and 5). The classification agreement was almost perfect in eleventh-graders (98.6%) and perfect in the earlier grades (100%). Conclusions: Findings show that the AUDIT may be adequately used in adolescents of different ages and school grades, although the number of homogeneous categories may differ accordingly. Besides, raw scores may be pragmatically used to identify groups with confidence by applying specific optimal cutoffs.

Chronic stress exposure in men and women, and implications for the course of fatigue after percutaneous coronary intervention; the THORESCI study

BackgroundFatigue is a prevalent symptom in patients with coronary heart disease (CHD). Individual differences in chronic stress may affect the experience and persistence of fatigue, and this may vary between the sexes. Therefore, we studied the effect of chronic stress on the course of fatigue over a 2-year period after percutaneous coronary intervention (PCI), and examined the moderating effects of sex. Methods1682 patients (78% men, age = 67.1 ± 10.6) were recruited and filled out multiple self-report questionnaires at baseline, one, 12, and 24 months post-PCI, including questions on demographics, fatigue (HCS). Multiple chronic stressors were assessed at baseline: work stress (ERI16), marital stress (MMQ-6), early life events (Life Events Questionnaire) and social stress. Latent class factor analysis (LatentGOLD) was used to construct a comprehensive chronic stress index. Linear mixed modeling examined the predictive quality of predictors and covariates. ResultsFatigue was found to substantially decrease over the first month post-PCI, then stabilized at a moderate level. Chronic stress impacted both the level and course of fatigue by increasing its level and delaying recovery. Overall and across time, women reported more fatigue than men. The level and course effects of chronic stress and sex were independent of demographic, health behavioral, and medical covariates. ConclusionsIndividual differences in chronic stress impact both the level and course of fatigue post-PCI, with women being affected most. Future research could further explain the mechanisms underlying the observed relationships. Developing and testing interventions focusing on exercise and stress-reduction could be used to alleviate fatigue.

Heterogeneity of borderline personality disorder symptoms in help-seeking adolescents

BackgroundThe heterogeneous presentation of borderline personality disorder (BPD) represents a clinical challenge. There is an ongoing scientific debate whether the heterogeneity can best be understood in terms of qualitative (categorical) or quantitative (dimensional) differences between individuals. The present study examined the latent structure of BPD in adolescents.MethodsFive-hundred and six outpatients aged 12 to 17 years with risk-taking and/or self-harming behavior were assessed at baseline and one-year follow-up. Latent class analysis (corresponding with the categorical approach), factor analysis (corresponding with the dimensional approach), and factor mixture models (allowing for both categorical and dimensional aspects) were applied to the DSM-IV BPD criteria.ResultsThe best fitting model distinguished between a majority class with high probabilities for all BPD criteria (“borderline group”) and a minority class with high probabilities for the impulsivity and anger criteria only (“impulsive group”). Sex significantly affected latent class membership, and both a latent factor and age explained within-class variability. The borderline group primarily consisted of females, frequently reported adverse childhood experiences, scored high on the emotion dysregulation and inhibitedness personality traits, and was associated with internalizing psychopathology. In contrast, the impulsive group primarily consisted of males, scored high on the dissocial behavior personality trait, and was associated with externalizing psychopathology. After one year, the two groups showed similar clinical improvement.ConclusionsThe study provides evidence for two distinct subgroups of adolescents with BPD features that resemble the subtypes of the ICD-10 emotionally unstable personality disorder. More research is needed to further investigate the diagnostic stability of the two groups over time and potential differential treatment indications.

Welfare solidarities in the age of mass migration: evidence from European Social Survey 2016

Welfare opinion research has traditionally viewed migration as a potential hazard for welfare solidarity. In this article, we argue that while increased presence of foreigners can indeed make some people less supportive of public welfare provision in general or trigger opposition to migrants’ social rights, the link between migration and solidarity is not universally a negative one. Instead, many people can combine support for migration with high preferences for comprehensive social protection; others can endorse migration while they are not particularly supportive of an all-encompassing welfare state. Based on this line of reasoning we construct a taxonomy of four ideal types of welfare solidarity that are present in contemporary European welfare states. To illustrate the usefulness of this heuristic tool, we apply Latent Class Factor Analysis to European Social Survey round 8 data. We find that the majority of Europeans (56%) combine strong support for both migration and the welfare state (extended solidarity). However, exclusive solidarity is also widely spread as over a quarter of respondents (28%) oppose migration while expressing strong support for the welfare state. People who oppose migration and have relatively low preference for the welfare state (diminished solidarity) represent a small minority (5%). A little more than a tenth (11%) of Europeans endorse migration, but express relatively low support for the welfare state, which we assume to be a reflection of cosmopolitan solidarity. Despite considerable variation in the incidence of the four solidarities across countries, the preference structure is the same for all. Further, we find that at the individual level, the propensity to hold one of these types of solidarities is influenced by social trust, citizenship and country of birth, financial situation, education, and residence type. However, the extent of migration and social spending do not appear to be related with the propensity of holding either type of solidarity as the liberal’s dilemma and the welfare chauvinism theories would predict.

Investigating Measurement Invariance of Ankara University Foreign Students Selection Test According to Latent Class and Rasch Model

This study aimed to investigate the factor structure of the Basic Learning Skills Test included in the Ankara University Examination for Foreign Students and determine whether this test has measurement invariance and whether the items of the test shows differential item functioning according to the country and gender. Of the descriptive research models, screening was used in the design of the study. The population of the study consisted of 2134 individuals. Since the research involved intercultural comparisons, culture was taken into consideration in the selection of the sample. Accordingly, 1110 individuals from Germany, Azerbaijan and Iran constituted the sample. In the research, the first 60 items of the Basic Learning Skills Test concerning letters, numbers and figures were utilized. Latent Class and Latent Class Factor Analyses were employed to determine the factor structure of the test, and a Simultaneous Latent Class Analysis was undertaken to investigate the measurement invariance of the results according to country and gender. Besides, Recursive Partitioning Analysis based on Rasch Model was used to identify whether the items included in test show differential item functioning by country and gender. Before determining the factor structure of the Basic Learning Skills Test, an examination was conducted to ascertain whether the test as a whole fitted the scale structure, and which classes were included in the response patterns of the individuals taking the test. According to the results, the test had a latent model of four classes and a multiple-factor structure, comprising three factors of establishing part-to-whole relations, making inferences, and analytical thinking. Concerning the findings of analysis regarding the measurement invariance according to country and gender, it was found that the test had a homogeneous structure, and as a result, the structure measured by the test was equivalent across the groups compared. Studying whether the items in the test show differential item functioning according to country and gender, it was discovered that 14 items involve differential item functioning by country. Differential item functioning in regard to gender was not observed.

Suitability of the eight-item version of the Brazilian Household Food Insecurity Measurement Scale to identify risk groups: evidence from a nationwide representative sample.

The Brazilian Household Food Insecurity Measurement Scale (EBIA) has eight general/adult items applied in all households and six additional items exclusively asked in households with children and/or adolescents (HHCA). Continuing an investigation programme on the adequacy of model-based cut-off points for EBIA, the present study aims to: (i) explore the capacity of properly stratifying HHCA according to food insecurity (FI) severity level by applying only the eight 'generic' items; and (ii) compare it against the fourteen-item scale. Latent class factor analysis (LCFA) models were applied to the answers to the eight general/adult items to identify latent groups corresponding to FI levels and optimal group-separating cut-off points. Analyses involved a thorough classification agreement evaluation and were performed at the national level and by macro-regions. Data derived from the cross-sectional Brazilian National Household Sample Survey of 2013. A nationally representative sample of 116 543 households. In all households and investigated domains, LCFA detected four distinct household food (in)security groups (food security and three levels of severity of FI) and the same set of cut-off points (1/2, 4/5 and 6/7). Misclassification in the aggregate data was 0·66 % in adult-only households and 1·06 % in HHCA. Comparison of the scale reduced to eight items with the 'original' fourteen-item scale demonstrated consistency in the classification. In HHCA, the agreement between both classifications was 96·2 %. Results indicate the eight 'generic' items in HHCA can be reliably used when it is not possible to apply the fourteen-item scale.

Joint assessment of handedness and footedness through latent class factor analysis

ABSTRACTRecently, some studies have demonstrated the effectiveness of two latent variable approaches in which hand preferences are analysed using either latent class methods or latent class factor (LCF) methods. The main aims of this study are: (i) to establish whether these approaches are adequate for assessing footedness, (ii) to evaluate their appropriateness when hand and foot preferences are jointly analysed, and (iii) to measure the association between handedness and footedness based on the examined latent variable models. To this end, a dataset providing information about the limb used to perform ten hand actions and three foot movements by 2236 young Italian sportspeople is analysed. The first aim is pursued through an exploratory analysis of the observed foot preferences; according to this analysis, footedness patterns are adequately described by two latent levels of footedness. As far as the second aim is concerned, a confirmatory analysis of foot and hand preferences is carried out; the best fit to the dataset is obtained using a two-dimensional LCF model with four latent levels of handedness and two latent levels of footedness. Finally, the association between handedness and footedness resulting from the employed methods is remarkably lower than that registered in other studies.

Modeling Optimal Cutoffs for the Brazilian Household Food Insecurity Measurement Scale in a Nationwide Representative Sample

Background: This is the second part of a model-based approach to examine the suitability of the current cutoffs applied to the raw score of the Brazilian Household Food Insecurity Measurement Scale [Escala Brasileira de Insegurança Alimentar (EBIA)]. The approach allows identification of homogeneous groups who correspond to severity levels of food insecurity (FI) and, by extension, discriminant cutoffs able to accurately distinguish these groups.Objective: This study aims to examine whether the model-based approach for identifying optimal cutoffs first implemented in a local sample is replicated in a countrywide representative sample.Methods: Data were derived from the Brazilian National Household Sample Survey of 2013 (n = 116,543 households). Latent class factor analysis (LCFA) models from 2 to 5 classes were applied to the scale's items to identify the number of underlying FI latent classes. Next, identification of optimal cutoffs on the overall raw score was ascertained from these identified classes. Analyses were conducted in the aggregate data and by macroregions. Finally, model-based classifications (latent classes and groupings identified thereafter) were contrasted to the traditionally used classification.Results: LCFA identified 4 homogeneous groups with a very high degree of class separation (entropy = 0.934-0.975). The following cutoffs were identified in the aggregate data: between 1 and 2 (1/2), 5 and 6 (5/6), and 10 and 11 (10/11) in households with children and/or adolescents <18 y of age (score range: 0-14), and 1/2, between 4 and 5 (4/5), and between 6 and 7 (6/7) in adult-only households (range: 0-8). With minor variations, the same cutoffs were also identified in the macroregions. Although our findings confirm, in general, the classification currently used, the limit of 1/2 (compared with 0/1) for separating the milder from the baseline category emerged consistently in all analyses.Conclusions: Nationwide findings corroborate previous local evidence that households with an overall score of 1 are more akin to those scoring negative on all items. These results may contribute to guide experts' and policymakers' decisions on the most appropriate EBIA cutoffs.

Heterogeneity in resident perceptions of a bio-cultural heritage in Hong Kong: A latent class factor analysis

There is an increasing recognition of ecosystem services provided by urban trees and their importance to urban resilience and sustainability through the preservation and enhancement of biological diversity so as to withstand disturbances and retain ecosystem functions as well as guarantee the well-being of current and future urban dwellers. However, the heterogeneous perceptions that urban residents may hold towards various ecosystem services have seldom been investigated. This study made a unique contribution to the growing body of literature on urban ecosystem services by examining the unobserved heterogeneity in resident perceptions of ecosystem services provided by a distinctive bio-cultural asset, urban heritage trees, in Hong Kong, via a novel application of latent class factor analysis which allows for considering the multidimensionality of latent factors and increases model parsimony. A total of 1075 face-to-face interviews were conducted with a stratified sample of residents about their perceived importance of two categories of distinctive ecosystem services provided by urban heritage trees: biological benefits and cultural benefits. The results indicated that, on average, both biological and cultural benefits of urban heritage trees were perceived to be important. Nevertheless, six classes were identified on the basis of different levels of two latent class factors, which differed markedly with respect to individual’s perceived importance of ecosystem services provided by urban heritage trees, from fairly balanced to very divergent perceptions of biological services and cultural services. This heterogeneity was explained with covariates describing respondents’ sociodemographic characteristics and activities at heritage tree sites. The results have implications for optimally tailoring promoting and participatory approaches, fostering improved communications with the general public, and nurturing overall support for urban heritage tree conservation from heterogeneous resident groups in order to achieve urban resilience and sustainability.

How to Classify Who Experienced Flow from Who Did Not Based on the Flow State Scale-2 Scores: A Pilot Study of Latent Class Factor Analysis

The present study examined the extent to which scores on the Flow State Scale-2 (FSS-2) could differentiate individuals who experienced flow characteristics in physical activity from those who did not. A total of 1,048 participants completed the Japanese version of the FSS-2. Latent class factor analysis (LCFA), which combines the strengths of both latent class analysis and factor analysis, was conducted on the FSS-2 responses. Four classes were identified through a series of LCFAs and the patterns of the item-average scores for the nine flow attributes were found parallel among these classes. The top two classes (15.1% and 38.9% of the whole sample) were considered the groups who experienced flow characteristics during their physical activities. These results indicated that individuals who experienced flow attributes in physical activity could be differentiated from those who did not based on their FSS-2 scores. Criteria for classifying individuals into the two groups were proposed.

A Model-Based Approach to Identify Classes and Respective Cutoffs of the Brazilian Household Food Insecurity Measurement Scale

Background: The Brazilian Household Food Insecurity Measurement Scale (EBIA) is the main tool for assessing household food insecurity (FI) in Brazil, assisting in monitoring and improving national public policies to promote food security. Based on the sum of item scores, households have been classified into 4 levels of FI, with the use of cutoffs arising from expert discussions informed by psychometric analyses and policy considerations.Objectives: This study aimed to identify homogeneous latent groups corresponding to levels of FI, examine whether such subgroups could be defined from discriminant cutoffs applied to the overall EBIA raw score, and compare these cutoffs against those currently used.Methods: A cross-sectional population-based study with a representative sample of 1105 households from a low-income metropolitan area of Rio de Janeiro was conducted. Latent class factor analysis (LCFA) models were applied to the answers to EBIA’s items to identify homogeneous groups, obtaining the number of latent classes for FI measured by the scale. Based on this and a thorough classification agreement evaluation, optimal cutoffs for discriminating between different severity levels of FI were ascertained. Model-based grouping and the official EBIA classification cutoffs were also contrasted.Results: LCFA identified 4 homogeneous groups with a very high degree of class separation (entropy = 0.906), endorsing the classification of EBIA as a 4-level measure of FI. Two sets of cutoffs were identified to separate such groups according to household type: 1/2, 5/6, and 10/11 in households with children and adolescents (score range: 0–14); and 1/2, 3/4, and 5/6 in adult-only households (score range: 0–7).Conclusion: Although roughly classifying EBIA as in previous studies, the current approach suggests that, in terms of raw score, households endorsing only one item of the scale would be better classified by being placed in the same stratum as those remaining negative on all items.

Casting wider diagnostic nets for anxiety and depression: Disability-driven cross-diagnostic subtypes in a large population study

IntroductionData-driven techniques are frequently applied to identify subtypes of depression and anxiety. Although they are highly comorbid and often grouped under a single internalizing banner, most subtyping studies have focused on either depression or anxiety. Furthermore, most previous subtyping studies have not taken into account experienced disability.ObjectivesTo incorporate disability into a data-driven cross-diagnostic subtyping model.AimsTo capture heterogeneity of depression and anxiety symptomatology and investigate the importance of domain-specific disability-levels to distinguish between homogeneous subtypes.MethodsSixteen symptoms were assessed without skips using the MINI-interview in a population sample (LifeLines; n = 73403). Disability was measured with the RAND-36. To identify the best-fitting subtyping model, different nested latent variable models (latent class analysis, factor analysis and mixed-measurement item response theory [MM-IRT]) with and without disability covariates were compared. External variables were compared between the best model's classes.ResultsA five-class MM-IRT model incorporating disability showed the best fit (Fig. 1). Accounting for disability improved the differentiation between classes reporting isolated non-specific symptoms (“Somatic” [13.0%], and “Worried” [14.0%]) and those reporting more psychopathological symptoms (“Subclinical” [8.8%], and “Clinical” [3.3%]). A “Subclinical” class reported symptomatology at subthreshold levels. No pure depression or anxiety, but only mixed classes were observed.ConclusionsAn overarching subtyping model incorporating both symptoms and disability identified distinct cross-diagnostic subtypes. Diagnostic nets should be cast wider than current phenomenology-based categorical systems.Figure not available.Disclosure of interestThe authors have not supplied their declaration of competing interest.

Comparing Extreme Response Styles between Agree-Disagree and Item-Specific Scales

Although Likert scales in agree-disagree (A/D) format are popular in surveys, the data quality yielded by them is controversial among researchers. Recognizing the measurement issues involved with the A/D format, researchers have developed other question formats to measure attitudes. In this study, we focused on an alternative question type, the item-specific (IS) question, which asks the respondent to choose an option that best describes his or her attitude. Using political efficacy items from the American National Election Studies (ANES), we compare extreme response style (ERS) between A/D and IS scales. Latent class factor analysis showed that ERS exists in both A/D and IS scale formats, but differs slightly across the two. Also, when analyzing ERS within subjects across two waves, there is only a single ERS for both question formats, after controlling for the correlation within respondents. The last finding suggests that ERS is a stable characteristic

The latent class multitrait-multimethod model.

A latent class multitrait-multimethod (MTMM) model is proposed to estimate random and systematic measurement error in categorical survey questions while making fewer assumptions than have been made so far in such evaluations, allowing for possible extreme response behavior and other nonmonotone effects. The method is a combination of the MTMM research design of Campbell and Fiske (1959), the basic response model for survey questions of Saris and Andrews (1991), and the latent class factor model of Vermunt and Magidson (2004, pp. 227-230). The latent class MTMM model thus combines an existing design, model, and method to allow for the estimation of the degree to and manner in which survey questions are affected by systematic measurement error. Starting from a general form of the response function for a survey question, we present the MTMM experimental approach to identification of the response function's parameters. A "trait-method biplot" is introduced as a means of interpreting the estimates of systematic measurement error, whereas the quality of the questions can be evaluated by item information curves and the item information function. An experiment from the European Social Survey is analyzed and the results are discussed, yielding valuable insights into the functioning of a set of example questions on the role of women in society in 2 countries.

The effect of sample selection on the distinction between alcohol abuse and dependence

Steppan, M., Piontek, D., &amp; Kraus, L. (2014). The effect of sample selection on the distinction between alcohol abuse and dependence. The International Journal Of Alcohol And Drug Research, 3(2), 159-168. doi:http://dx.doi.org/10.7895/ijadr.v3i2.100Aim: The effect of sample selection on the dimensionality of DSM-IV alcohol and dependence (AUD) criteria was tested applying different methods.Sample: Data from the 2006 German Epidemiological Survey of Substance Abuse (ESA) were used. A mixed-mode design was used (self-administered questionnaires and telephone interviews), and 7,912 individuals, aged 18 to 64 years, participated. The response rate was 45%. Alcohol abuse and dependence were assessed according to DSM-IV, based on the Munich Composite International Diagnostic Interview (M-CIDI). Inter-item correlations, Confirmatory Factor Analysis (CFA), and Latent Class Analysis (LCA) were applied to the total sample (unrestricted sample, URS) and a subsample of individuals with at least one endorsed criterion (restricted sample, RS). Latent Class Factor Analysis (LCFA) was performed using the RS, including covariates (age, sex, education).Findings: The mean inter-item correlation was higher in the URS than in the RS. When individuals without criterion endorsement were excluded, factor analyses resulted in more dimensions. In the RS, LCA yielded an interaction between abuse, dependence and class membership. The LCFA identified two dimensions and five classes corresponding to abuse and dependence.Conclusions: Sample selection has a critical effect on dimensionality analyses. When individuals who do not endorse a single criterion are excluded, the bi-axial factor structure of the DSM-IV (abuse and dependence) can be supported. However, there is also evidence that a further diagnostic category should be included or that the threshold for dependence should be lowered.

Self-Regulated Learning, Motivation and Emotions Towards University Study. A Latent Class Approach

Students' attitudes, motivations and emotions towards university study have a great inuence on their university careers. In this work, we use a latent class factor analysis approach to reveal the underlying latent factors which summarise a series of items investigating students' positions in three domains: self-regulated learning, motivation, and emotions towards university study. Data come from a CAWI survey conducted in 2012 on a cohort of stu- dents enrolled in academic year 2006-07 at University of Padova, a large public university in north-east Italy. Results show that the underlying latent factors are in line with related psychological literature.

The Effect of Labeling and Numbering of Response Scales on the Likelihood of Response Bias

Extreme response style (ERS) and acquiescence response style (ARS) are among the most encountered problems in attitudinal research. The authors investigate whether the response bias caused by these response styles varies with following three aspects of question format: full versus end labeling, numbering answer categories, and bipolar versus agreement response scales. A questionnaire was distributed to a random sample of 5,351 respondents from the Longitudinal Internet Studies for the Social Sciences household panel, of which a subsample was assigned to one of five conditions. The authors apply a latent class factor model that allows for diagnosing and correcting for ERS and ARS simultaneously. The results show clearly that both response styles are present in the data set, but ARS is less pronounced than ERS. With regard to format effects, the authors find that end labeling evokes more ERS than full labeling and that bipolar scales evoke more ERS than agreement style scales. With full labeling, ERS opposes opting for middle response categories, whereas end labeling distinguishes ERS from all other response categories. ARS did not significantly differ depending on test conditions.

The preferred role and perceived performance of the welfare state: European welfare attitudes from a multidimensional perspective

Welfare state support has two core dimensions: attitudes about what the welfare state should do and beliefs about its actual performance. People can combine any position on one dimension with any position on the other, yielding four opinion clusters: people can combine preferences for a relatively strong role of the welfare state with a perception of a relatively low or high welfare state performance; likewise, people preferring a small role of the welfare state can perceive a high or low performing welfare state. We apply Latent Class Factor Analysis to data of 22 European countries from the 2008/9 European Social Survey. We find that each of the four clusters contains a substantial proportion of respondents that differs between welfare regimes. In addition, cluster membership is also related to covariates that measure people’s structural positions and ideological preferences.