Tanja Lischetzke

Structural equation modeling of multitrait-multimethod data: Different models for different types of methods.

The question as to which structural equation model should be selected when multitrait-multimethod (MTMM) data are analyzed is of interest to many researchers. In the past, attempts to find a well-fitting model have often been data-driven and highly arbitrary. In the present article, the authors argue that the measurement design (type of methods used) should guide the choice of the statistical model to analyze the data. In this respect, the authors distinguish between (a) interchangeable methods, (b) structurally different methods, and (c) the combination of both kinds of methods. The authors present an appropriate model for each type of method. All models allow separating measurement error from trait influences and trait-specific method effects. With respect to interchangeable methods, a multilevel confirmatory factor model is presented. For structurally different methods, the correlated trait-correlated (method-1) model is recommended. Finally, the authors demonstrate how to appropriately analyze data from MTMM designs that simultaneously use interchangeable and structurally different methods. All models are applied to empirical data to illustrate their proper use. Some implications and guidelines for modeling MTMM data are discussed.

Analysing multitrait–multimethod data with structural equation models for ordinal variables applying the WLSMV estimator: What sample size is needed for valid results?

Convergent and discriminant validity of psychological constructs can best be examined in the framework of multitrait-multimethod (MTMM) analysis. To gain information at the level of single items, MTMM models for categorical variables have to be applied. The CTC(M-1) model is presented as an example of an MTMM model for ordinal variables. Based on an empirical application of the CTC(M-1) model, a complex simulation study was conducted to examine the sample size requirements of the robust weighted least squares mean- and variance-adjusted chi(2) test of model fit (WLSMV estimator) implemented in Mplus. In particular, the simulation study analysed the chi(2) approximation, the parameter estimation bias, the standard error bias, and the reliability of the WLSMV estimator depending on the varying number of items per trait-method unit (ranging from 2 to 8) and varying sample sizes (250, 500, 750, and 1000 observations). The results showed that the WLSMV estimator provided a good -- albeit slightly liberal -- chi(2) approximation and stable and reliable parameter estimates for models of reasonable complexity (2-4 items) and small sample sizes (at least 250 observations). When more complex models with 5 or more items were analysed, larger sample sizes of at least 500 observations were needed. The most complex model with 9 trait-method units and 8 items (72 observed variables) requires sample sizes of at least 1000 observations.

The structure of emotional expressivity: each emotion counts.

Several models of the dimensionality of emotional expressivity were examined in a multitrait-multimethod study. Targets and peer raters completed measures of the targets emotional expressivity (Berkeley Expressivity Questionnaire. BEQ; J. J. Gross & O. P. John, 1995; and a measure of emotion-specific expression) and the Big 5 personality dimensions. The results of structural equation modeling and analysis of variance revealed that an emotion-specific model was superior to models of valence-specific or unidimensional expressivity. The distinct emotions differed in their relations with the dimensions of the 5-factor model. These results were corroborated by self- and other reports. Finally, the degree of convergence between self- and other ratings differed between emotions, demonstrating the multidimensional character of emotional expressivity.

Compliance to a cell phone-based ecological momentary assessment study: the effect of time and personality characteristics.

Ecological momentary assessment (EMA) is a method that is now widely used to study behavior and mood in the settings in which they naturally occur. It maximizes ecological validity and avoids the limitations of retrospective self-reports. Compliance patterns across time have not been studied. Consistent compliance patterns could lead to data not missing at random and bias the results of subsequent analyses. In order to use modern statistical approaches for handling missing data, it is important to include variables predicting missing values into the statistical analysis. Therefore, these predictors have to be known and measured. The authors collected data on 3 four-item mood scales measuring well-being, wakefulness, and nervousness on 6 occasions per day for 7 days (N = 305) and examined compliance rate across time, within day, and within week. Results show good global compliance (mean compliance: 74.9% of calls answered). Compliance varied more within day than within week. Within day, it was lower for the first call of the day between 9 p.m. and 11 p.m. and higher for the call between 5 p.m. and 7 p.m. Within week, calls were equally answered across days of the week, but, as the study progressed, there was a slight drop in compliance with a progressive decrease that was stronger for the first 2 calls. Compliance on the person level did not depend on personality or on satisfaction with life. Practical consequences of the results for conducting ambulatory assessment studies are discussed, and some recommendations are given.

Psychometric properties of a computerized mobile phone method for assessing mood in daily life

Ecological momentary assessment is a method that is now largely used to study behavior and mood in the settings in which they naturally occur. It maximizes ecological validity and avoids the limitations of retrospective self-reports. Studies on the psychometric properties of scales administered via mobile phone ecological momentary assessment are lacking. Therefore, we collected data on a 4-item mood scale measuring well being on six occasions per day for 7 days (N = 307) and examined compliance rate across time, within day, and within week. Using specific latent state-trait structural equation models, we analyzed the degree to which interindividual mood differences on an occasion of measurement were because of (a) measurement error, (b) stable differences in mood level, and (c) occasion-specific differences. Results show good compliance (mean compliance: 74.9% of calls answered). Moreover, the scale showed good reliability (M = .82). Mood was mostly stable, especially the first 3 days of the week. It depended weakly albeit significantly on the previous assessment (autoregressive coefficient). In conclusion, computerized mobile phone assessment is an appropriate, easy-to-use, and promising method to measure mood.

Measuring affective clarity indirectly: individual differences in response latencies of state.

This research investigated a new method to measure momentary affective clarity indirectly, which is based on latencies of responses to state affect items. Three studies revealed that this indirect measure of momentary clarity demonstrated high reliability and stability as well as convergent and predictive validity. The indirect measure was associated with dispositional clarity when the concept of clarity was activated before measuring response latencies (Studies 1 and 2) and was related to self-reports of momentary clarity (Study 3). Furthermore, Study 3 demonstrated that indirectly measured clarity decreased after an affectively complex film. Indirectly, but not directly, measured momentary clarity predicted a more positive affective state at the end of the study. This effect was mediated by affect regulation.

A comparison of method effects in two confirmatory factor models for structurally different methods

Multimethod data analysis is a complex procedure that is often used to examine the degree to which different measures of the same construct converge in the assessment of this construct. Several authors have called for a greater understanding of the definition and meaning of method effects in different models for multimethod data. In this article, we compare 2 recently proposed approaches for modeling data with structurally different methods with regard to the definition and meaning of method effects, the restricted CT-C(M – 1) model (Geiser, Eid, & Nussbeck, 2008) and the latent difference model (Lischetzke, Eid, & Nussbeck, 2002). We also introduce the concepts of individual, conditional, and general method bias and show how these types of biases are represented in the models. An application to a multirater data set (N = 199) as well as recommendations for the application and interpretation of each model are provided.

Die Wahrnehmung eigener und fremder Gefühle

Zusammenfassung. Das Erkennen der eigenen Gefuhle und der Gefuhle anderer Menschen ist eine wichtige Kompetenz im Umgang mit Emotionen und Stimmungen. Es werden die bisher vor allem im englischen Sprachraum untersuchten Konstrukte der emotionalen Selbstaufmerksamkeit und der Klarheit uber eigene Gefuhle vorgestellt und die konzeptuelle Trennung der Konstrukte erstmals auf die Wahrnehmung fremder Gefuhle ubertragen. Die Konstruktion von Skalen zur Erfassung der Konstrukte sowie deren teststatistische Uberprufung werden beschrieben. Die Ergebnisse von drei Studien (N = 236; N = 117; N = 1446) zeigen, dass die konzeptuelle Trennung der Dimensionen bestatigt wird und dass die Skalen der Wahrnehmung eigener und fremder Gefuhle gute psychometrische Eigenschaften besitzen. Hinweise auf die Validitat der Skalen liefern die Zusammenhangsmuster mit anderen Personlichkeitskonstrukten (Private Selbstaufmerksamkeit, Alexithymie, “Big Five“, Habituelle Befindlichkeit, Perspektivenubernahme, Empathie).

Validating an indirect measure of clarity of feelings: evidence from laboratory and naturalistic settings.

This study analyzed the reliability and validity of an indirect measure of clarity of feelings that is based on response latencies (RTs) of mood ratings. Fifty-two participants completed a laboratory session and an experience-sampling week with 6 measurement occasions per day. Shorter RT of mood ratings measured in the laboratory (but not self-reported dispositional clarity) predicted higher overall mood regulation success during the experience-sampling week. As a new indirect ambulatory measure of clarity, RTs of mood ratings were measured on handheld devices during the experience-sampling week. The new ambulatory RT measure of clarity demonstrated good psychometric properties. Within-occasions reliability (internal consistency) was satisfactory, and between-occasions reliability (consistency of aggregated scores) was high. Ambulatory RT of mood ratings demonstrated moderate to high convergence with RT of mood ratings measured in the laboratory session. Both RT measures were unrelated to self-reported dispositional clarity of feelings. However, momentary RT converged with a self-report measure of momentary clarity on the within-persons level: Participants were faster to rate those mood items that they were more certain about. Evidence for the predictive validity of the new ambulatory RT measure was provided by the finding that on the within-persons level, shorter RT (but not self-reported momentary clarity) predicted higher mood regulation success and better mood at subsequent measurement occasions. The results suggest that RT of mood ratings can be used as a reliable and valid indicator of an individuals clarity of feelings in laboratory and experience-sampling studies.

Exploring dynamics in mood regulation--mixture latent Markov modeling of ambulatory assessment data.

Objective To illustrate how fluctuation patterns in ambulatory assessment data with features such as few categorical items, measurement error, and heterogeneity in the change pattern can adequately be analyzed with mixture latent Markov models. The identification of fluctuation patterns can be of great value to psychosomatic research concerned with dysfunctional behavior or cognitions, such as addictive behavior or noncompliance. In our application, unobserved subgroups of individuals who differ with regard to their mood regulation processes, such as mood maintenance and mood repair, are identified. Methods In an ambulatory assessment study, mood ratings were collected 56 times during 1 week from 164 students. The pleasant-unpleasant mood dimension was assessed by the two ordered categorical items unwell-well and bad-good. Mixture latent Markov models with different number of states, classes, and degrees of invariance were tested, and the best model according to information criteria was interpreted. Results Two latent classes that differed in their mood regulation pattern during the day were identified. Mean classification probabilities were high (>0.88) for this model. The larger class showed a tendency to stay in and return to a moderately pleasant mood state, whereas the smaller class was more likely to move to a very pleasant mood state and to stay there with a higher probability. Conclusions Mixture latent Markov models are suitable to obtain information about interindividual differences in stability and change in ambulatory assessment data. Identified mood regulation patterns can serve as reference for typical mood fluctuation in healthy young adults. Abbreviations AA = ambulatory assessment MLM = mixture latent Markov MMQ = Multidimensional Mood Questionnaire BIC = Bayesian Information Criterion AIC3 = modified Akaike Information Criterion