Using dynamic factor analysis to provide insights into data reliability in experience sampling studies.

Fuller‐Tyszkiewicz, Matthew; Hartley-Clark, Linda; Cummins, Robert A.; Tomyn, Adrian J.; Weinberg, Melissa K.; Richardson, Ben

doi:10.1037/pas0000411

Cited by 20 publications

(40 citation statements)

References 42 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To answer this question, we modeled ratings of freely moving thought with the hypothesis that they would vary as a function of time. We used a mixed-effect multilevel modelling approach to test this hypothesis because: (1) it assesses change over time while preserving between-participant differences in baseline ratings (intercept) and estimated relationships (slope; Fuller-Tyszkiewicz et al, 2017); and (2) it is robust to missing data (Mirman, 2016). Below, we describe our analytical approach using current best-practices for growth curve modeling; interested readers can find more detail in Mirman (2016), Mirman, Dixon, and Magnuson (2008), and Singer and Willett (2003).…”

Section: Introductionmentioning

confidence: 99%

Mind-wandering rates fluctuate across the day: evidence from an experience-sampling study

et al. 2018

View full text Add to dashboard Cite

Previous research has demonstrated reliable fluctuations in attentional processes during the course of the day. Everyday life experience sampling, during which participants respond to “probes” delivered at random intervals throughout the day on their mobile devices, is an effective tool for capturing such diurnal fluctuations in a naturalistic way. The existence of diurnal fluctuations in the case of mind-wandering, however, has not been examined to date. We did so in two studies. In the first study, we employed everyday experience sampling to obtain self-reports from 146 university students who rated the degree of free movement in their thoughts multiple times per day over five days. These time course data were analyzed using multilevel modelling. Freely moving thought was found to fluctuate reliably over the course of the day, with lower ratings reported in the early morning and afternoon and higher ratings around midday and evening. In the second study, we replicated these effects with a reanalysis of data from a past everyday experience-sampling study. We also demonstrated differences in parameter values for the models representing freely moving thought and two common conceptualizations of mind-wandering: task-unrelated thought and stimulus-independent thought. Taken together, the present results establish and replicate a complex pattern of change over the course of the day in how freely thought moves, while also providing further evidence that freedom of movement is dissociable from other dimensions of thought such as its task-relatedness and stimulus-dependence. Future research should focus on probing possible mechanisms behind circadian fluctuations of thought dynamics.Electronic supplementary materialThe online version of this article (10.1186/s41235-018-0141-4) contains supplementary material, which is available to authorized users.

show abstract

Section: Introductionmentioning

confidence: 99%

Mind-wandering rates fluctuate across the day: evidence from an experience-sampling study

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Note that single-level state-trait SEMs are commonly used to analyze data that have between two and eight measurement occasions (Geiser & Lockhart, 2012, Appendix B). The conditions with 30 measurement occasions or more aimed to mimic the common number of observations in psychological time series (e.g., Bringmann et al, 2016;Fuller-Tyszkiewicz et al, 2017;Schuurman et al, 2015;Song & Zhang, 2014). Thirdly, three proportions of missing values were selected: 0%, 10%, and 20% 2 .…”

Section: Methodsmentioning

confidence: 99%

“…Functions to compute these coefficients can be found in the R code. -Tyszkiewicz et al, 2017;Molenaar, 1985;Song & Zhang, 2014), and more general frameworks such as state-space modeling (Chow, Hamaker, Fujita, & Boker, 2009;Kalman, 1960;Lodewyckx, Tuerlinckx, Kuppens, Allen, & Sheeber, 2011) Firstly, multilevel-VAR models are an integration of time series and multilevel modeling, which allow modeling auto-and cross-regressive effects when N > 1 (Rovine & Walls, 2006). In contrast to autoregressive effects, cross-regressive effects model the dependency of a variable X at time t on a different variable Y at previous time points (e.g., Y at t − 1 or t − 2).…”

Section: Similarities and Differencesmentioning

confidence: 99%

“…Initially, DFA models (Fuller-Tyszkiewicz et al, 2017;Molenaar, 1985) were inspired by the P-technique analysis proposed by Cattell (1963). These are factor analysis models USING STRUCTURAL EQUATION MODELING TO STUDY TRAITS AND STATES IN INTENSIVE LONGITUDINAL DATA 23 that are applied to the time series of an individual and account for the lagged structure in the data.…”

Section: Relation Ofmentioning

confidence: 99%

See 1 more Smart Citation

Using Structural Equation Modeling to Study Traits and States in Intensive Longitudinal Data

Castro-Alvarez¹,

Tendeiro²,

Meijer³

et al. 2020

Preprint

View full text Add to dashboard Cite

Traditionally, researchers have used time series and multilevel models to analyze intensive longitudinal data. However, these models do not directly address traits and states which conceptualize the stability and variability implicit in longitudinal research, and they do not explicitly take into account measurement error. An alternative to overcome these drawbacks is to consider structural equation models (state-trait SEMs) for longitudinal data that represent traits and states as latent variables. Most of these models are encompassed in the Latent State-Trait (LST) theory. These state-trait SEMs can be problematic when the number of measurement occasions increases. As they require the data to be in wide format, these models quickly become overparameterized and lead to non-convergence issues. For these reasons, multilevel versions of state-trait SEMs have been proposed, which require the data in long format. To study how suitable state-trait SEMs are for intensive longitudinal data, we carried out a simulation study. We compared the traditional single level to the multilevel version of three state-trait SEMs. The selected models were the multistate-singletrait (MSST) model, the common and unique trait-state (CUTS) model, and the trait-state-occasion (TSO) model. Furthermore, we also included an empirical application. Our results indicated that the TSO model performed best in both the simulated and the empirical data. To conclude, we highlight the usefulness of state-trait SEMs to study the psychometric properties of the questionnaires used in intensive longitudinal data. Yet, these models still have multiple limitations, some of which might be overcome by extending them to more general frameworks.

show abstract

“…Functions to compute these coefficients can be found in the R code. Ebner-Priemer et al, 2015;Rovine & Walls, 2006), dynamic factor analysis models (DFA; Fuller-Tyszkiewicz et al, 2017;Molenaar, 1985;Song & Zhang, 2014), and more general frameworks such as state-space modeling (Chow, Hamaker, Fujita, & Boker, 2009;Kalman, 1960;Lodewyckx, Tuerlinckx, Kuppens, Allen, & Sheeber, 2011) and dynamic structural equation modeling (DSEM; Asparouhov, Hamaker, & Muthén, 2017. All these models have in common that they are specifically developed to analyze intensive longitudinal data, and they incorporate autoregressive effects to model persons' dynamics.…”

Section: Similarities and Differencesmentioning

confidence: 99%

Using structural equation modeling to study traits and states in intensive longitudinal data.

Castro-Alvarez¹,

Tendeiro²,

Meijer³

et al. 2022

Psychological Methods

View full text Add to dashboard Cite

We wish to thank prof. dr. Peter de Jonge and the team of HoeGekisNL, as well as the participants, for allowing us to use their data in this study. We would also like to thank the Center for Information Technology of the University of Groningen for their support and for providing access to the Peregrine high performance computing cluster.Partial results of this study were presented at the measurement error in longitudinal data workshop held in the university of Manchester in June 2019 and at the IMPS 2019 meeting in Santiago de Chile. Additionally, all the code developed during this research is available in the following GitHub repository: https://github.com/secastroal/LST_Analyses. We are also very grateful for the helpful comments provided by four anonymous reviewers. Finally, we are especially thankful to dr. Markus I. Eronen and María Angélica Acevedo-Mesa, who help us to proofread the revised manuscript.

show abstract

Using dynamic factor analysis to provide insights into data reliability in experience sampling studies.

Cited by 20 publications

References 42 publications

Mind-wandering rates fluctuate across the day: evidence from an experience-sampling study

Mind-wandering rates fluctuate across the day: evidence from an experience-sampling study

Using Structural Equation Modeling to Study Traits and States in Intensive Longitudinal Data

Using structural equation modeling to study traits and states in intensive longitudinal data.

Contact Info

Product

Resources

About