A Limited Information Estimator for Dynamic Factor Models

Fisher, Zachary; Bollen, Kenneth A.; Gates, Kathleen M.

doi:10.1080/00273171.2018.1519406

Cited by 15 publications

(15 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data were analyzed in R using a structural equation modeling approach, Model-Implied Instrumental Variable estimtation (Bollen, 1996, 2001), appropriate for high-dimensional data (MIIVsem; https://cran.r-project.org/package=MIIVsem, Fisher, Bollen, Gates, & Rönkkö, 2017). This approach is designed for robust estimation of high-dimensional structural equation models and has recently been extended to handle individual-level multivariate timeseries data (Fisher, Bollen, & Gates, In Press). Furthermore, this approach allows for the estimation of variance and covariance parameters of network timeseries along with bootstrap standard errors.…”

Section: Methodsmentioning

confidence: 99%

Between-network Functional Connectivity Is Modified by Age and Cognitive Task Domain

Varangis

Razlighi

Habeck

et al. 2019

Journal of Cognitive Neuroscience

View full text Add to dashboard Cite

Research on the cognitive neuroscience of aging has identified myriad neurocognitive processes that are affected by the aging process, with a focus on identifying neural correlates of cognitive function in aging. The present study aimed to test whether inter-network connectivity among 6 cognitive networks is sensitive to age-related changes in neural efficiency and cognitive functioning. A factor analytic connectivity approach was used to model network interactions during 11 cognitive tasks grouped into 4 primary cognitive domains: vocabulary, perceptual speed, fluid reasoning, and episodic memory. Results showed that both age and task domain were related to inter-network connectivity, and that some of the connections among the networks were associated with performance on the in-scanner tasks. These findings demonstrate that inter-network connectivity among several cognitive networks is not only affected by aging and task demands, but also shows a relationship with task performance. As such, future studies examining inter-network connectivity in aging should consider multiple networks, and multiple task conditions, in order to better measure dynamic patterns of network flexibility over the course of cognitive aging.

show abstract

Section: Methodsmentioning

confidence: 99%

Between-network Functional Connectivity Is Modified by Age and Cognitive Task Domain

Varangis

Razlighi

Habeck

et al. 2019

Journal of Cognitive Neuroscience

View full text Add to dashboard Cite

show abstract

“…Gates et al (2020) propose a MIIV-2SLS approach to time series data that allows individual-level analysis without assuming measurement invariance across individuals. Fisher et al (2019) introduce a MIIV method to analyze dynamic factor analysis models that is more robust to structural misspecifications than alternative times series methods. Culpepper et al (2019) illustrate a MIIV-2SLS technique to handle measurement and prediction invariance.…”

Section: Extensions and Applicationsmentioning

confidence: 99%

An introduction to model implied instrumental variables using two stage least squares (MIIV-2SLS) in structural equation models (SEMs).

Bollen¹,

Fisher²,

Giordano³

et al. 2022

Psychological Methods

Self Cite

View full text Add to dashboard Cite

Structural equation models (SEMs) are widely used to handle multiequation systems that involve latent variables, multiple indicators, and measurement error. Maximum likelihood (ML) and diagonally weighted least squares (DWLS) dominate the estimation of SEMs with continuous or categorical endogenous variables, respectively. When a model is correctly specified, ML and DWLS function well. But, in the face of incorrect structures or nonconvergence, their performance can seriously deteriorate. Model implied instrumental variable, two stage least squares (MIIV-2SLS) estimates and tests individual equations, is more robust to misspecifications, and is noniterative, thus avoiding nonconvergence. This article is an overview and tutorial on MIIV-2SLS. It reviews the six major steps in using MIIV-2SLS: (a) model specification; (b) model identification; (c) latent to observed (L2O) variable transformation; (d) finding MIIVs; (e) using 2SLS; and (f) tests of overidentified equations. Each step is illustrated using a running empirical example from Reisenzein's (1986) randomized experiment on helping behavior. We also explain and illustrate the analytic conditions under which an equation estimated with MIIV-2SLS is robust to structural misspecifications. We include additional sections on MIIV approaches using a covariance matrix and mean vector as data input, conducting multilevel SEM, analyzing categorical endogenous variables, causal inference, and extensions and applications. Online supplemental material illustrates input code for all examples and simulations using the R package MIIVsem.

show abstract

“…A second and related benefit is that the latent variable model parameter estimation is conducted separately from measurement model parameter estimation. As noted above, much work has shown that the strict assumption of homogeneity in processes across individuals is often not met in neuroimaging (Finn et al, 2015;Gates, Molenaar, Iyer, Nigg, & Fair, 2014;Laumann et al, 2015;Miller et al, 2002), has been shown previously that relations (even misspecifications) occurring for the latent variable model do not influence the measurement model parameter estimates (Bollen et al, 2018) and that MIIV-2SLS estimates of dynamic factor model parameters can be more robust to model misspecification when compared to traditional system-wide estimators (pseudo-ML, Kalman filter) (Fisher, Bollen, & Gates, 2019). Hence in this framework, estimating the entire final model using MIIV-2SLS will provide the same measurement model parameter estimates as those one would obtain by estimating the model with no latent variable paths.…”

Section: The Miiv-2sls Estimatormentioning

confidence: 99%

“…Because there are fewer parameters in a single equation than in a full model, this reduces the burden on the estimation in that there are more observations per parameter in a single In sum, the MIIV-2SLS opens up the new opportunities in that it: 1) is more robust to structural misspecification than full information estimators, 2) does not require equal parameters or structures across individuals, 3) is a noniterative estimator of coefficients and factor loadings that avoids issues of nonconvergence, 4) is computationally quick, and 5) enables estimation of identified equations in underidentified models. Importantly, more recent investigations indicate that MIIV-2SLS also has unique advantages over pseudo-ML and ML approaches for estimating dynamic factor models (Fisher, Bollen, & Gates, 2019). LV-GIMME takes advantage of these properties in our time series analyses.…”

Section: The Miiv-2sls Estimatormentioning

confidence: 99%

“…LV-GIMME operates from within a structural equation modeling (SEM) framework for dynamic factor analysis (DFA; Molenaar, 1985) and uses model-implied instrumental variables with two-stage least squares (MIIV-2SLS; Bollen, 1996) for estimation. The synthesis of these two lines of research has been provided in the development of the MIIV-2SLS for estimating dynamic factor models at the individual level has already been provided by Fisher, Bollen and Gates (2019).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Latent variable GIMME using model implied instrumental variables (MIIVs).

Gates¹,

Fisher²,

Bollen³

2020

Psychological Methods

Self Cite

View full text Add to dashboard Cite

Researchers across many domains of psychology increasingly wish to arrive at personalized and generalizable dynamic models of individuals' processes. This is seen in psychophysiological, behavioral, and emotional research paradigms, across a range of data types. Errors of measurement are inherent in most data. For this reason, researchers typically gather multiple indicators of the same latent construct and use methods, such as factor analysis, to arrive at scores from these indices. In addition to accurately measuring individuals, researchers also need to find the model that best describes the relations among the latent constructs. Most currently available data-driven searches do not include latent variables. We present an approach that builds from the strong foundations of Group Iterative Multiple Model Estimation (GIMME), the idiographic filter, and model implied instrumental variables with two-stage least squares estimation (MIIV-2SLS) to provide researchers with the option to include latent variables in their data-driven model searches. The resulting approach is called Latent Variable GIMME (LV-GIMME). GIMME is utilized for the data-driven search for relations that exist among latent variables. Unlike other approaches such as the idiographic filter, LV-GIMME does not require that the latent variable model to be constant across individuals. This requirement is loosened by utilizing MIIV-2SLS for estimation. Simulated data studies demonstrate that the method can reliably detect relations among latent constructs, and that latent constructs provide more power to detect effects than using observed variables directly. We use empirical data examples drawn from functional MRI and daily self-report data.

show abstract

A Limited Information Estimator for Dynamic Factor Models

Cited by 15 publications

References 56 publications

Between-network Functional Connectivity Is Modified by Age and Cognitive Task Domain

Between-network Functional Connectivity Is Modified by Age and Cognitive Task Domain

An introduction to model implied instrumental variables using two stage least squares (MIIV-2SLS) in structural equation models (SEMs).

Latent variable GIMME using model implied instrumental variables (MIIVs).

Contact Info

Product

Resources

About