Search for: All records

ABSTRACT This work considers estimation and forecasting in a multivariate, possibly high‐dimensional count time series model constructed from a transformation of a latent Gaussian dynamic factor series. The estimation of the latent model parameters is based on second‐order properties of the count and underlying Gaussian time series, yielding estimators of the underlying covariance matrices for which standard principal component analysis applies. Theoretical consistency results are established for the proposed estimation, building on certain concentration results for the models of the type considered. They also involve the memory of the latent Gaussian process, quantified through a spectral gap, shown to be suitably bounded as the model dimension increases, which is of independent interest. In addition, novel cross‐validation schemes are suggested for model selection. The forecasting is carried out through a particle‐based sequential Monte Carlo, leveraging Kalman filtering techniques. A simulation study and an application are also considered. 

ABSTRACT This work introduces a novel framework for dynamic factor model‐based group‐level analysis of multiple subjects time‐series data, called GRoup Integrative DYnamic factor (GRIDY) models. The framework identifies and characterizes intersubject similarities and differences between two predetermined groups by considering a combination of group spatial information and individual temporal dynamics. Furthermore, it enables the identification of intrasubject similarities and differences over time by employing different model configurations for each subject. Methodologically, the framework combines a novel principal angle‐based rank selection algorithm and a noniterative integrative analysis framework. Inspired by simultaneous component analysis, this approach also reconstructs identifiable latent factor series with flexible covariance structures. The performance of the GRIDY models is evaluated through simulations conducted under various scenarios. An application is also presented to compare resting‐state functional MRI data collected from multiple subjects in autism spectrum disorder and control groups. 

Contamination is a methodological phenomenon occurring in child maltreatment research when individuals in an established comparison condition have, in reality, been exposed to maltreatment during childhood. The current paper: (1) provides a conceptual and methodological introduction to contamination in child maltreatment research, (2) reviews the empirical literature demonstrating that the presence of contamination biases causal estimates in both prospective and retrospective cohort studies of child maltreatment effects, (3) outlines a dual measurement strategy for how child maltreatment researchers can address contamination, and (4) describes modern statistical methods for generating causal estimates in child maltreatment research after contamination is controlled. Our goal is to introduce the issue of contamination to researchers examining the effects of child maltreatment in an effort to improve the precision and replication of causal estimates that ultimately inform scientific and clinical decision-making as well as public policy. 

Abstract. The use of dynamic network models has grown in recent years. These models allow researchers to capture both lagged and contemporaneous effects in longitudinal data typically as variations, reformulations, or extensions of the standard vector autoregressive (VAR) models. To date, many of these dynamic networks have not been explicitly compared to one another. We compare three popular dynamic network approaches – GIMME, uSEM, and LASSO gVAR – in terms of their differences in modeling assumptions, estimation procedures, statistical properties based on a Monte Carlo simulation, and implications for affect and personality researchers. We found that all three dynamic network approaches provided yielded group-level empirical results in partial support of affect and personality theories. However, individual-level results revealed a great deal of heterogeneity across approaches and participants. Reasons for discrepancies are discussed alongside these approaches’ respective strengths and limitations.