Alessandro Ansani | Searcharxiv

arXiv2025

PLS-SEM-power: A Shiny App and R package for Computing Required Sample Size and Minimum Detectable Effect Size in PLS-SEMs

Despite its evanescent nature, statistical power is crucial for planning Partial Least Squares Structural Equation Modelling (PLS-SEM) studies. This brief paper introduces PLS-SEM-power, a Shiny Application and R package that implements the inverse square root method by Kock and Hadaya (2018) to calculate both the minimum required sample size (a priori analysis) and the Minimum Detectable Effect Size (MDES, sensitivity analysis), given a chosen significance level (alpha level) at 80% power (1 - beta). The application provides an intuitive user interface, facilitating reproducible and easily accessible analyses in diverse research contexts.

stat.ME↗

arXiv2023

Development and User Experiences of a Novel Virtual Reality Task for Poststroke Visuospatial Neglect: An Exploratory Pilot Study

Background: Visuospatial neglect (VSN) affects spatial awareness, leading to functional and motor challenges. This case study explores virtual reality (VR) as a potential complementary tool for VSN rehabilitation. Objective: Specifically, we aim to explore the initial experiences of patients and physiotherapists engaging with a novel protocol, using an audiovisual cue task to support VSN rehabilitation. Methods: A preliminary VR task integrating audiovisual cues was co-designed with 2 physiotherapists. The task was then tested with 2 patients with VSN over 12 sessions. The intervention focused on engaging neglected spatial areas, with physiotherapists adapting the task to individual needs and monitoring responses. Results: Initial testing with 2 trainee physiotherapists indicated high usability, engagement, and perceived safety. Two patients with VSN completed 12 VR sessions. For Patient A, completion times increased following the introduction of an audio cue, though modeling indicated a nonsignificant linear trend (beta = 0.08; P = .33) and a marginally significant downward curvature (beta = -0.001; P = .08). In contrast, Patient B showed a significant linear decrease in completion times (beta = -0.53; P = .009), with a quadratic trend indicating a performance minimum around session 10 (B = 0.007; P = .04). Intraweek variability also decreased. Motor scores (Box and Block Test and 9-Hole Peg Test) remained stable, and subjective feedback indicated improved mobility confidence and positive task engagement. Conclusions: Further research with larger cohorts is needed to confirm the VR task's utility and refine the intervention.

cs.HC↗