iiinova — where your digital self keeps evolving

Michele Scandola (He / Him) @scandle.bsky.social · 04/08/2026

Important limitations: the sample was relatively small, the design was cross-sectional, and the analyses were exploratory. The findings do not establish causality, and some unexpected results require replication. Preprint: osf.io/preprints/ps... #NEET #Psychology #OpenScience

osf.io

OSF

000

Michele Scandola (He / Him) @scandle.bsky.social · 04/08/2026

Practical implication: one-size-fits-all interventions focused only on “motivation” may be insufficient. Support may need to strengthen realistic future planning, interpersonal learning, emotional regulation, and the ability to recognize and use available social support.

110

Michele Scandola (He / Him) @scandle.bsky.social · 04/08/2026

Emotionality showed the most stable personality-related association: higher Emotionality was linked to a higher probability of NEET status. Education was negatively associated with NEET status and also moderated the role of several personality traits.

100

Michele Scandola (He / Him) @scandle.bsky.social · 04/08/2026

Social support also did not appear to work in the same way for everyone. It was associated with a lower probability of NEET status mainly among people high in Extraversion, who may be more likely to activate social networks and turn support into concrete opportunities.

100

Michele Scandola (He / Him) @scandle.bsky.social · 04/08/2026

A Strategic Future-Oriented Mindset—combining perceived employability, self-directed learning, and future-oriented beliefs—was associated with a lower probability of NEET status, especially at low or average levels of Honesty–Humility.

100

Michele Scandola (He / Him) @scandle.bsky.social · 04/08/2026

The central finding: personality traits do not appear to operate in isolation. Their associations with NEET status depended on psychological resources, education, and, in some cases, sex. A person–context perspective may therefore be more useful than a fixed personality profile.

100

Michele Scandola (He / Him) @scandle.bsky.social · 04/08/2026

The study involved 254 young adults: 75 classified as NEET and 179 as non-NEET. Researchers assessed HEXACO personality traits, perceived employability, self-directed learning, future orientation, mental health, social support, education, age, and sex.

100

Michele Scandola (He / Him) @scandle.bsky.social · 04/08/2026

There does not appear to be a single “NEET personality profile.” Our new preprint examines how personality traits, psychological resources, and sociodemographic conditions combine in their association with disengagement from employment, education, and training.

100

Michele Scandola (He / Him) @scandle.bsky.social · 21/07/2026

Yes, we know... We read YOUR guidelines <3 XD

130

Michele Scandola (He / Him) @scandle.bsky.social · 21/07/2026

I hope I am not getting lost here; if I am, please tell me. To the best of my understanding, the formulation `(1 | g) + (1 | g:f)` is not redundant, whereas `(1 | g) + (1 | g/f)` is redundant. So, no, we did not discuss redundancy.

120

Michele Scandola (He / Him) @scandle.bsky.social · 19/07/2026

Correct—there are no heterogeneous correlations. I suppose every simulation study will always be at least one simulation short XD

030

Michele Scandola (He / Him) @scandle.bsky.social · 19/07/2026

I personally agree in using by default maximum slope models, and only if they fail use CRIs. This is exactly our suggestion. I think that what you really lose is the opportunity to study and make inferences on the random effects.

020

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

We believe that using BMSC and EBMSC together can support a more flexible approach to single-case analysis, while reducing the risk of false inferences. The article was written in R Markdown for reproducibility and Open Science. doi.org/10.31234/osf...

doi.org

OSF

000

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

EBMSC is not free from limitations. In particular, it may be more difficult for the Bayes Factor to correctly identify the null hypothesis, that is, no difference between the single case and the control group.

100

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

The advantages are twofold. First, interpretation is more straightforward, because the analysis does not depend on the researcher’s prior beliefs. Second, the prior distribution no longer needs to be chosen externally.

100

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

In the new preprint, we propose EBMSC: Empirical Bayesian Multilevel Single Case models. Here, the single case is studied using Bayesian statistics, but the prior is directly derived from the control group data.

100

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

Second, choosing a prior distribution can be difficult for researchers in neuropsychology who are not experienced in Bayesian statistics. This is a practical problem, not only a theoretical one.

100

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

This can be problematic for at least two reasons. First, interpretation becomes less direct: the result does not simply reflect the difference between the single case and the control group.

100

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

This prior distribution depends on the researcher’s beliefs or previous knowledge. As a consequence, the Bayes Factor reflects not only the difference between the single case and the control group, but also the chosen prior.

100

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

In previous work, we proposed Bayesian Multilevel Single Case models, or BMSC. In BMSC, control group data and single-case data are analysed starting from a common a priori distribution.

100

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

Single-case analysis is central in neuropsychology, especially when we need to assess whether one patient differs from a control group. The statistical question is simple in principle, but difficult in practice.

100

Michele Scandola (He / Him) @scandle.bsky.social · 14/07/2026

New preprint with Sylia Makhloufi: Single case analysis in neuropsychology: an Empirical Bayesian perspective We propose a new methodology based on Bayesian Linear Mixed Models to analyse single-case data in neuropsychology. doi.org/10.31234/osf...

doi.org

OSF

100

Michele Scandola (He / Him) @scandle.bsky.social · 10/07/2026

Across four simulation studies, we show that Complex Random Intercepts can preserve important dependency structures while improving convergence and reducing computational demands in Bayesian LMMs.

110

Michele Scandola (He / Him) @scandle.bsky.social · 10/07/2026

The problem is that removing random effects can also remove important information about how observations are grouped. This may lead to overconfident conclusions.

110

Michele Scandola (He / Him) @scandle.bsky.social · 10/07/2026

However, specifying the random-effects part of these models can be difficult. When models become too complex, researchers often simplify them by removing some random effects.

110

Michele Scandola (He / Him) @scandle.bsky.social · 10/07/2026

In many areas of experimental research, data are not independent. Observations often come from the same participants, the same stimuli, or both. Linear Mixed Models are commonly used to account for this structure.

110

Michele Scandola (He / Him) @scandle.bsky.social · 10/07/2026

We are now happy to share the pre-print of our new article, where we extend this approach to Bayesian Linear Mixed Models: *Complex Random Intercepts in Bayesian Linear Mixed Models for fully crossed experimental designs* doi.org/10.5281/zeno...

doi.org

Complex Random Intercepts in Bayesian Linear Mixed Models for fully crossed experimental designs

Bayesian Complex Random Intercepts in Linear Mixed Models This Zenodo repository contains the preprint article "Bayesian Complex Random Intercepts in Linear Mixed Models", by Michele Scandola and Emma...

110

Michele Scandola (He / Him) @scandle.bsky.social · 07/10/2025

Join us for the 5th Annual Meeting of the Italian Reproducibility Network “The Present of Research is Open” Registrations are now open! tinyurl.com/ITRN2026 🗓️ Feb 13, 2026 – Verona 🛠️ Workshop on Feb 12 🌍 International speakers 🧪 Posters & prizes! #OpenScience #ITRN2026

151

Michele Scandola (He / Him) @scandle.bsky.social · 23/09/2025

🌍 How has #OpenScience changed your work or vision of science? Share your story in a short video (🎥) or text+photo 📝 and inspire others! ➡️ Submit here: shorturl.at/w31dH or here: shorturl.at/7Ktgd ✨ Testimonials will be shown at #ITRN2026 in Verona!

010

Michele Scandola (He / Him) @scandle.bsky.social · 31/07/2025

8/ We’d love to hear your thoughts! 💬 Join the conversation: How are you addressing replicability in AI-enhanced research? 📄 Read the pre-print: osf.io/preprints/os... #OpenScience #Reproducibility #AI #SocialRobotics #ITRN

osf.io

OSF

011

Michele Scandola (He / Him) @scandle.bsky.social · 31/07/2025

7/ Authored by: Antonio Aquino, Fabio Aurelio D’Asaro, Rocco Gaudenzi, Marco Lezcano, Vittorio Iacovella, Michela Vezzoli, and Michele Scandola 🧠 ITRN AI Working Group

100

Michele Scandola (He / Him) @scandle.bsky.social · 31/07/2025

6/ Though rooted in social robotics, this framework applies to any AI-driven experimental research, especially in the social sciences.

100

Michele Scandola (He / Him) @scandle.bsky.social · 31/07/2025

5/ To address this, we offer a framework based on Open Science: ✅ Modular testing ✅ Parameter fixation ✅ Structured prompt engineering ✅ Robust experimental design

100

Michele Scandola (He / Him) @scandle.bsky.social · 31/07/2025

4/ This raises new challenges: 🤖 Adaptive AI behavior 🎭 GAN-generated facial expressions 💬 Emotionally expressive chatbots All can undermine experimental control.

100

Michele Scandola (He / Him) @scandle.bsky.social · 31/07/2025

3/ We propose a new experimental model: 🔁 Experiment-AI-Subjects Triad (EAIST) AI becomes part of the experimental loop, generating stimuli and conditions.

100

Michele Scandola (He / Him) @scandle.bsky.social · 31/07/2025

2/ Generative AI is reshaping experimental research. But how do we ensure replicability when AI introduces randomness and variability?

100

Michele Scandola (He / Him) @scandle.bsky.social · 31/07/2025

🧵1/ 🚨 New pre-print from the ITRN AI Working Group! "AI in the Experimental Loop: Implications for Replicability in Social Robotics and Social Sciences" 📄 osf.io/preprints/os...

osf.io

OSF

100

Michele Scandola (He / Him) @scandle.bsky.social · 09/07/2025

6/ Bottom line: ADHD is not just a core symptom diagnosis—it clusters with distinct comorbidity profiles. These profiles are shaped by familial psychiatric history and environmental risk. 🧠 We argue for a nosology of ADHD that reflects this complexity.

100

Michele Scandola (He / Him) @scandle.bsky.social · 09/07/2025

5/ Notably: 👩 Mothers with ADHD influenced the Tic-Autism vs. Bipolar group only when siblings had lower ADHD rates. 🏠 High negative parenting & lower FDR neurodevelopmental disorders were linked to profile 4 (ODD vs. SLD).

100

Michele Scandola (He / Him) @scandle.bsky.social · 09/07/2025

4/ We looked at family mental health: ✅ Psychiatric disorders in FDRs had a direct effect on Anxiety-Depression-CD (profile 1). ✅ ADHD in siblings + negative parenting affected multiple profiles. ✅ Proband’s age and overlap between profiles gave further insight.

100

Michele Scandola (He / Him) @scandle.bsky.social · 09/07/2025

3/ Some comorbidities were mutually exclusive—like Tic/Autism vs. Bipolar in group 3 and ODD vs. Learning Disorders in group 4. These “contraposed” profiles suggest different developmental pathways.

100

Michele Scandola (He / Him) @scandle.bsky.social · 09/07/2025

2/ Comorbidities grouped into 4 main profiles: 1. Anxiety, Depression & Conduct Disorder 2. Intellectual Disability, Specific Language Disorder & Coordination Disorder 3. Tic/Tourette & Autism vs. Bipolar Disorder 4. Oppositional Defiant Disorder vs. Specific Learning Disorders

110

Michele Scandola (He / Him) @scandle.bsky.social · 09/07/2025

1/ We studied comorbidities in 1,086 individuals with ADHD and explored how first-degree relatives’ (FDRs) mental disorders and socio-environmental factors influence these patterns. What we found suggests ADHD is not one-size-fits-all. Here's what we learned 👇

100

Michele Scandola (He / Him) @scandle.bsky.social · 09/07/2025

We’re very happy to share our new publication: "Comorbidity aggregation models in children and adolescents with ADHD and direct and moderator effects of familial clinical history and psychosocial factors" 🧵Thread 👇

110

Michele Scandola (He / Him) @scandle.bsky.social · 28/05/2025

🚨Call for Papers!🚨Share your knowledge of cutting-edge neuropsychological techniques in the Journal of Neuropsychology (@BPSOfficial @WileyPsychology) SI “Neurotutorials: Advances in Neuropsychological Methods Made Simple”. tinyurl.com/3yjvmncc #Neuropsychology #Neuroscience

tinyurl.com

Journal of Neuropsychology | Wiley Online Library

Journal of Neuropsychology is an international neuroscience journal publishing original contributions in both experimental and clinical neuropsychology.

010