Xingyao (Doria) Xiao, Ph.D.
  • Home
  • About
  • Research
  • Publications
  • Blog
  • More
    • Talks
    • Teaching
    • Software & Demos
    • Projects
    • Contact

Xingyao (Doria) Xiao, Ph.D.

Email GitHub Google Scholar LinkedIn CV (PDF)

Welcome! I am a Research Fellow 2 at the Australian Council for Educational Research (ACER) in Melbourne. I develop statistical methods that make educational and psychological measurement more reliable, valid, and fair, particularly as AI enters the assessment pipeline.

Before joining ACER, I was a Postdoctoral Scholar at the Stanford University Graduate School of Education, where I worked on the LEVANTE Project with Ben Domingue, Mike Frank, and Nilam Ram.

My research bridges methodological innovation with practical assessment design and large-scale data analysis. I specialize in:

  • Statistical Psychometrics: multidimensional IRT (mIRT) and Many-Facet Rasch Models (MFRM)
  • Bayesian Modeling: longitudinal and latent variable models, including Growth Mixture Modeling (GMM)
  • AI-Integrated Measurement: evaluating ML-based scoring of constructed responses and the integration of LLMs into educational assessment
  • Large-Scale Assessment: scaling, linking, and technical evaluation for national and international assessment programs

Recent Highlights

  • Publication (October 2026): Recovering Accuracy From Miscalibrated Item Banks: Scoring Error Is Fixable, Selection Error Is Not (with Domingue, Ram, & Frank) in Educational and Psychological Measurement · DOI · Interactive demo
  • Publication (October 2026): Which Algorithm Hurts Most? Differential Associations of Task Allocation, Scheduling, and Performance Monitoring with Worker Well-Being across 27 EU Countries (with Cheng) in International Archives of Occupational and Environmental Health · DOI · Free full text
  • Preprint (2026): Enhancing Routing Fairness in Hybrid Scoring with Group-Conditional Coverage (with Xue & Cheng) · EdArXiv
  • Preprint (2026): How Far Can a Language Model Carry a Systematic Review? Preregistered Reliability Evidence from Screening to Measurement-Quality Coding (with Cheng) · MetaArXiv
  • Preprint (2026): Beyond Acceptance: A Pre-Attitudinal “Uninformed” Stage in Teachers’ Engagement with AI across 53 Education Systems (with Cheng) · EdArXiv

Full publication list

Recent Posts

When the DIC Goes Negative: A Parameterization-Invariant Fix

Why the classic DIC breaks down in latent variable models, and how a simple plug-in-free variant (DIC_i) fixes it: new paper with Sophia Rabe-Hesketh, now on arXiv.

Jun 10, 2026

New Publication: Reliability of Hybrid Human-ML Scoring Systems

I am pleased to share that our new paper, “Revisiting reliability with human and machine learning raters under scoring design and rater configuration in the many-facet Rasch…
Feb 1, 2026

New Publication: Trajectories of Depressive Symptoms During COVID-19

I’m very excited to share that our article,
“Trajectories of Depressive Symptom Among College Students in China During the COVID-19 Pandemic: Association With Suicidal…
Sep 15, 2025
No matching items

All posts

© 2026 Xingyao (Doria) Xiao

 

Built with Quarto