Psychological assessment
I assess the measurement quality, validity and fairness of psychological tests and assessments, examining whether a method suits the specific question and which conclusions its findings support.
DDR. MARTIN STEPPAN · BASEL
Expert reports
& advice
I provide scientifically grounded expert reports for individuals, companies, insurers and courts, as well as expert assessments in patent matters.
As an established expert in psychometrics and human data analysis with a particular focus on artificial intelligence I combine psychological knowledge with sound methodological expertise. My research is documented in more than 50 scientific publications .
My expertise covers psychological assessment, the use of AI in psychology and the evaluation of possible misuse of psychological tests and instruments.
Request an expert report
AI in psychology
I evaluate AI-based psychological methods for their scientific foundation, output quality, transparency and potential bias, including expert questions in patent matters.
Test use & possible misuse
I examine whether psychological tests and instruments have been appropriately used and interpreted, focusing on use beyond their intended purpose, insufficiently supported claims and possible misinterpretation.
REASONS TO REQUEST AN EXPERT REPORT
When an independent assessment can help.
An expert report can help evaluate a disputed assessment, understand decisions and clarify open questions against scientific criteria.
Do you question a psychological diagnosis?
If you feel misdiagnosed or inadequately represented in a psychological report, I review the methods used, the underlying data and the reasoning behind the conclusions, based on the available records.
Does a test or selection procedure misrepresent your abilities?
If an aptitude test, university admission process or recruitment procedure seems to misrepresent your abilities, I examine its interpretability and possible influences of language, norms or testing conditions.
Do you suspect inappropriate test use?
A psychological test may have been used beyond its intended scope, incorrectly scored or overinterpreted. I examine whether its use and the resulting claims have a scientific basis.
Is AI assessing personality, aptitude or behaviour?
If you want to know how robust an AI-based assessment is, I evaluate its validation, transparency and possible bias, as well as the limits of its psychological interpretation.
Would your company like an independent review of a method?
If you use or plan to introduce tests, assessments or AI tools, independent expertise can help assess their suitability, measurement quality and fitness for the intended purpose.
Do you need expertise for a court or patent matter?
Where a dispute or patent matter involves claims about psychological measurement or AI methods, I examine the scientific foundations, methods and expert claims, and present the findings transparently.
Describe your situation. We can clarify which expert questions can be examined and which documents are needed.
Discuss your questionMY RESEARCH APPROACH
Understanding human data across multiple levels.
My research approach uses multimodal multi-omics integration, linking statistical genomics (GWAS, SNPs) with digital phenotyping through biosignals (ECG, HRV, skin conductance), neuroimaging and AI-based emotion and behaviour analysis.
This approach describes the overall direction of my research. The following publications document individual methodological components, examining these data levels in separate studies.
Statistical genomics
Steppan, M. (2020). Pubertal timing and mental health. Understanding social and genetic determinants. Dissertation, University of St Andrews. Genetic correlations and Mendelian randomisation connect genetic data with longitudinal and social characteristics.
Read the St Andrews dissertationNeuroimaging
Raschle, N. M., Menks, W. M., Fehlbaum, L. V., Steppan, M., et al. (2018). Callous-unemotional traits and brain structure: Sex-specific effects in anterior insula of typically-developing youths. NeuroImage: Clinical, 17, 856–864. Structural MRI and voxel-based morphometry for investigating behavioural traits.
Read the neuroimaging studyBiosignals
Prätzlich, M., Oldenhof, H., Steppan, M., et al. (2019). Resting autonomic nervous system activity is unrelated to antisocial behaviour dimensions in adolescents. Journal of Criminal Justice, 65, 101536. Assessment of autonomic activity, including heart rate and heart rate variability.
Read the biosignal studyAI-based emotion analysis
Steppan, M., Zimmermann, R., Fürer, L., et al. (2024). Machine Learning Facial Emotion Classifiers in Psychotherapy Research: A Proof-of-Concept Study. Psychopathology, 57(3), 159–168. Automated facial expression analysis in recorded psychotherapy sessions.
Read the emotion recognition studyOur methodological contribution High Resolution Psychotherapy Research (Steppan & Birkhölzer, 2025) discusses multimodal analysis of speech, facial expression and gestures, and its research and clinical implications.
RESEARCH UNDERPINNING MY EXPERTISE
Scientifically assessing measurement quality and interpretability.
Designed study coverASSESSMENT · INTELLIGENCE
Language barriers in cognitive assessment
The IDS-2 study in children and adolescents with and without a migrant background demonstrates the importance of language demands for test fairness, supporting the need for language-free, culturally fair assessments.
The study concerns children and adolescents and does not validate a new language-free method.
Gantscheva, L., Steppan, M., & Grob, A. (2024). Investigating measurement invariance of the IDS-2 intelligence scales between migrant and non-migrant groups. Intelligence, 107, 101873.
Read the publication
Designed study coverDIGITAL TRACES · VALIDATION
Google search volumes as a complementary data source
The study compares Google search volume indices with survey data on cannabis use, examining the comparability of prevalence estimates across countries and regions.
Search volumes alone are too weak a basis for prevalence estimates. Combining them with other sources is essential.
Steppan, M., Kraus, L., Piontek, D., & Siciliano, V. (2013). Are cannabis prevalence estimates comparable across countries and regions? A cross-cultural validation using search engine query data. International Journal of Drug Policy, 24(1), 23–29.
Read the publication
Designed study coverPHYSIOLOGICAL DATA · MULTICENTRE STUDY
ECG data and autonomic activity
This European study examines heart rate, heart rate variability and other autonomic measures alongside behavioural dimensions, combining physiological data with multivariate analysis and adjustment for relevant covariates.
The examined associations disappeared after adjustment for covariates. Physiological signals do not allow simple inferences about behaviour.
Prätzlich, M., Oldenhof, H., Steppan, M., et al. (2019). Resting autonomic nervous system activity is unrelated to antisocial behaviour dimensions in adolescents: Cross-sectional findings from a European multi-centre study. Journal of Criminal Justice, 65, 101536.
Read the publicationPSYCHOMETRICS & ALGORITHMIC TEST DEVELOPMENT
Developing and shortening questionnaires systematically
Our LoPF-Q study examined the factor structure of a clinical questionnaire and used ant colony optimisation to develop a 20-item short form, combining psychometric modelling with algorithmic item selection.
Zimmermann, R., Steppan, M., et al. (2022). A DSM-5 AMPD and ICD-11 compatible measure for an early identification of personality disorders in adolescence – LoPF-Q 12–18 latent structure and short form. PLOS ONE, 17(9), e0269327. Shared first authorship.
Read the LoPF-Q studyWhat assessment do you need?
Describe the context, question and available documents. Together we can clarify the scope, intended use and professional requirements of the expert report.
Request expert advice by email