Psychiatry and psychology research groups
You have imaging, questionnaire or digital data and need an analysis you can defend.
Mental Health & Biomarkers
Study design and statistics for mental-health research: imaging and digital biomarkers, sleep and circadian measures, symptom scales and treatment outcomes.
Who this is for
Teams we help in this field.
Digital mental-health teams
You collect app, sleep or wearable data and need to show what it measures.
Graduate students and postdocs
You face a methods decision or reviewer comment on a mental-health study.
Audiences we welcome, not a list of clients.
Questions we help answer
What teams in this field ask us.
- Is our imaging or digital measure a useful biomarker, or just a correlate?
- How many participants do we need to detect a difference between groups?
- How do we analyze symptom scales measured repeatedly over time?
- Do sleep or chronotype measures explain part of our result?
- How do we handle drop-out, which is common in mental-health studies?
- Are our findings robust to medication, age and sex?
What you receive
- A written analysis plan: outcomes, covariates, models and checks agreed before analysis starts.
- A biomarker evaluation: association, prediction and reliability, each with confidence intervals.
- Longitudinal outcome analysis: symptom scales over time, with missing data handled openly.
- Methods and results text: written so a reviewer can follow every step.
- Reproducible code: R or Python, with the software environment recorded.
Methods we use
The methods specialists ask about.
- Mixed-effects models
- Repeated-measures symptom scales
- MRI morphometry
- Sleep and circadian measures
- Multiple imputation
- ROC and calibration
- Multiple-comparison control
- Cross-validation
Evidence
How our published methods apply.
Neuroanatomical signatures of chronotype in young adults
Linked chronotype, a circadian trait tied to mood and sleep, to brain anatomy in young adults.
Read the paper (external site)Advancements and challenges in using AI for biomarker detection in early Alzheimer's disease
Reviewed where AI biomarkers stand for early Alzheimer's disease, and what makes a biomarker trustworthy.
Read the paper (external site)Predicting Brain Age Using Machine Learning Algorithms: A Comprehensive Evaluation
Compared prediction methods on data they had not seen, the test any biomarker model must pass.
Read the paper (external site)The founder was a researcher at Japan's National Center of Neurology and Psychiatry. We have not published a psychiatric treatment trial; these papers show the methods we use.
Boundaries
Research analysis only. We do not assess, diagnose or treat anyone, and this site is not a crisis or patient service. Data arrive de-identified and are used only under your data-use agreement.
Packages that fit
Start at the right scale.
The same packages and prices on every page. Each starts with a written scope.
Research Diagnostic
Fixed priceCAD 495
- 60-minute video call
- Two-page risks and next-steps memo
- Optional 30-minute debrief
Paid in full at booking.
Memo within 5 business days of the call.
Ask about thisAnalysis Plan Sprint
Fixed priceCAD 1,250
- Analysis and validation plan
- Scoped sample-size or power calculation
- Methods text or reviewer response
50% to start; 50% on delivery.
Delivery date agreed in the written scope.
Ask about thisData-to-Results Sprint
FromCAD 3,000
- Agreed analysis and quality-control log
- Figures, tables and methods text
- R or Python code and recorded environment
50% to start; 50% on delivery.
Final price and delivery date agreed after scoping.
Ask about thisRelated
Go deeper.
Questions
About working in mental health & biomarkers.
Do you work with clinical trial data in mental health?
Exploratory and research analyses, yes. For a regulated trial, the sponsor's statistician of record remains responsible.
Can you analyze app or wearable data?
Yes, as a de-identified export with documentation of how it was collected. We agree the format and quality rules first.
Can a biomarker diagnose a mental-health condition?
We do not make that claim. We report how well a measure separates groups or predicts outcomes, with its limits.
How do you handle missing questionnaire data?
We choose a method such as multiple imputation or mixed models and explain why it suits your data.
Can you help answer reviewers?
Yes. We draft the statistical part of your response and any extra analysis, with the reasoning a reviewer can check.
Who owns the code and results?
You do, once the invoice is paid, unless the written scope says otherwise.
Discuss a mental health project.
Start with a short, non-confidential description. We reply with a suggested next step.