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 thisStudy design & biostatistics
A defensible analysis plan, a justified sample size and statistics a reviewer can follow, for research teams in health and life sciences. Starting at CAD 495.
Typical questions
What teams bring to us.
- Which outcomes, comparisons and covariates belong in our analysis plan?
- How many participants do we need, and how do we justify it to a funder?
- How should missing data, repeated visits and multiple comparisons be handled?
- How do we answer a reviewer who questions our statistics?
- How do we design a reliability, agreement or pilot evaluation study?
- Is our planned analysis appropriate for the data we will actually have?
What you receive
- Statistical analysis plan: PDF and editable Word file: outcomes, models, covariates, missing-data rules and sensitivity analyses, written before the analysis starts.
- Sample-size justification: a short report with every assumption stated, a sensitivity table, and simulation code where formulas do not fit the design.
- Methods text: ready to paste into a protocol, grant application or ethics submission.
- Reviewer response: the statistical part of your response letter, with any extra analysis the reviewer asked for.
- Results package: where analysis is in scope: tables, figures, results text and reproducible R or Python code.
Exact deliverables are agreed in writing.
How it works
From first call to handover.
- 01
First call
30 to 60 minutes to understand the question, data and deadline.
Week 1
- 02
Written scope
deliverables, fee, timeline and data arrangements agreed in writing.
Within 2 business days of the call
- 03
Draft
analysis plan or sample-size report delivered for your comments.
Typically 1 to 2 weeks
- 04
Revision and handover
one round of revisions, final files and a short debrief call.
Typically 1 week
Durations are typical; the written scope sets the actual dates.
What we need from you
Enough to start well.
- A short description of the study question and design (a page is enough to start).
- A data dictionary or list of variables, or a description of the data you will collect.
- Ethics or data-use approval status, if data already exist.
- Your deadline (grant, ethics board, journal) and one named contact person.
Please do not send patient information or identifiable data. How we handle data
Methods and quality checks
How results are checked.
- Power and sample size
- Simulation-based power
- Mixed-effects models
- Survival analysis
- Multiple imputation
- Multiplicity control
- Equivalence testing
- Bayesian sensitivity analysis
Every analysis is run from code, not by hand. Results are reproduced from a clean environment before delivery, key decisions are logged, and the main findings are checked with sensitivity analyses that vary the assumptions most likely to matter.
Evaluation studies
Validation and evaluation studies.
Planning a study to show how well a test, device or digital tool performs? We design and analyze reliability, agreement, accuracy and pilot evaluation studies: sample size, acceptance criteria, analysis plan and report. We do not certify products or prepare regulatory submissions.
- Reliability (ICC)
- Agreement (Bland–Altman)
- Accuracy (ROC, calibration)
- Equivalence and tolerance intervals
Fields we apply this in
Areas that use this service.
Boundaries
This service does not include data collection, regulated GCP or 21 CFR Part 11 delivery, acting as statistician of record for a regulated trial, or full-service grant writing. No publication, funding or positive-result guarantee.
Price and what changes it
Start at the right scale.
Analysis 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 thisWhat makes a project larger
- The number of outcomes and comparisons in the plan.
- Whether the design needs simulation rather than a standard formula.
- How much analysis, not only planning, is in scope.
- Deadlines shorter than the usual timeline.
- The number of review rounds with co-authors or reviewers.
Questions
About study design & biostatistics.
What do you need from us to start?
A short, non-confidential description of the study question and design is enough for a first call. A data dictionary helps. Do not send participant data before a written agreement is in place.
Can you calculate sample size before data exist?
Yes. That is the most common case. We use published estimates or pilot data, state every assumption, and show how the number changes if the assumptions are wrong.
Do you write the analysis plan for ethics or registration?
Yes. The plan can be formatted for an ethics submission, a trial or study registry, or a grant application. You remain the author of record for the protocol.
Can you answer statistical reviewer comments?
Yes, as a scoped task. We draft the statistical response and run any extra analysis the reviewer asked for. Journal acceptance is never guaranteed.
Which software do you use, and do we get the code?
Mainly R and Python. Where analysis is in scope, you receive the code and a record of the software versions, so your team can rerun every number.
Can you help with a device or digital-test evaluation study?
Yes. See the section on validation and evaluation studies on this page. We design and analyse reliability, agreement, accuracy and pilot studies; we do not certify products or prepare regulatory submissions.
Does an Analysis Plan Sprint include running the outcome analysis?
No. Outcome-data analysis belongs in a separately scoped Data-to-Results Sprint. This keeps the plan independent of the results.
Let us define the evidence your study needs.
Start with a short, non-confidential description. We reply with a suggested next step.