Skip to content
datanalyze Statistics & data science
Language FR EN
Get in touch
Services Training About Get in touch
Language FR EN

Service

Support for researchers

You want to stay in control of your own analysis, but be certain the method holds. I support you at the moments that matter: the choice of model, the difficult calls, and the response to reviewers.

Discuss your project
01

Who it is for

This service is for those who do the analysis themselves — by preference, by academic requirement or by budget — and who want a statistician beside them rather than instead of them.

  • PhD students mid-thesis, in any discipline
  • Postdocs preparing a submission
  • Doctors running a clinical or retrospective study
  • Master's students with a quantitative component
  • Research teams with no dedicated statistician
  • Researchers facing a harsh review report
02

The problem it solves

In most academic paths, statistics is taught once, early on, using clean examples. Then you find yourself alone with real data: unbalanced groups, missing values, repeated measures, variables that follow no normal distribution.

The classic mistake is not miscalculating. It is choosing a test designed for a different situation than yours, and only realising it when the reviews come back — once collection is over and it is too late to change the study design.

Support up front is almost always cheaper than repair downstream.

  • You are torn between several tests and cannot decide
  • Your supervisor asks you to "justify the model"
  • A reviewer demands a correction for multiple testing
  • You do not know how to handle your missing data
  • Your results are significant but you doubt they hold
  • Your jury will ask about method and you want to be ready
03

What you get

The aim is not only to unblock the current point, but to make you self-sufficient on the next ones.

  • Test justifications you can lift straight into your methods section
  • The model that fits the structure of your data
  • A critical review of your statistics section
  • Reasoned answers to reviewers' comments
  • Your software output interpreted, line by line
  • Your R scripts reviewed, corrected and commented
04

How it works

  1. First contact

    You set out your project and where it is stuck. I tell you frankly whether I can help.

  2. Scoping

    We agree on the format: one-off on a single question, or ongoing across the study.

  3. Working together

    Working sessions on your data, with the explanations that go with them. You keep control.

  4. Autonomy

    You leave with the written justification and the understanding needed to defend your choices.

05

Concrete examples

The most frequent requests, as methodological illustrations.

Choosing the right test

Two groups, small samples, skewed distribution: t-test, Wilcoxon, or a permutation test? A reasoned, checkable decision.

Repeated measures

The same subjects measured at several time points. Standard tests become invalid; you need a model that accounts for the dependence.

Answering a reviewer

"The statistical analysis is inadequate." A precise diagnosis of the objection, the correction, and the written response.

Correcting for multiple testing

Twenty comparisons, and one comes out "significant" by chance. Which correction to apply, and when it is not needed.

Missing data

Dropping incomplete rows often biases the results. Choosing between complete-case analysis, imputation, or a robust model.

Preparing your defence

Anticipating a jury's methodological questions and answering them without contradicting yourself.

Frequently asked questions

When is the best time to contact you?
This service covers the phase where you have your data and you are analysing it. If collection has not started yet, what you want is study design: that is the only moment when the design, the variables and the sample size are still fixable. Most requests do arrive mid-analysis or after a review, though, and there is almost always something to be done.
Do you run the analysis for me?
Not under this service: here you keep control and I secure the method. If you would rather delegate entirely, the data analysis service is the one you want.
Can I consult you about a single question?
Yes. Many requests are settled in one session: a choice of test, an interpretation of output, a review of a methods section. There is no minimum duration.
Do you work with software other than R?
Methodological advice does not depend on the software: I can support you whether you work in SPSS, Stata, SAS, Python, Jamovi, JASP, JMP or Excel. When it comes to writing or reviewing code, though, I do that in R.
My field is not medical. Is that a problem?
No. My own research was mostly in biostatistics and actuarial science, but the methods carry across: social sciences, economics, biology, engineering, marketing. What matters is the structure of your data and your question, not the label on the discipline.

Other services

Data analysis

You have the data, I produce the results

Learn more

Study design and sample size

Design it right before you collect

Learn more

Consulting and decision support

From dormant data to evidence-based decisions

Learn more

R development and automation

An analysis that runs itself, identically

Learn more

Training

Making your teams self-sufficient in R and data analysis

Learn more

A dataset to analyse, a method to validate?

Describe your need in a few lines, or book a first no-commitment call. I will tell you straight if I am the right person for it.

Describe my need Book a call