Statistician for medical researchers: survival analysis (Cox), logistic regression, ROC curves, meta-analysis and reviewer responses. PhD theses and Q1/Q2.
Statistics for clinical research that survives peer review in indexed journals
PhD theses, Q1/Q2 articles and reviewer responses in medicine, clinical trials, epidemiology and observational studies. Cox, logistic regression, ROC, meta-analysis and multilevel models: always with methodology that holds up to reviewer 2 and STROBE.
Almost every project comes in with one of these three pain points. If any sounds familiar, we are a fit.
You submitted the manuscript and reviewer 2 demands a logistic or Cox regression that wasn't in your plan. Major revision deadline ticking.
You have longitudinal follow-up with events (mortality, relapse, drop-out) and don't know whether the right model is Kaplan-Meier, Cox or competing risks.
The journal requires STROBE or CONSORT reporting with adjusted analyses, sensitivity, multiple imputation and specific comparisons. Everything must fit in weeks.
What any indexed medical journal expects. If your design isn't listed and is quantitative, get in touch: it almost always fits.
Survival curves, adjusted hazard ratios, proportional-hazards assumption, models for multiple events.
Models for binary outcomes, adjusted ORs, goodness of fit, model diagnostics.
AUC with 95% CI, curve comparison (DeLong), positive/negative predictive value, Youden index.
Forest plots, heterogeneity (I², τ²), random-effects models, publication bias (Egger, funnel) and meta-regression.
Intent-to-treat and per-protocol analyses, ANCOVA with baseline, mixed models for repeated measures, full CONSORT reporting.
Propensity score matching, confounder adjustment, non-random missing data and full STROBE reporting.
No clock running on your tab. We agree on scope, timeline and a fixed price upfront: no inflated hours, no surprise invoice at the end. Before delivery, every analysis goes through a careful review on my side: I rerun the code, re-check the assumptions and review tables and figures line by line. That's the part I obsess over: that what you receive is ready to defend without errors surfacing in peer review. If something out of scope appears, we discuss it before I touch it.
Illustrative example: forest plot with per-study odds ratios, 95% CI, heterogeneity (I²) and the pooled-effect diamond. The kind of figure I deliver ready for a systematic review or clinical article.
Free resources on the analyses that appear most in medical and clinical research.
Fill out the form telling me the design, the phase you are in and what the journal or supervisor demands. I respond within 24h with a tentative proposal.
Biostatistics and statistical consulting for health research · All services
Yes, under NDA when needed. I always recommend you send the data pseudonymized: I explain how to prepare it so GDPR is covered. Data is encrypted on my end and deleted after project completion.
Yes. I have worked with manuscripts submitted to journals that require STROBE (observational), CONSORT (trials) and PRISMA (systematic reviews). I deliver the full checklist, tables and flow diagram.
Many medical specialty trials publish with N of 50-100. The key is the analytical design: ANCOVA with baseline instead of change comparison, mixed models for repeated measures, confidence intervals alongside p-values, and transparent reporting of limitations.
It's one of the most requested services. I review the reviewer's letter, run additional analyses and help you draft the point-by-point response. Typical turnaround: 48-72h.