Clinical & Epidemiological Data Analysis

Statistical support from protocol through to the methods section — and the sample size calculation done before recruitment, not after.

The most valuable statistical work happens before any data exists. A study powered for the wrong effect size, or with a design that cannot separate the exposure from a confounder, cannot be rescued by analysis afterwards.

We work with investigators at protocol stage as readily as at analysis stage, and we write the statistical analysis plan before the data is unblinded.

Data We Accept

  • Study protocol or draft protocol for design support
  • REDCap, ODK or KoboToolbox exports
  • Excel, CSV or Stata, SPSS and SAS datasets
  • Routine health information system or surveillance extracts
  • Data dictionary and any existing analysis plan

Questions We Answer

  • How many participants do I need, and to detect what effect?
  • Does the intervention work after adjusting for the confounders that matter?
  • How do outcomes differ over time between arms?
  • What is the incidence in this population, and how does it compare?
  • How should I handle the missing data in my cohort?

What We Do

Each project uses the subset of these that your research question requires.

01

Study Design and Sample Size

Power and sample size calculation for parallel, cluster, crossover and stepped-wedge designs, randomisation schedules, and advice on measurement and follow-up strategy.

02

Statistical Analysis Plans

A pre-specified plan naming the primary and secondary outcomes, estimands, models, covariates, subgroups, missing data strategy and multiplicity approach — written before unblinding.

03

Data Cleaning and Preparation

Reproducible cleaning from raw export to analysis dataset, with every recode and exclusion documented and an auditable trail from source to result.

04

Regression and Survival Modelling

Linear, logistic, Poisson and negative binomial regression, mixed-effects and GEE models for clustered or repeated data, Cox and competing risks survival analysis.

05

Epidemiological Analysis

Incidence and prevalence estimation with appropriate confidence intervals, standardisation, risk and rate ratios, matched case-control analysis, and outbreak epidemic curves.

06

Reporting and Publication Support

CONSORT, STROBE and PRISMA-aligned tables and flow diagrams, forest and Kaplan-Meier plots, and a methods section drafted with you.

What You Receive

  • Statistical analysis plan and sample size justification
  • Cleaned analysis dataset with a documented derivation trail
  • Model outputs with effect estimates and confidence intervals
  • Publication-ready tables including baseline characteristics
  • Forest, Kaplan-Meier and diagnostic plots
  • Reproducible R or Stata code and a manuscript methods section

Tools We Use

  • R (tidyverse, survival, lme4, gtsummary)
  • Stata
  • REDCap and ODK export handling
  • Power analysis: G*Power, PASS methodology, simulation
  • meta and metafor for evidence synthesis

Typical turnaround: 1–2 weeks for design and sample size; 3–6 weeks for full trial or cohort analysis

Indicative price: From $399 for sample size and analysis plan; project-quoted for full analysis

Reduced rates are available for students and researchers at African public institutions. Every project is quoted in writing before work begins.

Services are provided for research purposes only. They are not intended for clinical diagnosis, treatment decisions or individual health assessment. See how it works, data submission guidelines and what you receive.

Contact DataCore Analytics

Tell us about your data and we will scope it — free, within one working day.

+233 558 017 827