What a strong statistical analysis section should do

Start with data summarization

The section should begin by describing how the data were summarized. Continuous variables should be reported using means and standard deviations or medians and interquartile ranges, depending on their distribution. Categorical variables should be presented as counts and percentages.

Define the primary outcome and main exposure

Next, the primary outcome and main exposure or predictor should be clearly defined. This helps the reader understand exactly what relationship the study is testing.

Match tests to the type of data

The statistical tests should then be matched to the type of data. For example, categorical variables may require chi-square tests, while continuous variables may require t tests or non-parametric alternatives. A strong section also explains the main model used, such as linear regression, logistic regression, Cox regression, or another appropriate model.

Report adjustment variables

Good statistical writing also includes adjustment variables. These are the confounders or covariates included in the model, such as age, sex, baseline severity, comorbidities, or other clinically relevant factors.

Address missing data, sensitivity, and subgroups

A complete statistical analysis section should also address missing data, sensitivity analyses, subgroup analyses, and interaction testing when appropriate. These details show whether the results remain stable under different assumptions.

Report significance, software, and reproducibility

Finally, the section should report the threshold for statistical significance, confidence intervals, the software used, and any reproducibility measures such as code review or independent verification.

Annotated checklist

A strong statistical analysis section typically covers:

• Data summary — how continuous and categorical variables are described
• Key variables — primary outcome and main exposure defined clearly
• Choice of tests — methods matched to data type and distribution
• Main model — regression approach and key covariates for adjustment
• Assumption checking — how model assumptions were evaluated
• Missing data — how incomplete records were handled
• Sensitivity analysis — robustness under alternative approaches
• Subgroups / interaction — predefined group and interaction testing
• Significance & reproducibility — P values, confidence intervals, software, code review

Click to enlarge

In short

A strong statistical analysis section does not just say which tests were used.

It shows why those tests were appropriate, how the models were built, and how the reliability of the findings was checked.

For broader manuscript structure, see our how to write a scientific paper guide—or run a pre-submission review that flags statistical reporting gaps.