Free tool
Table 1 generator
Paste your data. Get the baseline characteristics table by group, with the right test for each row, ready to paste into Word.
Make your Table 1 from your data
Paste your data from Excel, SPSS Data View or a CSV file: one row per participant, column names in the first row. You get n (%) and mean (SD) or median (IQR) for each group, with the right test for each row.
Read by fixed rules, not an AI model. Remove names and other identifiers before pasting; we do not keep the data.
What belongs in Table 1 and how journals format it is in the guide on how to make Table 1.
Questions
Which test does each row use?
Categories: Pearson's chi-square, or Fisher's exact test for a 2 x 2 table with an expected count below 5, or a Monte Carlo exact test for larger tables with small counts. Continuous columns: Welch's t test or one-way ANOVA with mean (SD); Mann-Whitney U or Kruskal-Wallis with median (IQR). The note under the table names the tests used.
Should Table 1 of a randomised trial have p-values?
No. CONSORT advises against testing baseline differences in a randomised trial: randomisation makes any difference chance by design. Untick Show p-values. In an observational study, p-values in Table 1 are common.
Mean (SD) or median (IQR)?
Mean (SD) for roughly symmetric variables; median (IQR) for skewed ones, such as length of stay or income. Many journals ask for the choice to be stated in the note, which the table does.
Is my data kept?
No. It is read by fixed rules, not an AI model, and not stored. Remove names and other identifiers before pasting all the same.