Paste or upload your dataset and get a publication-ready baseline characteristics table. The tool detects continuous and categorical variables, summarizes each by group as mean (SD), median [IQR], or n (%), runs the correct comparison test, and exports an APA-formatted Word table.
Header row required. Comma or tab separated. The first column defines the groups (2 to 6). Numeric columns with many distinct values are treated as continuous; everything else as categorical. Showing example data until you paste your own.
Drag & drop a file or
CSV, TSV, Excel (.xlsx/.xls) - max 500 rows
| Characteristic | Treatment n = 8 | Control n = 8 | Overall n = 16 | p |
|---|---|---|---|---|
| age, mean (SD) | 55.3 (6.3) | 57.8 (7.0) | 56.5 (6.6) | .467 |
| sex, n (%) | > .999 | |||
| M | 4 (50.0%) | 4 (50.0%) | 8 (50.0%) | |
| F | 4 (50.0%) | 4 (50.0%) | 8 (50.0%) | |
| bmi, mean (SD) | 27.5 (2.9) | 28.3 (2.6) | 27.9 (2.7) | .595 |
| smoker, n (%) | > .999 | |||
| Yes | 3 (37.5%) | 4 (50.0%) | 7 (43.8%) | |
| No | 5 (62.5%) | 4 (50.0%) | 9 (56.3%) |
Continuous variables: mean (SD) or median [IQR]; categorical: n (%). Tests: t-test, Fisher's exact. Percentages are within-group and exclude missing values. For randomized trials, consider whether baseline p values belong (CONSORT discourages them).
A baseline characteristics table, universally called Table 1, is the first table in almost every clinical, epidemiological, and social-science paper. Its job is to describe the sample and show whether the study groups were comparable before any intervention or exposure. Each row is a variable; each column is a group, usually with an overall column and the group sizes in the headers. Continuous variables are summarized as mean and standard deviation when roughly symmetric, or median and interquartile range when skewed; categorical variables are summarized as counts and within-group percentages. The choice of summary is not cosmetic: reporting a mean for a heavily skewed variable such as length of stay or income misrepresents the typical value, which is why this tool checks skewness and switches to the median automatically.
The p-value column is where Table 1 causes the most trouble. In an observational study, comparing baseline characteristics between groups can be informative. In a randomized trial, however, any baseline difference is by definition due to chance, so a baseline p-value tests a null hypothesis that is known to be true; the CONSORT guidelines and many leading journals therefore discourage baseline significance tests in trials. This generator computes them because reviewers at some journals still request them, but it flags the caveat, and it never uses a baseline p-value to decide which covariates to adjust for, a common and statistically indefensible practice.
Next step
Baseline balance, the primary and adjusted analyses, effect sizes, and a publication-ready results section, handled end to end.
Our promise: Free re-run and re-write if reviewers question the analysis or reporting.
Timeline
Most projects deliver in under 2 weeks. We confirm an exact date in your quote.
If reviewers push back
If reviewers question the analysis, assumptions, or reporting, we re-run and re-write free.
Confidentiality
NDA available on request before any project discussion. Your data, study design, and manuscript stay private either way.
Want a PhD methodologist to handle the whole project?
Get a complete systematic review or meta-analysis handled end-to-end. Free rework on search, screening, or synthesis if reviewers push back. Pay only after you approve your quote.
The tool classifies each variable, then matches it to the right summary and test. A continuous variable (numeric with many distinct values) is summarized as mean (SD), or median [IQR] when its distribution is skewed. Its groups are compared with an independent-samples t-test for two groups or a one-way ANOVA for three or more; when the median summary is used, the rank-based Mann-Whitney U or Kruskal-Wallis test is applied instead so the test matches the summary. A categorical variable is summarized as n (%) per level, and its groups are compared with a chi-square test of independence, automatically switching to Fisher's exact test when any expected cell count falls below 5.
Every choice is stated in the table so your methods section can reproduce it, and the continuous-summary style is overridable if your field has a convention. The percentages are computed within each group and exclude missing values, which is the standard for a Table 1; the tool reminds you to describe how missing data were handled. For the underlying tests themselves, the individual calculators are one click away: the t-test calculator, the chi-square calculator, and the ANOVA calculator each give the full test output with an APA write-up.
Table 1 reports the baseline characteristics of the sample, one row per variable, split into columns by study group. Continuous variables are summarized as mean (standard deviation) or, when skewed, median [interquartile range]; categorical variables as count (percentage). An overall column and, where the journal expects it, a p-value column comparing groups complete the table. Table 1 describes the sample and shows whether groups were comparable at baseline; it is not where the study hypothesis is tested.
List each characteristic as its own row, grouped logically (demographics, then clinical variables), with the summary statistic format stated in the row label, such as 'Age, mean (SD)' or 'Sex, n (%)'. Put group sizes in the column headers, keep decimals consistent (usually one for means, whole numbers for counts), and describe the tests and any missing-data handling in a table note. This generator builds that structure automatically and exports it to Word with APA formatting.
The five descriptive statistics most often taught are the mean (average), the median (middle value), the mode (most frequent value), the standard deviation (spread around the mean), and the range or interquartile range (spread of the data). A Table 1 uses the mean and standard deviation together for symmetric continuous variables, the median and interquartile range for skewed ones, and counts with percentages for categorical variables.
In text, report the mean and standard deviation as M = 24.3, SD = 4.1 (both italicized in APA style, without leading zeros where the value cannot exceed one). For a skewed variable, give the median and interquartile range instead. When there are many variables, a Table 1 is clearer than prose: describe the table in one or two sentences and let the table carry the numbers. This tool produces both the table and a citation-ready describing paragraph.
In R the tableone package (CreateTableOne) or gtsummary (tbl_summary) build a Table 1 from a data frame, choosing summaries and tests automatically. This browser tool does the same thing without any code: paste your data, and it detects continuous versus categorical variables, picks mean (SD) or median [IQR], runs t-tests, ANOVA, chi-square, or Fisher's exact as appropriate, and exports the finished table.
Not sure which comparison test your outcome needs? The statistical test selector walks you to the right one. For the full spread and shape of a single variable, the variance and descriptive statistics calculator adds skewness, kurtosis, and confidence intervals. When your studies report medians instead of means and you need to pool them, the median and IQR to mean and SD estimator converts them for meta-analysis.
Reviewed by
Dr. Sarah Mitchell holds a PhD in Biostatistics from Johns Hopkins Bloomberg School of Public Health and has over 15 years of experience in systematic review methodology and meta-analysis. She has authored or co-authored 40+ peer-reviewed publications in journals including the Journal of Clinical Epidemiology, BMC Medical Research Methodology, and Research Synthesis Methods. A former Cochrane Review Group statistician and current editorial board member of Systematic Reviews, Dr. Mitchell has supervised 200+ evidence synthesis projects across clinical medicine, public health, and social sciences. She reviews all Research Gold tools to ensure statistical accuracy and compliance with Cochrane Handbook and PRISMA 2020 standards.
From data cleaning and assumption checks to the full analysis and a publication-ready results section, we handle the numbers so you can focus on the science.
Our promise: Free re-run and re-write if reviewers question the analysis or reporting.