Turn raw answers into clean distributions fast. See totals, percentages, confidence ranges, and comparisons instantly. Download tables, share insights, and validate your survey results.
You can paste raw answers or enter counts like the sample below.
| Category | Count |
|---|---|
| Strongly agree | 42 |
| Agree | 58 |
| Neutral | 19 |
| Disagree | 12 |
| Strongly disagree | 9 |
| No answer | 3 |
This calculator turns raw answers or category totals into a frequency distribution. Each row includes count, proportion p_i = count_i / n, percent, and cumulative percent. Use trimming, case grouping, and blank removal to standardize messy exports from forms, chats, or incident notes. When Top N is enabled, remaining categories are consolidated into an Other row while totals stay unchanged. This is useful when you have dozens of labels.
Percent values describe how common each response is in the sample. Cumulative percent helps you see how quickly the table reaches 50 percent, 80 percent, or 95 percent of all responses. The summary also reports Shannon entropy in bits and Gini impurity. Higher entropy means a broader mix, while lower entropy signals strong convergence on one choice. Track these metrics monthly to compare stability across releases.
Every percent is an estimate that changes with sample size. The calculator uses the Wilson score interval, which behaves well for small n and for proportions near 0 or 1. Select 90, 95, or 99 percent confidence and the tool derives a z value. It returns lower and upper bounds, clipped to valid percentage limits. Overlapping intervals suggest differences may be inconclusive.
When you enter expected values, the calculator runs a chi square goodness of fit test. Expected inputs may be probabilities that sum to one, or counts that are normalized to n. The statistic is computed as sum over i of ( O_i minus E_i ) squared divided by E_i, with degrees of freedom k minus 1. A small p value indicates a meaningful deviation. Ensure expected counts are not extremely small for reliable results.
For numeric responses, the tool can bin values into ranges using Sturges, square root, or Freedman Diaconis rules, or your custom bin count and limits. The summary reports how many numeric entries were used, plus mean and median. Set custom minimum and maximum bounds to control outliers. Export as CSV for spreadsheets, or as PDF for reports, audits, and dashboards.
Paste values separated by new lines, commas, tabs, or semicolons. You can also switch to category counts and enter labels with integers. Cleanup options let you trim spaces, ignore blanks, and group by case.
Top N keeps only the largest N categories in the table. All remaining categories are summed into the Other label you choose. The overall n stays the same, so percentages and cumulative totals remain consistent.
For each category, the interval estimates where the true population proportion may lie at your chosen confidence level. Wider intervals usually indicate smaller samples or rarer categories. It is a range, not a guarantee for any single run.
Enable it when responses are numbers like scores, times, or measurements. The tool will create ranges and count how many values fall into each bin. Use custom limits to control outliers or to match reporting standards.
Enter one expected number per displayed category, in the same order as the result table. You may provide probabilities that sum near one or counts. The calculator normalizes them to match n, then reports chi square, df, and p value.
The PDF is generated without external libraries, so it focuses on readable text and a compact table. For branded layouts, export CSV and style it in your reporting tool, then print to PDF with your preferred template.
Important Note: All the Calculators listed in this site are for educational purpose only and we do not guarentee the accuracy of results. Please do consult with other sources as well.