The Statistical Analysis page summarizes every numeric column of the selected dataset. Optionally apply filters first to summarize only a subset of records (see Working with Data Filters).
Statistics calculated
| Statistic | Definition |
|---|---|
| Count | Number of valid numeric values used in the calculation. |
| Missing / Invalid | Empty cells, and non-empty cells that are not numbers. Both are excluded. |
| Sum, Mean | Total of the values, and the total divided by the count. |
| Median | The middle value when sorted (the 50th percentile). |
| Mode(s) | The most frequent value(s). Shown only when a value occurs more than once; ties list several values. |
| Minimum, Maximum, Range | Smallest and largest values, and their difference. |
| Variance, Standard deviation | Sample formulas, dividing by n − 1. Population values (dividing by n) are also shown for reference. Requires at least two values. |
| Quartiles (Q1, Q3), IQR | 25th and 75th percentiles, and the interquartile range Q3 − Q1. |
| Percentiles P5–P95 | Linear interpolation between closest ranks — the same method as Excel PERCENTILE.INC and NumPy's default. |
| Skewness | Adjusted Fisher–Pearson coefficient, as in Excel SKEW. Positive values indicate a longer right tail. Requires at least three values. |
Reading the results
- When the mean and median differ noticeably, the distribution is skewed; the median is often a better description of a typical value.
- A large standard deviation relative to the mean indicates widely spread values.
- A high number of missing or invalid values means the statistics describe only part of your records — check the data quality panel first.
Saving
Save the analysis to History to reopen it with the same settings, or create a report (see Generating Reports).