Statistics Calculator

Statistics Calculator

The statistics calculator computes statistics for numerical variables grouped by combinations of categorical variables. If the data contains only categorical variables, it computes the frequency and percentage of each combination. If the data contains only numerical variables, it computes statistics for each numerical variable.

How to use the statistics calculator

Statistics calculator with optional Excel input. Computes statistics such as minimum, maximum, sum, count, standard deviation, quartiles, IQR, and skewness. Handles both numerical and categorical data. Insert one or more columns, and the statistics calculator processes each separately.

How to enter data?

The page opens with an Example of two number columns; Example with groups adds three categorical columns. Your first paste replaces the Example, or press Clear to empty the table. Each column is one variable, and its name goes in the header row.

• Type - one value per cell. Enter moves to the cell below. Type the column's name in its header.
• A list - paste numbers separated by commas, semicolons or spaces, such as 12, 15, 18, 22, or type them into a cell of an empty column: they go one per row. A number such as 1,200 stays one number.
• Copy and paste from Excel, Google Sheets, or any tool that separates the cells with tabs and line breaks:
  • with the names row - click the first header cell, then paste;
  • without the names row - click the first cell under the header, then paste.
  The paste fills as many columns and rows as it needs.
• Open a file - press 'Choose Excel / CSV file' (.xlsx, .xls or .csv), or drag the file onto the table. The first row gives the column names. The first sheet is loaded; choose another one in 'Select sheet'.

Next to each column name, small squares show how the column is read: 1 2 = numbers, a b = labels (categories). Click them to switch. In a number column, empty cells, NA and N/A are missing values (More options - Missing values). Untick a column under Select the variables to leave it out of the results. Last Run brings back the data and the options of your last calculation.

How many rows can I enter?

The grid shows about 14 rows at a time and scrolls for more — type or paste as many rows as you need, there's no built-in limit for manual entry.

When you import a large Excel or CSV file (over 500 data rows), only the first 500 rows are shown and editable in the grid; the rest stay in memory and are still included in every calculation — a note above the grid ("Showing the first 500 of 1,155 rows…") tells you when this applies. All these counts — the rows shown, the 500-row import preview, and the total — are data rows only; the header row is never included.

Numerical data

Quantitative data, continuous variable or ordinal variable

Categorical data

Qualitative data, categorical variable

Choose the statistics that you want to present

Numerical and Categorical Data

1. Count (n) - number of observations, the count of valid values, excluding empty cells or non-numerical cells for quantitative data
2. Percentage - the percentage of valid values, excluding empty cells or non-numerical cells for quantitative data
3. Missing values - number of missing values - the count of empty cells or non-numerical cells for quantitative data.

Numerical data

1. Min - minimum, the lowest value.
2. Max - maximum, the highest value.
3. Range - the distance between the minimum and the maximum.
4. Mean (x̄) - the average.
5. Mean CI - the confidence interval of the mean.
6. Sum - the cumulative total of all the values.
7. Standard Deviation (S), the sample standard deviation. Use it when you have only a sample data.
8. Variance (S²) - the sample variance.
9. Standard Deviation (σ), the population standard deviation, use it when you have the entire population data.
10. SD CI - the confidence interval of the standard deviation.
11. Variance (σ²) - the population variance, use it when you have the entire population data.
12. Sum of squares - refers to the sum of the square distances of all the values from the mean.
13. Q1- quartile 1, the 25th percentile.
14. Median- quartile 2, the 50th percentile.
15. Q3- quartile 3, the 75th percentile.
16. IQR - InterQuartile Range - the different between Quartile 1 and Quartile 3.
17. Skewness - the symmetrical level of the probability distribution
18. Skewness shape - text description of the skewness and the p-value of the test for a difference from normal skewness.
19. Excess kurtosis - the kurtosis difference from the normal distribution, the Kurtosis measured the level of the tails.
20. Tails shape - text description of the kurtosis and the p-value of the test for a difference from normal kurtosis.
21. Outliers - using the Tukey's Fences
22. SW p-value - Shapiro Wilk test for normality. For more details, refer the Kolmogorov-Smirnov test
23. KS p-value - Kolmogorov-Smirnov test for normality based on the sample parameters (Lilliefors test). For other options, refer to the Kolmogorov-Smirnov test

Options

1. Outliers: extreme values. relevant only if you entered raw data.
   included - the calculator will calculate the outliers but will include them in the calculation.
   Excluded - The calculator will exclude the outliers before calculating the average and the standard deviation.
2. Format the numbers - the thousand separator and the decimal point.
3. Decimal Format - how to round the results?
   Smart When a resulting value is larger than one, the tool rounds it, but when a resulting value is less than one the tool displays the significant figures. Decimal places - the number of decimal places, except for the 'Count' and 'Num of Missing Value'.
4. Histogram - create a histogram for the data.
5. Boxplot - create a boxplot for the data.
6. Standardized - create table with standardized data for each variable. The standardized transformation is a way to compare data with different units of measure; it translates each value into a z-score.
   $z = \frac{x - \mu }{\sigma }$
7. Excel Pagination Display - the number of rows displayed per tab in the 'Enter data from Excel' option. This option displays the spreadsheet across multiple tabs.

Options

Cleaning the data

The calculator cleans the data but not the header, as follows:

1. Remove non-numerical characters - the calculator keeps only the following characters:
   numbers ('0'-'9'), minus ('-'), decimal point ('.'), and brackets ('(', ')').
2. Convert numbers in brackets to negative numbers.
3. Convert standalone minus signs to 0.

Examples

Should you exclude outliers?

It is important to exercise caution before excluding outliers from any calculation, as they may contain valuable information. However, excluding outliers from a histogram may significantly improve its visualization, even if the outliers are valid observations. If you choose to exclude outliers, the histogram maker will generate the chart without them. This method can create a more practical histogram that better represents the distribution of the majority of the data points.