Open Qstat
Charts
StatisticsOutlier Test
Qstat Desktop
English

Outlier Test (IQR + Z-score)

Find outliers with a strict rule, highlight them in yellow in the table, and after your confirmation delete their rows or replace them with the mean, median or mode. Undo restores everything.

1Data Table

Paste a table copied from Excel into a cell (Ctrl+V). Click a column header (A, B…) before pasting to use the first line as column names. Double-click a header to rename it, right-click to insert/delete rows and columns, and formulas such as =A1*2 work too.

2Outlier Test Options

Outlier handling

How to run the outlier test

  1. Copy the measurement column to check and paste it into the data table (CSV and Excel files work too).
  2. Choose the input column and the handling (delete rows / replace with mean, median or mode). For replacement, also choose the output column.
  3. Press Run: outliers are highlighted in yellow and you are asked whether to apply the handling.
  4. Choose Yes to apply. Press Undo (Ctrl+Z) to revert.

Criteria

A value is an outlier only if it is below Q1-1.5×IQR or above Q3+1.5×IQR (the box-plot rule) and also more than 3 standard deviations from the mean (|Z|>3). Both rules must hold, so this is stricter than outlier handling based on a single rule.

At least 4 valid numeric values are required; the mean, standard deviation and quartiles use all valid values of the column.

Handling

Delete rows removes the whole rows that contain outliers. The replacement options write the column to the output column with the outliers replaced by the mean, median or mode of the remaining data (choosing the input column itself replaces in place). If the output column already has data, you are asked before overwriting.

Outlier criteria

  • Deleting or replacing is fine for measurement or entry errors, but if the outlier is a real process event, investigate the cause first.
  • Handling outliers changes the mean, standard deviation and capability indices, so record results before and after.
  • If there are no outliers, you are told that no outliers were found.

Frequently asked questions

How is it different from box-plot outliers?

The box plot uses only the IQR rule; this test also requires |Z|>3, so it catches only much more extreme values.

I deleted the wrong rows.

Use the Undo button above the data table or Ctrl+Z.

What happens to non-numeric cells?

They are excluded from the calculation. When writing a replacement to the output column, non-numeric cells are left blank.

Is my data sent to a server?

No. All calculations run inside your browser and nothing is transmitted or stored.

Other chart tools

Descriptive Statistics CalculatorGet 16 statistics - mean, SD, quartiles, skewness, kurtosis and more - in one table.Box Plot MakerCompare medians, quartiles and outliers of several groups side by side.Dot Plot MakerStack one dot per data point in each interval to show the distribution of small samples.

Need process capability, control charts or DOE?

The Qstat desktop program offers about 250 analysis features: histograms and box plots plus process capability (Cp, Cpk), control charts, measurement system analysis (MSA), design of experiments (DOE), regression and machine learning.

Try Qstat free for 30 days