An outlier can be defined in terms of quartiles, as any value which is:

either \(> Q_3 + 1.5×IQR \)

or \(< Q_1 - 1.5×IQR \)

Alternatively, an outlier can be defined in terms of the mean and standard deviation, as any value which is:

either \(> \bar{x} + 2\sigma \)

or \(< \bar{x} - 2\sigma \)

Questions may specify different parameters, such as \(\pm 3\sigma\).

Cleaning data is the process of removing outliers from a data set.