Sometimes a set of data will have one or more items with unusually large or unusually small values. Such extreme values are called outliers. Outliers often arise from some mistakes in data-gathering or data-recording procedures. It is good practice to inspect a data set for outliers first, before other statistical methods are applied to the data. While there are statistical techniques that can single out outliers for special attention, no statistical technique can decide, simply on the basis of the numbers, that a data point is spurious. By the same token, the term outlier means merely that a point is extreme, it does not mean it is spurious.