This tutorial explains how outliers can affect traditional statistics and introduces robust techniques to handle them. The sample median is a reliable way to estimate the middle value of data, and robust methods can also estimate the spread of the data effectively. By using 'z-scores', outliers can be easily identified. These techniques can be applied to large datasets for accurate averaging of curves or images. For multivariate data, a robust regression method is described, which helps in identifying outliers. Overall, robust statistics provide a more accurate and reliable way to analyze data compared to traditional methods.