Overview of the main descriptive statistics
Let's now have a look at the most used descriptive statistics and see how you can adapt them to use a rolling window on any data stream. Of course, as you have seen in the previous chapter, streaming analytics can be executed on a multitude of tools. The important takeaway is to understand which descriptive analytics to use and to have a basis that can be adapted to different streaming input tools.
The mean
The first descriptive statistic that will be covered is the mean. The mean is the most commonly used measure of centrality.
Interpretation and use
Together with other measures of centrality, such as the median and the mode, its goal is to describe the center of the distribution of a variable. If the distribution is perfectly symmetrical, the mean, median, and mode will be equal. If there is a skewed distribution, the mean will be affected by the outliers and move in the direction of the skew or the outliers.
