Statistics for Data Science

Summarization modeling

The common practice of establishing multiple summarization points is through the development of a summation model. Simply put, to create a summarization model from the data is to create a table or data frame with the rows being mean, standard distribution, median, min, max, and a total for each component in the data (or at least each component in the data that you are interested in).

Let's use our previous data example, where we examined sales quantities by individual sales type group. Fortunately, R gives us simple functions to calculate our comparison points: max, mean, standard distribution, median, min, and sum.

We can use them to calculate each group's comparison points individually, as follows:

# --- create subset ...