In general, statistics can be divided into two categories based on their purposes: descriptive statistics and inferential statistics.
Descriptive statistics can be extended to summarize multivariate behaviours, via sample correlations, contingency tables, scatter plots, etc. They not only provide an easily understandable overview of the dataset; they also give analysts a chance to study the collected sample and investigate two important questions:
is the sample compatible with their understanding of the situation?
is the sample representative of the underlying population?
Inferential statistics, on the other hand, aim to facilitate the process of inference (induction) to the general population from which the sample is drawn.