There are a number of descriptive statistics that, like descriptive plots, provide basic information on the nature of a particular variable or set of variables.  A statistic is simply a number that summarizes or represents a set of observations of a particular variable.  

Before describing the statistics, it will be helpful to look at the summation operator, Σ (sigma), and summation notation.

Univariate descriptive statistics

In general, descriptive statistics--like the univariate descriptive plots--can be classified into three groups, those that measure 1) central tendency or location of a set of numbers, 2) variability or dispersion, and 3) the shape of the distribution.

• Univariate statistics details
• Univariate statistics examples

Bivariate Descriptive Statistics

A frequent goal in data analysis is to efficiently describe or measure the strength of relationships between variables, or to detect associations between factors used to set up a cross tabulation.  A related goal may be to determine which variables are related in a predictive sense to a particular response variable, or put another way, to learn how best to predict future values of a response variable.  Correlation (and regression analysis), along with measures of association constructed from tables,  provide the means for constructing and displaying such relationships.

Bivariate descriptive statistics allow the strength dependence of the relationship displayed in a scatter plot to be efficiently summarized, in much the same way that the univariate descriptive statistics provide efficient summaries of the information evident in univariate plots, but the form of the relationship and possible external influences are best detected using descriptive plots, or by specific analyses like regression.

• Bivariate descriptive statistics -- details and examples

Readings: 

Rossiter (Introduction ... ITC):  sections 4.15-4.16; Rogerson (Statistical Methods):  section 1.4