Summary Procedures for Derived Variables

Summarizing Derived Variables

Numeric Variable: Age

  • Age is a numeric variable.
  • The appropriate procedure for summarizing numeric variables like age is the PROC MEANS procedure.
  • PROC MEANS generates summary statistics such as:
    • n (number of observations)
    • Mean
    • Standard deviation
    • Minimum value
    • Maximum value
  • In SAS code, PROC MEANS is used to obtain these statistics for the variable age.

Categorical Variable: Sex

  • Sex is a categorical variable with character type values.
  • The categories are male and female.
  • For categorical variables like sex, the PROC FREQ procedure is used to obtain summary statistics.
  • PROC FREQ generates:
    • Counts (number of occurrences of each category)
    • Percentages (percentage of each category)
  • This section of the table (section number two) containing counts and percentages will be built using the PROC FREQ procedure on the sex variable.

Categorical Variable: Race

  • Race is similar to sex; it is categorical and of character type.
  • It contains categories representing various races of the subjects.
  • The PROC FREQ procedure is also used to obtain the data portion for this section.
  • This procedure generates:
    • Counts (number of occurrences of each race)
    • Percentages (percentage of each race)