One and Two-Way Frequency Tables Using PROC FREQ STT 305 The

1
One and Two-Way Frequency Tables Using PROC FREQ

• STT 305

2
The FREQ Procedure

• FREQ is used to construct frequency tables
  (count/percentage) for variables in a data set.
• Tables may include from one to three variables
• FREQ can also produce tests for
  independence/association.

3
The FREQ Procedure

• General Syntax
• PROC FREQ lt options gt
• BY variables
• EXACT statistic-options lt / computation-options gt
  
• OUTPUT lt OUTSAS-data-set gt options
• TABLES requests lt / options gt
• TEST options
• WEIGHT variable lt / option gt
• No var statement.

4
The FREQ Procedure

• Default behavior
• proc freq datastt305.fish
• run
• is to give a frequency table for every variable
  in the data set.
• Each variable is taken as a classification
  variable, i.e. each distinct value is taken as a
  separate category.

5
The Table Statement

• The table statement is like the var statement in
  that it selects variables for analysis however,
  it will also affect the structure of the
  table(s).
• This case
• proc freq datastt305.fish
• table lt dam
• run

6
The Table Statement

• Produces a table for both dam and lake type

7
Using Formats

• Formats are recognized for any variable listed in
  the table statement and classes are constructed
  based on formatted values.
• Using these formats
• proc format
• value lake
• 1'Oligotrophic'
• 2'Eutrophic'
• 3'Mesotrophic'
• value dam
• 1'Yes'
• 0'No'
• value safety
• low-lt0.5'Safe'
• 0.5-lt1.0'Unsafe'
• 1.0-high'Dangerous'
• run

8
Using Formats

• With this code
• proc freq datastt305.fish
• table lt dam hg
• format lt lake. dam dam. hg safety.
• run
• Produces

9
Two-Way tables

• The operator can be used in the table statement
  to create a two dimensional table.
• Consider
• proc freq datastt305.fish
• table lthg
• format lt lake. hg safety.
• run

10
Two-Way tables
Legend for numbers in each cell
11
Two-Way tables
Ratio of these two
Percentage of the whole represented by this cell
12
Two-Way tables
Ratio of these two
Percentage of the row represented by this cell
13
Two-Way tables
Ratio of these two
Percentage of the column represented by this cell
14
Three-Way Tables

• Consider
• proc freq datastt305.fish
• table damlthg
• format lt lake. dam dam. hg safety.
• run
• Creates the two-way table for lake type and
  mercury for each level of dam (no yes).

15
Three-Way Tables
Three is the maximum number of variables that can
be used with the operator.
16
Practice Problems

• Using the birthweight data and the following
• Normal gestation is 259 days or more, less is
  premature (missing values are coded as 999)
• Smoking status is coded as
• 0, Never smoked
• 1, Currently smoke
• 2, Stopped smoking at pregnancy
• 3, Stopped before current pregnancy
• 9, Unknown
• Create

17
Practice Problem 1
18
Practice Problem 2 (page 1)
19
Practice Problem 2 (page 2)