turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- SAS Programming
- /
- SAS/GRAPH and ODS Graphics
- /
- Proc Freq FreqPlot with Column Percents

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

06-22-2011 03:42 PM

Hello,

I am using PROC FREQ to create some quick summary tables and plots for a large number of variables by two groups (Rx2 tables, e.g. sex*group, race*group, etc.). The options for the PLOTS = FREQPLOT () include a value for the scale as

SCALE=FREQ | LOG | PERCENT| SQRT

However, I would like SAS to graph the column percents rather than the overall percent, because unless the two groups have equal totals, this gives a misleading graph.

For instance:

Group 1 has 30 males out of 100 people.

Group 2 has 30 males out of 50 people.

SCALE = PERCENT graphs both groups as 20% (30/150 total); however, in reality, males account for 30% of group 1, but 60% of group two.

These two groups are not comparable with regard to sex, but the graph makes it appear as if they are.

Any ideas? I suppose I could edit the template, but I'm hoping to avoid that

Thanks,

Michael

I am using PROC FREQ to create some quick summary tables and plots for a large number of variables by two groups (Rx2 tables, e.g. sex*group, race*group, etc.). The options for the PLOTS = FREQPLOT (

SCALE=FREQ | LOG | PERCENT| SQRT

However, I would like SAS to graph the column percents rather than the overall percent, because unless the two groups have equal totals, this gives a misleading graph.

For instance:

Group 1 has 30 males out of 100 people.

Group 2 has 30 males out of 50 people.

SCALE = PERCENT graphs both groups as 20% (30/150 total); however, in reality, males account for 30% of group 1, but 60% of group two.

These two groups are not comparable with regard to sex, but the graph makes it appear as if they are.

Any ideas? I suppose I could edit the template, but I'm hoping to avoid that

Thanks,

Michael