BookmarkSubscribeRSS Feed
tbardsley
Calcite | Level 5

Hello Everyone!

 

I am generating a forest plot to present the results, odds ratios and 95% CIs, of many different logistic models.  I am using proc sgpanel to make a lattice of the multiple plots.  I would like like to have all of the vertical axes be the same for consistency, however some of the 95% CIs are quite large (up to a value of 20).  If I allow a max value of 20 for the axis then most of the other plots look squished.  Is there a good to keep the axis reasonably small and consistent?  Is there a way in the syntax to have a 'broken line' so that I don't have to show the plot lines extend all the way up to 20 for example?  I've attached an example plot of what i have thus far.  Thank you for any help!

2 REPLIES 2
Rick_SAS
SAS Super FREQ

I don't believe it is possible to "continue" a confidence interval across an axis break. An alternative is to use a logarithmic axis for the odds ratios. See the article "Odds ratio plots with a logarithmic scale in SAS", which includes code snippets and a discussion of the pros and cons of log axes. The article shows PROC SGPLOT, but the COLAXIS statement in PROC SGPANEL also supports the TYPE=LOG option.

tbardsley
Calcite | Level 5

Great thank you,  I'll check that out!

SAS Innovate 2025: Call for Content

Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 16. Read more here about why you should contribute and what is in it for you!

Submit your idea!

How to Concatenate Values

Learn how use the CAT functions in SAS to join values from multiple variables into a single value.

Find more tutorials on the SAS Users YouTube channel.

Click image to register for webinarClick image to register for webinar

Classroom Training Available!

Select SAS Training centers are offering in-person courses. View upcoming courses for:

View all other training opportunities.

Discussion stats
  • 2 replies
  • 788 views
  • 1 like
  • 2 in conversation