| To: | <s-news@lists.biostat.wustl.edu> |
|---|---|
| Subject: | How to create a "summary" data frame |
| From: | "Hunsicker, Lawrence" <lawrence-hunsicker@uiowa.edu> |
| Date: | Mon, 22 Dec 2008 16:06:03 -0600 |
| Thread-index: | AclkgXtcoC+OxQCaRiC9gxzViQ/c+w== |
| Thread-topic: | How to create a "summary" data frame |
|
Hi, folks, and Happy Holidays to all:
I have a data frame with about 11,000 patients from about 600 different centers. Roughly half of these patients have had a certain test done, and the other half have not had the test. But the fraction with the test varies from center to center. I’d like to add a column to the data frame indicating the fraction of patients at each center that had the test done. I tried doing this using the GUI to calculate the average of 0 (no) and 1 (yes) values, doing the average by center, and saving the result. I get a list with a single value (the average) for each center, but the center IDs are not included, so that I can’t do a merge on center ID. How can I create a data frame with two columns, the first column being the center number, and the second being the fraction of patients with the test done? Larry Hunsicker
|
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | ANNOUNCEMENT: February Short Course - Regression Modeling Strategies, Frank E Harrell Jr |
|---|---|
| Next by Date: | Re: How to create a "summary" data frame, Alan Hochberg |
| Previous by Thread: | ANNOUNCEMENT: February Short Course - Regression Modeling Strategies, Frank E Harrell Jr |
| Next by Thread: | Re: How to create a "summary" data frame, Alan Hochberg |
| Indexes: | [Date] [Thread] [Top] [All Lists] |