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
- /
- Analytics
- /
- Stat Procs
- /
- Base SAS (Geometric Means and Related)

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
- Permalink
- Email to a Friend
- Report Inappropriate Content

05-08-2017 11:32 AM - edited 05-08-2017 01:13 PM

I've seen similar posts but I am trying to determine if there is a simpler method for this:

1. Create log10 transformed values of x

2. Process through PROC MEANS to obtain mean, sd, median, min max

3. Raise each of the quantities in (2) to 10**(mean), etc. to get "mean", "SD", "min", and "max" values

4. Calculate dispersion factors

-All quantities based on output from Means procedure in step 2

dfplus=(**10****mean)+(**10****(mean+sd)-**10****(mean));

dfminus=(**10****mean)-(**10****(mean)-**10****(mean-sd));

Since I need to calculate grand mean, sd, min, max, dfplus, and dfminus by anaysis category, is there a way I can reduce the number of steps?

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

Posted in reply to Doug____

05-08-2017 01:05 PM

I don't understand what your question has to do with the title of this post, "Factor analysis using maximum likelihood estimation."

What are you trying to accomplish? What variables are you using in the factor analysis?

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

Posted in reply to Rick_SAS

05-08-2017 01:06 PM

I chose the incorrect select - can I edit the post so it will show up in the correct location?

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

Posted in reply to Doug____

05-08-2017 01:09 PM

Sure. You are welcome to edit the post title, add details, clarify your questions, and so forth.

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

Posted in reply to Doug____

05-09-2017 09:42 AM

Here could get you many statistical estimators .

```
data class;
set sashelp.class;
log_height=log(height);
run;
proc univariate data=class outtable=want noprint;
var log_height;
run;
```