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
- /
- SAS Nested Procedure shows dots

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

01-04-2012 07:46 AM

Hello,

I am working on a task concerning nested procedures.

The input is as follows:

data experiment;

input lot wafer site rho;

cards;

1 1 1 4.289

...

run;

Then I use the following commands:

proc print;

run;

proc sort;

by lot wafer site;

run;

proc nested;

class lot wafer site;

var rho;

run;

As output, I get the 'Nested random effects analysis of variance for variable rho'.

But the output shows some dots, for example: Variance source Site: There is a dot in the column of 'random sum of squares' in 'F value' and in 'Pr>F'.

Also in variance source Error, there are only dots or zeros.

Can anyone tell me why these dots are there?? And how I can get them away? => How can I solve this problem?

Thanks in advance and best regards,

Richard

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

Posted in reply to Richard

01-04-2012 08:11 AM

The first thing that I would think of would be incomplete data, so that all degrees of freedom are used. I would guess that there is only one observation per site within wafer within lot--hence no residual variability and no variance due to site. What happens if you fit:

proc nested;

class lot wafer;

var rho;

run;

The residual error in this case will be due to site within wafer within lot.

Steve Denham

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

Posted in reply to SteveDenham

01-10-2012 01:58 PM

Thank you very much!

Best regards,

Richard