Programming the statistical procedures from SAS

PROC CALIS: Standardized Results for Linear Equations 9.3 vs 9.4

Accepted Solution Solved
Reply
New Contributor
Posts: 2
Accepted Solution

PROC CALIS: Standardized Results for Linear Equations 9.3 vs 9.4

The format of the Standardized Results for Linear Equations table of PROC CALIS has changed from version 9.3 to 9.4.  In 9.3 this table consisted of the standardized beta, the standard error and the t-statistic for each parameter and took up three rows per equation.  In 9.4 this information is summarized within the equation.  For example:

myY   =     0.1978(**) X1   +   0.2483(**) X2  +   0.1837(**) X3  + -0.00063(ns) X4    +   1.0000 e1

A separate table now reports the standard error and t and p values.

Two questions.  How you you set the significance level used in the equation summary?  Is it possible to revert the report back to the 9.3 format?

I am using TYPE= LINEQS but my assumption is that the equations table is the same for all types.


Accepted Solutions
Solution
‎07-16-2015 04:29 PM
SAS Super FREQ
Posts: 3,537

Re: PROC CALIS: Standardized Results for Linear Equations 9.3 vs 9.4

1) Use the ALPHA= option on the PROC CALIS statement

2) I don't see a table named "Standardized Results for Linear Equations."  What is the name of that ODS table when you use ODS TRACE ON?

View solution in original post


All Replies
Solution
‎07-16-2015 04:29 PM
SAS Super FREQ
Posts: 3,537

Re: PROC CALIS: Standardized Results for Linear Equations 9.3 vs 9.4

1) Use the ALPHA= option on the PROC CALIS statement

2) I don't see a table named "Standardized Results for Linear Equations."  What is the name of that ODS table when you use ODS TRACE ON?

New Contributor
Posts: 2

Re: PROC CALIS: Standardized Results for Linear Equations 9.3 vs 9.4

Ah yes, Alpha.  Thank you very much.

The standardized equations can be found in the results tree as:

Calis

+ Standardized Results

  + Equations

I tried to insert a picture but was not able to.

I am finding the new output less problematic than I thought it would be but I am still interested if the options exist to revert to prior formats.

🔒 This topic is solved and locked.

Need further help from the community? Please ask a new question.

Discussion stats
  • 2 replies
  • 251 views
  • 0 likes
  • 2 in conversation