Statistical programming, matrix languages, and more

%goflogit Errors

Accepted Solution Solved
Reply
Contributor
Posts: 28
Accepted Solution

%goflogit Errors

[ Edited ]

I am running the %goflogit Macro for the goodness-of-fit of the Logit model I am running. Right off the bat, I have these errors, and I don't really know what they mean or what I should do to remedy the issue. These errors keep repeating 61 times. I found this post, which again can not pin to the problem I am facing: http://blogs.sas.com/content/iml/2010/11/29/how-to-interpret-sasiml-error-messages.html

 

Any help is highly appreciated.

 

Here is the output:

 

308 %goflogit (data=b, y=Y, xlist=X1 X2 X3 X4 X5 X1*X1, trials=num)

NOTE: Worksize = 2048000

NOTE: Symbol size = 204800

NOTE: IML Ready

statement : READ at line 8877 column 56

ERROR: (execution) Invalid argument to function.

operation : REPEAT at line 8888 column 32

operands : *LIT1004, n, *LIT1005

*LIT1004 1 row 1 col (numeric)

1

n 1 row 1 col (numeric)

0

*LIT1005 1 row 1 col (numeric)

1

statement : ASSIGN at line 8888 column 17

ERROR: (execution) Matrix has not been set to a value.

operation : // at line 8888 column 58

operands : design, design

design 0 row 0 col (type ?, size 0)

 

design 0 row 0 col (type ?, size 0)

 

 

 


Accepted Solutions
Solution
‎08-08-2017 08:49 AM
SAS Super FREQ
Posts: 3,752

Re: %goflogit Errors

You need to specify valid variable names that exist in the data set. The macro does not interpret interaction terms like X1*X1.

Instead, you need to generate the interaction yourself and create a new variable that contains the interaction term.

For information about how to create a design matrix, see 

"Four ways to create a design matrix in SAS"

or use the DATA step to create the interaction.

View solution in original post


All Replies
Solution
‎08-08-2017 08:49 AM
SAS Super FREQ
Posts: 3,752

Re: %goflogit Errors

You need to specify valid variable names that exist in the data set. The macro does not interpret interaction terms like X1*X1.

Instead, you need to generate the interaction yourself and create a new variable that contains the interaction term.

For information about how to create a design matrix, see 

"Four ways to create a design matrix in SAS"

or use the DATA step to create the interaction.

☑ This topic is solved.

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

Discussion stats
  • 1 reply
  • 248 views
  • 0 likes
  • 2 in conversation