Hello everyone,
I'm a new user of EViews. I was doing ordinal logistic regression with three ordinal independent variables. But when I was proceeding through estimate equation and generating result this error message "Unable to compute automatic estimates of starting values. Use user-supplied starting values." was popping up every time. Where was the error? Can anyone help me how to run a ordinal logistic regression through EViews?
Estimation
Moderators: EViews Gareth, EViews Moderator
-
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13316
- Joined: Tue Sep 16, 2008 5:38 pm
Re: Estimation
Sounds like EViews was unable to compute the starting values automatically. You should try user-supplied starting values instead.
Follow us on Twitter @IHSEViews
-
- Posts: 7
- Joined: Fri May 12, 2017 4:39 am
Re: Estimation
I'm not getting it. What does "user-supplied starting values" imply? What shall I do now?.....@EViews Gareth
-
- Fe ddaethom, fe welon, fe amcangyfrifon
- Posts: 13316
- Joined: Tue Sep 16, 2008 5:38 pm
Re: Estimation
Follow us on Twitter @IHSEViews
-
- Posts: 7
- Joined: Fri May 12, 2017 4:39 am
Re: Estimation
Got it. Results are coming now.
Thanks.
Thanks.
-
- Posts: 7
- Joined: Fri May 12, 2017 4:39 am
Re: Estimation
Hi,
I've attached a file here. I'm facing a problem when I'm copying result from EViews to elsewhere in estimation result. There are two options in Copy Options; "As Displayed" and "Using Highest precision". When copied as "Using Highest Precision", probability of "Product Effectiveness" is coming 5.97749 and when copied as "As Displayed", probability of that independent variable is coming 0.0001. This is huge variation in the result. Why does this result differ?
I've attached a file here. I'm facing a problem when I'm copying result from EViews to elsewhere in estimation result. There are two options in Copy Options; "As Displayed" and "Using Highest precision". When copied as "Using Highest Precision", probability of "Product Effectiveness" is coming 5.97749 and when copied as "As Displayed", probability of that independent variable is coming 0.0001. This is huge variation in the result. Why does this result differ?
- Attachments
-
- Result Variation.docx
- (21.99 KiB) Downloaded 247 times
-
- Non-normality and collinearity are NOT problems!
- Posts: 3775
- Joined: Wed Sep 17, 2008 2:25 pm
Re: Estimation
When you're copying highest precision and pasting into Word you're not showing the digits at the right. That's what the "..." means. You're probably missing something like "E-05."
-
- Posts: 7
- Joined: Fri May 12, 2017 4:39 am
Re: Estimation
Then what should I do? Copy as "As displayed" and what will show, will be the actual values?
-
- Non-normality and collinearity are NOT problems!
- Posts: 3775
- Joined: Wed Sep 17, 2008 2:25 pm
Re: Estimation
You may need to adjust the table width in Word.
Who is online
Users browsing this forum: No registered users and 14 guests