Autocorrelation Error Interpretation

  • #1
1
0
Hello, I have a question on Autocorrelation of OLS model.
So I encountered a autocorrelation error, and use Cochrane - Orcutt Two-step Procedure(CORC) to fix it. And my OLS became GLS. And I have no idea how to interpret the coefficient on my initial X and Y with the new model. I mean something like, if X rise by 1 unit then Y rise by 3 units. Below are my real output
32739761_1896324580418118_637276870739492864_n.jpg
32739761_1896324580418118_637276870739492864_n.jpg
Please help me, thank you so much.
fyi: Y is outputs per hour ( productivity), X1 is wages/ week, X2 is working hours/week
 

Attachments

Last edited by a moderator:

Answers and Replies

  • #2
FactChecker
Science Advisor
Gold Member
5,743
2,132
Is the left hand side of the GLS autocorrelation fixed model correct? Shouldn't that be ##Y-0.71*Y(-1)##?
(see https://en.wikipedia.org/wiki/Cochrane–Orcutt_estimation )

And a small correction: 248*(1-0.71) = 71.92

With that in mind, the equation only gives you values for the change of ##Y## based on the change of the ##X_i##s. So if you want to apply it to current values of ##Y## and ##X_i##s, you would have to include the data from the prior time ( ##Y(-1)## and ##X_i(-1)##s ).
 
Last edited:
  • #3
BWV
648
569

Related Threads on Autocorrelation Error Interpretation

Replies
3
Views
5K
  • Last Post
Replies
2
Views
30K
  • Last Post
Replies
1
Views
4K
  • Last Post
Replies
1
Views
1K
  • Last Post
Replies
2
Views
3K
  • Last Post
2
Replies
33
Views
10K
Replies
1
Views
442
Replies
0
Views
4K
  • Last Post
Replies
5
Views
3K
Replies
3
Views
4K
Top